|
19804
|
: [Platform] Refinemen... 24 m left100% L2Mon 11 M : [Platform] Refinemen... 24 m left100% L2Mon 11 May 16:36:22V APP#Client.oho 9w HubspotPaqinationService.phoapp > Services > Crm › Hubspot › Pagination › #* HubspotPaginationService.php › g HubspotPaginationService › executeSearchRequest()private tunction shouldswitchtoKevsetPaqlnation PaqinationState Sstate, 1nt SresultsPerPage: boolSshouldSwitch=sstate->reauestcount> 0s Estate->offset + SresultsPerPade Padinat IonConTiOAATONAL QUERY LAMEif ($shouldSwitch && $state->lastRecordId === null) {Sthis->logger->warning(' [Hubspot] Cannot switch to keyset pagination: lastRecordId is null', [results per page => SresultsPerPage'total query Uimit' = PaginationConfia:: TOTAL OUERY LIMITreturn false; // Continue with offset paginationDv 23 10~ OpportunitySyncStrategy• HubsnotLastModified@nenSvncStra..# HubspotLastModifiedSyncStrategy..# HubsootSinaleSyncstrategy.onp## HubspotSyncStrategyBase.php• HubsnotWebhookBatchSyncstrateg.Wwlallawwaawhuospotraginatlonservice.ong# PaginationConfig.phpPaginationstate.php> Redis~ Servicelraits# OpportunitySyncTrait.php• SvncCrmEntitiesTrait.phpwsuncrields.rait.ono• WriteCrmTrait.phr• Utils• Webhook# BatchSvncCollector.pho# BatchSvncRedisService.ohvCllient.nho* ClosedDealStagesService.oho* DealFieldsService.oho* DecorateActivitv.oho• FieldDefinitions.ohn• FieldTvneConverter.ohn# HubspotClientinterface.php# HubspotTokenManager.php# PayloadBuilder.php*- PemoteCrmOhiectManinulator.nhn€* PecnonceNormalize nhn# Service.php# SyncFieldAction.phpw SynckelatedActivitymanager.php# WebhookSyncBatchProcessor.phpIntearationapo• Listeners> MetadataMiarationV Pipedrive• OpportunitySvncStrateav• ProspectSearchStrateavOUTIINETIMELINGI8 JY-20725-le-HS-search-rate-limit* Oprivate function validateTokenIfNeeded(Client Sclient, PaginationState Sstate): voidif (Sstate->shouldValidateTokeno)Sstate-sundateLastTokenChecko.private functzon executesearchkequest(ctlent sclient, string sobjectlype, array spayload, Paginatzonstate sstate): arraytry {Client.php ~/liminr/app/Services/Crm/Hubspot - Definitions (2clacs Client eytends Raceflient imnlementc HuhsnotClientInterfaceaparam array<string, mixed> Spayload The search payload with filters, sorts, properties. etc.athrows HubsnotFycention On APT errore: @return array The search response with 'results', 'total', 'paging' keyspublic function search(string $objectType, array Spayload): array$endpoint = self::BASE URL . "/crm/v3/objects/{$objectType}/search";return Sthis->executeRequest(function () use (Sendpoint, $payload) {Sresponse = Sthis->qetInstance()->getClient()→>request('POST', Sendpoint. ['ison' => Spavload"166catch (\Exception Se) {if (sclient->isUnauthorizedException(Se)) ^Sthis->loager-swarnina(*Hubsoot) Got 401 durina pagination. attemoting token refresh'. "'team id' =s Sclient->aetConfia@->aetTeam@-saetIdOr.= Se_saetMeççane().]):celfont. soncurololidTokonl),pdatelastTokenCheck():try 1Sresult = Sclient-ssearch(SobiectTvne. Spavload)•@6A902• Client nhnann/Services/Crm/Huhsnotfunction search(string SobjectType, array $payload):> Client.php /_claude vscode fs_riaht:/Users/lukas/i...1• 2 C23 Review rate limit handli..Keview fate lmit nanaling tor nuospouo..<> HandleHubspotRateLimit…fix @tests/Unit/Services/Crm/Hubspot/Pagination/HubspotPaginationServiceTest.php and @tests/Unit/Jobs/Crm/MatchActivityCrmDataTest.php• The stries property doesn't exist on MatchActivityCrmData - it uses retryUntil() instead. That assertion should check maxExceptions . Let me fix that and continue with the remaining breaks• Edit MatchActivityCrmDataTest.phpSthis-sassertSame(3, Siob-stries):<this_sascertSame/200. Cioh_stimeout())•Sjob->uniqueFor()):ertSame([30, 90, 180]. Siob>backoff()):Sthis-sasserteptions):$this->assertSame(300, Sjob->timeout()):Sjob->uniqueFor()):Sthis->assertSame([3090,1801. Siob->backoff()):• Edit MatchActivitycrmDatarest.pnppublic function testFailedMethodLogsError(): voidSexception = new \RuntimeException('Test failure');public function testfailedMethodLogsErrorl: voidSexception = new \RuntimeException('Test failure');sencry:: shoulokeceivecapturecxception→>once→>wich SexcepcionSiob = new MatchAct ivitvermbatalactivitvid: 123.fromConfiauration: null.siob = new MatchAct ivitvermbataactivitvid: 123.fromConfiguration: null,remoteSearch: true• Now the pagination service test. The root problem is createMock(Client::class) mocks search() to return ! , so the hubspotClientMock->request() chain is never reached. The fix is to mocksearch() directly and drop the HTTP client chain entirely.• Write HubspotPaginationServiceTest.phpdeclare(strict tvnes-1).Summary of what was tixed and whyMatchActiv1tycrmDatatest — two changes:• $job->tries → $job-•maxExceptions : the job has no $tries property; it uses retryUntil() for retry bounding and maxExceptions for exception counting•unqueronewassertonso0e4ouhmaches140 00obane ne KaRaDonNuESchanderne ole valuesoudont matchtnetolehormuaten nelrson wasareadyiorokel• testFailedMethodLoosError:added \Sentrv::shouldReceive('caotureExcention' ->once@ since failedo now calls itHubspotPaginationServiceTest — structural fix:WHEo1Gn I1EstmoceedW9e1eindeS9eeen1ee9eseexoei1oeeieteeeto be Galledithrouatha cha n Bu aaEea teMoak Ca sten H lass limockse seaa te mool return[] ), so request() was never reached — every test was silently returning 0 results. Fixed by mocking search() directly on $clientMock, which is the actual boundary the pagination service interacts with.Dropped the now-unused sfactorvMock.ShubspotClientMock. and creatAdd coverage of new methods in Clientª HubspotPaginationService.ohd#Ask before edit.A tnkos Vovolil 160 minutoe ondlSpaces: 4 UTF-8 LF ( PHP 8 SignIn 8.3P 0...
|
Code
|
HubspotPaginationService.php — app
|
NULL
|
19804
|
|
19805
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 12 pending changes
12
Run and Debug (⇧⌘D)
SlackFileEditViewGoHistoryWindowHelpAPPDOCKER₴81DEV (docker)₴2APP (-zsh)-zsh* @param string SobjectType The object type('deals''companies''contacts''cal)* @param array<string, mixed>Spayload Thesearch payload with filters, sorts, prope* @return array The search response with'results''total''paging'keys* @throws RateLimitException When rate limit is hit* @throws HubspotException On API errors** @return array The search response with 'results', 'total', 'paging' keys*/public function search(string SobjectType, array Spayload): arrayend diff4) app/Console/Commands/JiminnyDebugCommand.php (statement_indentation)begin diff --/home/jiminny/app/Console/Commands/JiminnyDebugCommand.php+++/home/jiminny/app/Console/Commands/JiminnyDebugCommand.php-359,11+359,11 @ScrmService = ScrmResolver->prepareCrmService);-//-/1for ($i = 0; si < 3; Si++) {if (Si % 250) {Sthis->info("Syncing opportunity {Si}");Sthis->info("Matching contact {$i}");-1/-1/.+++++ScrmService->syncOpportunity('374720564');if ($i % 25=0{//Sthis->info("Syncing opportunity {$i}");Sthis->info("Matching contact {$i}");////}ScrmService->syncOpportunity('374720564');$crmService->matchByName('Robot');end diffFixed 4 of 5666 files in 146.870 seconds, 60.00 MB memory usedWhat's next:Try Docker Debug for seamless, persistent debugging tools in any containeror image →Learn more at https://docs.docker.com/go/debug-cli/lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~/jiminny/app (JY-20725-handle-HS-search-rate-lirHomeDMsActivityFilesLater..•More• [Platform) Refinemen…. 24 m left100% <78• Mon 11 May 16:36:24ED→Describe what you are looking forJiminny ...# contusion-clinic# curiosity_lab# engineering# general# jiminny-bg# platform-tickets# product_launches# random# releases# sofia-office# support# thank-yous# the_people_of jimi...^ Direct messagesP. Aneliya Angelova®. Galya DimitrovaPetko Kashinski&. Stefka StoyanovaVasil Vasilev&. Nikolay IvanovAneliya Angelova, ...Stoyan Tanev• VesE Lukas Kovalik y... 0::: AppsS Jira CloudToastGanala Cala# support8 346 0MessagesC FilesBookmarksKara Joneswas added .Tuesday, April 28th~More v+Wednesday, April 29th ~Lauren Hudson 12:58 PMHi team, I'm trying to set up auto detect for LesMills, but when I add a new playbook (because theywant it applied across all teams), it's pulling in a loadof activity types that l am not able to delete. Anyideas please?Screenshot 2026-04-29 at 10.54.42.png •1 reply 12 days agoLauren Hudson 6:17 PMHello, request from Norstella to update theirJiminny to match this shared spreadsheet. lssomebody from the support team able to helpplease?Numbers Document -Message #support+Аа...
|
Code
|
HubspotPaginationService.php — app
|
NULL
|
19805
|
|
18726
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 22 pending changes
22
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Testing
Claude Code
EXPLORER
EXPLORER
Explorer Section: app
Explorer Section: app
APP
HubspotLastModifiedByProfileSyncStrategy.php
HubspotLastModifiedCreatedRecentlyOpenSyncStrategy.php
HubspotLastModifiedCreatedRecentlySyncStrategy.php
HubspotLastModifiedOpenSyncStrategy.php
HubspotLastModifiedSyncStrategy.php
HubspotSingleSyncStrategy.php
HubspotSyncStrategyBase.php
HubspotWebhookBatchSyncStrategy.php
Pagination
HubspotPaginationService.php...
|
Code
|
HubspotPaginationService.php — app — Modified
|
NULL
|
18726
|
|
18728
|
Explorer (⇧⌘E)
V APP" services• Hubspol~ Oppor Explorer (⇧⌘E)
V APP" services• Hubspol~ OpportunitySyncStrategy....# HubspotSyncStrategyBase.php#* HubspotWebhookBatchSyncStrateg...v Paainationl## HubspotPaginationService.php M# PaginationConfig.php# PaginationState.phpProspectsearchstrategyPodicYMorico irete# OpportunitySyncTrait.phpw synccrmentitiesirait.php# SyncFieldsTrait.php* WriteCrmirait.php•UtilsWebhookmBatchSvncCollector.pho# BatchSvncRedisService.onv# Client.phpI ClosedDeaStagesService.ohoI DealFieldsService. phoDecorateActivitv.oho# FieldTvoeConverter.oho* HubsootClientinterface.ohv# HubspotTokenManager.php* PavloadBuilder.oho# PemoteCrmOhiectManinulator.nhn€ PacnonceNormalize nhn# Service.php# SyncFieldAction.php# SyncRelatedActivityManager.php# WebhookSyncBatchProcessor.php> IntegrationApp> Listeners) Motodotol> MigrationV Pipedrive> OpportunitvSvncStrateav> ProspectSearchStrateavwApifields.ohow Client.ohoI FieldDefinitions.ohoOUTIINETIMELINGiê JY-20725-handle-HS-search-rate-limit*+ Cc# MatchActivitvCrmData.pho MmRateLimitException.ohovI HandleHubspotRateLimit.ohomapp > Services > Crm › Hubspot › Pagination > «* HubspotPaginationService.php › .k?phpdeclare(strict tvoes=1):nanespace damenny bervices tertnudspottraganactonguse Jiminny services crm nuospoc cltent,e Client.php 9, MHubspotPaginationService.php - app — Modified## HubspotPaginationService.php M X02 C;& Preparation for Refi... in 18 m100% C4Mon 11 May 14:42:14Dv * M Muse JiminnvExcent.ions SocialAccountTokenInvalidExcention:socla Laccountlokenenvaulocxcepcion* achrows badkequestpublic functionClient $client,array spayload,getPaginatedDataGenerator(int Sottset = 0,int oStotal = 0,?strina &SlastRecordId = nul1Sstate = new PadinationState(offset: Soffset)$endpoint = Client::BASE_URL . "/crm/v3/objects/{$type}/search";SresultsPerPage = PayloadBuilder::MAX SEARCH REQUEST LIMIT:if ($this->shouldStopPagination($state, $teamId)) <aepalke$payload = $this->handlePaginationStrategy($payload, $defaultFilter, $state, $resultsPerPage, $teamId);sthis-svalidateTokentfNeeded Sclient. Sstate):if (Sstate->requestCount > 0) ^us leep ($delay);Spage = Sthis->executeSearchRequest(Sclient, Stype, Spayload, $state):Sstate->setTotal(Spage['total'] 2? 0):22 11.@ You have Docker installed on vour svstem. Do you want toinstall the recommended extensions from Microsoft for itaCnodderdfipup8 sign In 8.3...
|
Code
|
HubspotPaginationService.php — app — Modified
|
NULL
|
18728
|
|
18729
|
iTerm2ShellEditViewSessionScriptsProfilesWindowHel iTerm2ShellEditViewSessionScriptsProfilesWindowHelpIiol§ Preparation for Refi... in 18 mDEV (docker)-zshDOCKERcompiledeventsroutesviewsO ₴1DEV (docker)$2APP (-zsh)H3Jiminny-worker-processing-2:j1minny-worker-processing-2_00: stoppedjiminny-worker-processing-3:jiminny-worker-processing-3_00: stoppedjiminny-worker-processing-4:jiminny-worker-processing-4_00: stoppedjiminny-worker-processing-5:jiminny-worker-processing-5_00: stoppedjiminny-worker-processing-delayed: jiminny-worker-processing-delayed_00:stoppedworker-analytics:worker-analytics_00: stoppedworker-audio:worker-audio_00: stoppedworker-crm-update:worker-crm-update_00:stoppedworker-download:worker-download_00:stoppedworker-nudges:worker-nudges_00:stoppedjiminny-worker-processing-1:jiminny-worker-processing-1_00: stoppedworker:worker_00: stoppedworker-calendar:worker-calendar_00:stoppedworker-conferences:worker-conferences_00: stoppedworker-crm-sync:worker-crm-sync_00:stoppedworker-emails:worker-emails_00: stoppedworker-es-update:worker-es-update_00: stoppedartisan-schedule:artisan-schedule_00: stoppedartisan-schedule:artisan-schedule_00: startedjiminny-worker-processing-1:jiminny-worker-processing-1_00: startedjiminny-worker-processing-2:jiminny-worker-processing-2_00: startedjiminny-worker-processing-3:jiminny-worker-processing-3_00: startedjiminny-worker-processing-4:jiminny-worker-processing-4_00: startedjiminny-worker-processing-5:jiminny-worker-processing-5_00: startedjiminny-worker-processing-delayed: jiminny-worker-processing-delayed_00: startedworker:worker_00: startedworker-analytics:worker-analytics_00: startedworker-audio:worker-audio_00: startedworker-calendar:worker-calendar_00:startedworker-conferences:worker-conferences_00: startedworker-crm-sync:worker-crm-sync_00: startedworker-crm-update:worker-crm-update_00: startedworker-download:worker-download_00: startedworker-emails:worker-emails_00: startedworker-es-update:worker-es-update_00:startedworker-nudges:worker-nudges_00: startedroot@docker_lamp_1:/home/jiminny#php artisan jiminny: debugDispatching 100 MatchActivityCrmDatajobs (portal=2)Done.Watch logs and runjiminny:debug observeRateLimit to inspect cachestate.root@docker_lamp_1:/home/jiminny# ]84-zshX5100% <8• Mon 11 May 14:42:15181-zsh+ffmpegO ₴61.79ms DONE2.06ms DONE0.85ms DONE4.12ms DONEDEV...
|
Code
|
HubspotPaginationService.php — app — Modified
|
NULL
|
18729
|
|
18756
|
iTerm2ShellEditViewSessionScriptsProfilesWindowHel iTerm2ShellEditViewSessionScriptsProfilesWindowHelplho]Preparation for Refi... in 17 m100% <78• Mon 11 May 14:44:00181DEV (docker)-zshDOCKERcompiledeventsroutesviewsO ₴1DEV (docker)$2APP (-zsh)H3Jiminny-worker-processing-2:j1minny-worker-processing-2_00: stoppedjiminny-worker-processing-3:jiminny-worker-processing-3_00: stoppedjiminny-worker-processing-4:jiminny-worker-processing-4_00: stoppedjiminny-worker-processing-5:jiminny-worker-processing-5_00: stoppedjiminny-worker-processing-delayed: jiminny-worker-processing-delayed_00:stoppedworker-analytics:worker-analytics_00: stoppedworker-audio:worker-audio_00: stoppedworker-crm-update:worker-crm-update_00:stoppedworker-download:worker-download_00:stoppedworker-nudges:worker-nudges_00:stoppedjiminny-worker-processing-1:jiminny-worker-processing-1_00: stoppedworker:worker_00: stoppedworker-calendar:worker-calendar_00:stoppedworker-conferences:worker-conferences_00: stoppedworker-crm-sync:worker-crm-sync_00:stoppedworker-emails:worker-emails_00: stoppedworker-es-update:worker-es-update_00: stoppedartisan-schedule:artisan-schedule_00: stoppedartisan-schedule:artisan-schedule_00: startedjiminny-worker-processing-1:jiminny-worker-processing-1_00: startedjiminny-worker-processing-2:jiminny-worker-processing-2_00: startedjiminny-worker-processing-3:jiminny-worker-processing-3_00: startedjiminny-worker-processing-4:jiminny-worker-processing-4_00: startedjiminny-worker-processing-5:jiminny-worker-processing-5_00: startedjiminny-worker-processing-delayed: jiminny-worker-processing-delayed_00: startedworker:worker_00: startedworker-analytics:worker-analytics_00: startedworker-audio:worker-audio_00: startedworker-calendar:worker-calendar_00:startedworker-conferences:worker-conferences_00: startedworker-crm-sync:worker-crm-sync_00: startedworker-crm-update:worker-crm-update_00: startedworker-download:worker-download_00: startedworker-emails:worker-emails_00: startedworker-es-update:worker-es-update_00:startedworker-nudges:worker-nudges_00: startedroot@docker_lamp_1:/home/jiminny#php artisan jiminny:debugDispatching 100 MatchActivityCrmDatajobs (portal=2)Done.Watch logs and runjiminny:debug observeRateLimit to inspect cachestate.root@docker_lamp_1:/home/jiminny# ]84-zshX5screenpipe"O 8861.79ms DONE2.06ms DONE0.85ms DONE4.12ms DONE-zsh+DEV...
|
Code
|
HubspotPaginationService.php — app — Modified
|
NULL
|
18756
|
|
18757
|
Explorer (⇧⌘E)
Search (⇧⌘F)
50 lal"Preparati Explorer (⇧⌘E)
Search (⇧⌘F)
50 lal"Preparation tor kerl.. In 1/m100% C4 & • Mon 11 May 14:44:00HubspotPaginationService.php - app — Modifiede Client.php 9, M## HubspotPaginationService.php M XV APP• Hubspol~ Opportunity SyncStratey...** HubspotLastModifiedOpenSyncStra...** HubspotLastModifiedSyncStrategy....R HubspotSingleSyncStrategy.php** HubspotSyncStrategyBase.php*R HubspotWebhookBatchSyncStrateg...Pagination** HubspotPaginationService.php M* PaginationConfig.php* PaginationState.php→Hoal~ Servicelraits# OpportunitySyncTrait.php** SyncCrmEntitiesTrait.phpwsuncrields.rait.ono14 WriteCrmTrait.php• Utils• Webhook# BatchSvncCollector.oho# BatchSvncRedisService.ohvCllient.nho9.MI* ClosedDealStagesService.oho* DealFieldsService.oho# DecorateActivity.php#FieldDefinitions.ohnField TypeConverter.php# HubspotClientinterface.php#R HubspotTokenManager.php# PayloadBuilder.phpA RemoteCrmObjectManipulator.php* ResponseNormalize.php#R Service.php# SyncFieldAction.phpSyncRelatedActivityManager.php#4 WebhookSyncBatchProcessor.php> IntearationApp• Listeners> Metadata• MiarationV Pipedrive• OpportunitySvncStrateavProspectSearchStrateav> OUTLINE> TIMELINEPa JY-20725-handle-HS-search-rate-limit*+ Co# MatchActivitvCrmData.pho MR RateLimitException.php MI HandleHubspotRateLimit.onomapp > Services > Crm > Hubspot › Pagination › «* HubspotPaginationService.php › ..declare(strict_types=1);nanespace damenny bervices tertnuospottraganactonguse Jiminny services crm nuospoc cltent,Dv*@ M .•2 C;3 Claude Code XUntitledCaude codeuse Jiminny\Exceptions\SocialAccountTokenInvalidException;socla Laccountlokenenvaulocxcepcion* achrows badkequestpublic functiongetPaginatedDataGenerator(Client $client,array spayload,int Sottset = 0,int oStotal = 0,?strina &SlastRecordId = nul1Sstate = new PadinationState(offset: Soffset)$endpoint = Client::BASE_URL . "/crm/v3/objects/{$type}/search";SresultsPerPage = PayloadBuilder::MAX SEARCH REQUEST LIMIT:You've come to the absolutely right place!if (sthis-schouldStonPagination(Sstate. SteamTd)) AaepalkeSpayload = sthis->handlePaginationStrategy(Spayload, $defaultFilter, $state, sresultsPerPage, steamId);sthis-svalidateTokentfNeeded Sclient. Sstate):if Sstate->requestCount > 0) ^us leep ($delay);Spage = Sthis->executeSearchRequest(Sclient, Stype, Spayload, $state):Sstate->setTotal(Spage['total'] 2? 0):77 0:5= Prefer the Terminal experience? Switch back in Settinas. X.Reveiw the diff. Mostly @app/Jobs/Crm/MatchActivityCrmData.php,@apo/Exceptions/RateLimitException.oho. @app.Jobs/Middleware/HandleHubspotRateLimit.ono@app/Services/Crm/Hubspot/Client.php7 HubspotPaginationService.ohv‹> Edit automaticallyLn 1, Col 1Spaces: 4 UTF-8 LF ( PHp 8 Signin 8.3g...
|
Code
|
HubspotPaginationService.php — app — Modified
|
NULL
|
18757
|
|
16656
|
AI Notes: Off
Thread
Every huddle has a thread
Sen AI Notes: Off
Thread
Every huddle has a thread
Send messages, files, and links to everyone in the huddle. They’re saved as a thread in this direct message with
@Petko Kashinski
@Petko Kashinski
, so you can access it even after the huddle is done.
Also send as direct message
Also send as direct message
Hide thread
loading…
Petko Kashinski is in the huddle.: .
Windowiaeinalalle winnDekel Kachtinckn40 h"suppont Dally • In Zn 40m100% L2• Mon 11 May 12:14:09AskJiminnyReportActivityServiceTest -V- Al Notes: Off |Thread© Every huddle has a threadSend messages, files, and links to everyone in thehuddle. They're saved as a thread in this directmessage witn aretko Kasninski, so you canaccess it even arter the nudale is done.Reply...• Also send as direct messageiminny@localhost]4 HS_local [jiminny@localhost]→ console [S lAGINe)INFO: [Hubspot] DEBUG Getting headers {21.15 bMI"Jnnson,charser=utt-on1-SOF"H':"max-aqe=31536008* 1ncludeSubDomains: preload")nCascade0 HubSpot Rate Limi+0 ..however the iob MatchActivityCrmData.pho is for all CRMs. Will that cause anv issue? Finallv lets think of possible solutions on 100000 calss with onlv 900¡entials": "false"].sс=\"019e02d0-6fd8-7812-bdba-885b7ccb3ee3\",•"nosniff".1": ["019e02d0-6fd8-7812-bdba-885b7ccb3ee3"],UrtdQgXVrik50pdqF6hZVYKhzTnQBidvMabeCtm0Y-1778163675-1.0.1.domain= hubani com: Httnûnlv• Secunp' SameSite=Nono")..successtullThinking•could miticate this with a Redis SEINX lock to serialize the probe so oniy one worker probes at a time, but that adds complexity. The simoler approach is to fustaccept the bounded waste as a reasonable tradeoff. Alternatively, I could use a Redis INCR pattern or a SETNX sentinel value to control the probing more precisely.иет укоае сvетса стетолу eхs єшuos зoes eяsosales оксетани тресиvеташсаска о uееас сvа за uw аоu галу сасhеоенел, шeшаdеwа сhаши: шЕmisleading, but functionally it works for any provider that throws that exception type. I could either rename it to something more generic or leave it as-is sinceHubSpot is the primary use caseFor the 100k jobs hitting the 9k ceiling, I'm looking at three main approaches: extending the retry window from 30 minutes to 6 hours to allow more jobs through,implementina dispatch-side throttlina to drio jobs into the queue aradually over several hours, or restructuring to use HubSpot's batch endpoints which couldprocess 100 activities per call instead of one, giving a 100x throughput improvement.Beyond those, l'm considering caching repeated CRM lookups to reduce actual API calls, deferring to off-peak hours when quota is fresher, pre-filtering activitiesbefore dispatch to remove ones that can't be matched, or dedicating a fixed worker pool to this queue so the natural concurrency aligns with HubSpot's 5 RPS limit—ensurina we stav under the cao by desian rather than hittina rate limits..cloudflare.com\\/report\\/v4?s=NYAlsVTP0fYm32qrSDjxYE4sd2RW|2098-4541-b9za-adta/SboYeab",104-9405-0e5b551e5545thina (84L)Claude Qnus 4.7 Medium26.52UTE.Río 4 spaces...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16656
|
|
16657
|
AI Notes: Off
Thread
Every huddle has a thread
Sen AI Notes: Off
Thread
Every huddle has a thread
Send messages, files, and links to everyone in the huddle. They’re saved as a thread in this direct message with
@Petko Kashinski
@Petko Kashinski
, so you can access it even after the huddle is done.
Also send as direct message
Also send as direct message
Hide thread
loading…
Petko Kashinski is in the huddle.: .
Hide thread
Windowhelt40 hl"suppont Dally • In Zn 40m100% 1• Mon 11 May 12:14:12iaeinalalle winniwe kel kachtinckinV- Al Notes: Off |Thread© Every huddle has a threadSend messages, files, and links to everyone in thehuddle. They're saved as a thread in this directmessage witn aretko Kasninski, so you canaccess it even arter the nudale is done.Reply..• Also send as direct messageiminny@localhost]4 HS_local [jiminny@localhost]→ console [S lAGINe)INFO: [Hubspot] DEBUG Getting headers {:21:15 GMT"],nson,charser=utt-on1-SOF"H':"max-aqe=31536008* 1ncludeSubDomains: preload")n¡entials": "false"].sс=\"019e02d0-6fd8-7812-bdba-885b7ccb3ee3\",•"nosniff".1": ["019e02d0-6fd8-7812-bdba-885b7ccb3ee3"],UrtdQgXVrik50pdqF6hZVYKhzTnQBidvMabeCtm0Y-1778163675-1.0.1.domain=.hubapi.com; Http0nly; Secure; SameSite=None"],Cascade0 HubSpot Rate Limihowever the iob MatchActivityCrmData.pho is for all CRMs. Will that cause anv issue? Finallv lets think of possible solutions on 100000 calss with onlv 900successtullThought for 42s1. The race window: A populates cache while B is still waitingYou've identified a real race. Let me trace it precisely with 10 workers.T = 0.000s: Initial stateCache: emptyWorkers 1-10: idleQueue: 100k jobsT = 0.000s to T = 0.005s: 10 workers all reach line 80+0 •.cloudflare.com\\/report\\/v4?s=NYAlsVTP0fYm32qrSDjxYE4sd2RVT=0.000: Worker A pops job,reaches line 80 - Redis::qet → nullT=0.001: Worker B pops job, reachesline 80 - Redis::get → null - cache still emptyT=0.002: Worker C pops nob, reachesLine 80 - Redis::get → null•. all 10 workers nass the cache check)T=0.005: All 10 workers now in flight, each making a real HTTP call to HubSpotT = 0.005s to T = 0.155s: 10 parallel HTTP callsT=0.005..02098-4541-09za-adta/SboYeab".104-9405-0e5b551e5545ing 884LW Windsurf Teamofo 4 spaces...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16657
|
|
16658
|
AI Notes: Off
Thread
Every huddle has a thread
Sen AI Notes: Off
Thread
Every huddle has a thread
Send messages, files, and links to everyone in the huddle. They’re saved as a thread in this direct message with
@Petko Kashinski
@Petko Kashinski
, so you can access it even after the huddle is done.
Also send as direct message
Also send as direct message
Hide thread
loading…
Petko Kashinski is in the huddle.: .
Hide thread
SlackFileEditViewGoHistoryWindowHelp<DEV (docker)• жз• Support Daily - in 2h 46 mDOCKERO 81DEV (docker)882APP (-zsh)|masterJY-20818-move-AJ-reports-to-separated-datadog-metricJY-20773-fix-automated-reports-user-pilot-trackingJY-20157-AJ-report-not-send-notificationJY-20508-notify-before-AJ-report-expirationJY-20372-ai-reports-promotion-pagesJY-20352-sync-opportunities-without-a-local-owner-user-id-is-nullJY-20738-debug-AJ-tracking-UPJY-18909-automated-reports-ask-jiminnyJY-20692-fix-integration-app-[API_KEY] laysJY-20698-fix-SF-activity-types-on-new-playbookJY-20543-AJ-report-trackingJY-20384-handle-auto-sync-with-no-access-to-event-typeJY-20458-ask-Jiminny-user-definitionsJY-19666-fix-import-contacts-account-associationJY-19666-HS-import-contacts-and-accounts-batch-jobJY-20458-Ask-Jiminny-ReportsJY-20200-batch-update-CRM-objects-SalesforceJY-19666-HS-webhooks-add-contact-and-companyJY-20348-trigger-setup-DI-layout-on-team-creationJY-20326-refactor-info-message-in-commandJY-20317-fix-auto-log-delay-issue-on-all-channels-disabledJY-20312-remove-on-update-change-last-synced-at-crm-configurationsJY-20306-SF-skip-auto-sync-for-task-based-playbookJY-20192-remove-deleted-team-from-saved-search-filtersJY-20197-import-opportunity-batch-jobJY-20293-enable-status-field-for-pipedrive-dealsJY-20191-remove-commands-interactive-promptsJY-20118-change-default-sync-strategyJY-20183-add-cache-on-auto-log-delayJY-20197-add-import-opportunity-batch-job20118-hs-opportunity-make-webhook-strategy-defaultJY-20118-make-default-hs-opportunity-sync-strategy-webhook-basedJY-20196-handle-opportunity-without-noteJY-20118-improve-opportunity-importJY-20189-handle-activity-search-on-deleted-groupsJY-20160JY-20145-filter-out-converted-leads-when-matchingJY-20150-skip-push-summary-on-summary-ready-1f-autologJY-20132-fix-note-encodingJY-19792-clean-logslukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~/jiminny/app (JY-20725-handle-HS-search-rate-limit) $ devroot@docker_lamp_1:/home/jiminny# ]-zsh84-zsh885100% |8• Mon 11 May 12:14:12181screenpipe"0 ₴6DEV...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16658
|
|
16659
|
AI Notes: Off
loading…
Petko Kashinski is in the h AI Notes: Off
loading…
Petko Kashinski is in the huddle.: .
Open thread
SlackcalVIewActivityMoreJiminny …..v# general# jiminny-bg# platform-tickets# product_launches# random# releasessoha-otnce# support# thank-yous# the_people_of jimi...6- Direct messages.. Petko..Oa 02a. Stefka Stoyanova€. Vasil VasilevC. Nikolay IvanovP. Galya Dimitrova E3 Aneliya Angelova,..2. Stoyan Tanev E@. VesA. Aneliya AngelovaJames Graham. Lukas Kovali.#: Apps6д Huddle with Petko Kashinski~ D OpportunitySyncStiD concernsC) HubspotLastmo(C) =uosootLastMorc) =uosootLastMo(C) HubspotLastMo©HubspotLastMor(C) HubsnotSinaleS© HubspotSyncStr(C) HubspotWebhorv O Pagination© PaginationConfic(C) PadinationStatemistonWindowhelp© Petko KashinskiMessagest Add canvasO FilesWednesday. April 22ndvКакво ставаPetko Kashinski 6:50PMНама плоблеміОправих се ®Lukas Kovallik 6.50 PMPetko Kashinski 12:11 PMЛукасИмаш ли 2 минутки ? (edited)Lukas Kovalik ® 12:13 PMздрасти даPetko Kashinski 12:13 PMМоже ли ла зрінна?Lukas Kovalik M 12:13 PNYou loined the huddle LIVE 12:14 PMIPetko Kashinski is here toolMessage Petko Kashinski+ Аa I© HubSpot/Service.php© SyncRelatedActivityManager.phpI.onpCachedcrmservicebecorator.onp© ProspectCache.phpС RematchActivityOnCrmObjectDetach.ongiVityservice.pnp© MatchCrmData.php*RateLimitexception.phpA12Aneratord$state->totalRecords,round ($state->getElapsedSeconds(), precisioon: 2),st' => $state-›requestCount › 0 ? round( num: $state->getElapsedSeconds()coraLoion(PaginationState $state, int $teamId): boolf...}crateqysetPagination(PaginationState $state, int SresultsPerPage): boolf...}Al Notes: OffLeaveprivate function validateTokenIfNeeded(Client $client, PaginationState $state): void{...}lusageprivate function executeSearchRequest(Client $client, string $objectType, array $payload, PaginationStatetry freturn $client->search($objectType, Spayload);} catch (\Exception $e) {if ($client->isUnauthorizedException(Se)) {Sthis->logger->warning('[Hubspot] Got 401 during pagination, attempting token refresh', I'team_id' => $client->getConfig()->getTeam()->getId(),'error' => $e->getMessage®1);Scuient->ensureValidTokenos50 lhl( Support Daily - in 2h 46m100% C2&• Mon 11 May 12:14:156 Huddle with Petko KashinskiE custom.log xE laravel.logA SF U*= Al Notes: Off# console [PKOb.# console leu)~/Library/Application Support/JetBrains/PhpStorm2026.1/consoles/db/d1e2c340-64e9-49c6-aa9a-196201874532/SF.sql:2026-05-07 14:21:15] L"headers":{"Vace"."Inu,U/ May 2020 14"Transter-Encodinq": |"chun"CF-Ray":"9t80deb8dbo0dcs"server-timing": ["hcid; de:cfr; desc=|"9f80deb8e7c6di"x-content-type-options""Set-Cookie":["__cf_bm=S!07-May-26 14:51:15 GMT;"Report-To" : ["{("urz\":\"https:\\/\\/a.nel"group\": \"cf-nel\","max_age\":604800}"],"NEL": ["€("success_fraction\":0.01,("report_to\":\"cf-nel\","max_age\":604800}"],'Server" : ["cLoudflare"]}} {'trace_id":"c7ab8365-903f-44Open threadLeave...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16659
|
|
16660
|
AI Notes: Off
loading…
Petko Kashinski is in the h AI Notes: Off
loading…
Petko Kashinski is in the huddle.: .
Open thread
SlackFileEditViewGoHistoryWindowHelp<DEV (docker)• *з.• Support Daily - in 2h 46 mDOCKERO 81DEV (docker)882APP (-zsh)|masterJY-20818-move-AJ-reports-to-separated-datadog-metricJY-20773-fix-automated-reports-user-pilot-trackingJY-20157-AJ-report-not-send-notificationJY-20508-notify-before-AJ-report-expirationJY-20372-ai-reports-promotion-pagesJY-20352-sync-opportunities-without-a-local-owner-user-id-is-nullJY-20738-debug-AJ-tracking-UPJY-18909-automated-reports-ask-jiminnyJY-20692-fix-integration-app-[API_KEY] laysJY-20698-fix-SF-activity-types-on-new-playbookJY-20543-AJ-report-trackingJY-20384-handle-auto-sync-with-no-access-to-event-typeJY-20458-ask-Jiminny-user-definitionsJY-19666-fix-import-contacts-account-associationJY-19666-HS-import-contacts-and-accounts-batch-jobJY-20458-Ask-Jiminny-ReportsJY-20200-batch-update-CRM-objects-SalesforceJY-19666-HS-webhooks-add-contact-and-companyJY-20348-trigger-setup-DI-layout-on-team-creationJY-20326-refactor-info-message-in-commandJY-20317-fix-auto-log-delay-issue-on-all-channels-disabledJY-20312-remove-on-update-change-last-synced-at-crm-configurationsJY-20306-SF-skip-auto-sync-for-task-based-playbookJY-20192-remove-deleted-team-from-saved-search-filtersJY-20197-import-opportunity-batch-jobJY-20293-enable-status-field-for-pipedrive-dealsJY-20191-remove-commands-interactive-promptsJY-20118-change-default-sync-strategyJY-20183-add-cache-on-auto-log-delayJY-20197-add-import-opportunity-batch-job20118-hs-opportunity-make-webhook-strategy-defaultJY-20118-make-default-hs-opportunity-sync-strategy-webhook-basedJY-20196-handle-opportunity-without-noteJY-20118-improve-opportunity-importJY-20189-handle-activity-search-on-deleted-groupsJY-20160JY-20145-filter-out-converted-leads-when-matchingJY-20150-skip-push-summary-on-summary-ready-1f-autologJY-20132-fix-note-encodingJY-19792-clean-logslukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~/jiminny/app (JY-20725-handle-HS-search-rate-limit) $ devroot@docker_lamp_1:/home/jiminny# ]-zsh84-zsh885100%8• Mon 11 May 12:14:44181ffmpeg886DEV...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16660
|
|
16661
|
AI Notes: Off
loading…
Petko Kashinski is in the h AI Notes: Off
loading…
Petko Kashinski is in the huddle.: .
Open thread
SlackcalVIewActivityMoreJiminny …..v# general# jiminny-bg# platform-tickets# product_launches# random# releasessoha-otnce# support# thank-yous# the_people_of jimi...6- Direct messages.. Petko..Oa 02a. Stefka Stoyanova€. Vasil VasilevC. Nikolay IvanovP. Galya Dimitrova E3 Aneliya Angelova,..2. Stoyan Tanev E@. VesA. Aneliya AngelovaJames Graham. Lukas Kovali.#: Apps6д Huddle with Petko Kashinski~ D OpportunitySyncStiD concernsC) HubspotLastmo(C) =uosootLastMorc) =uosootLastMo(C) HubspotLastMo©HubspotLastMor(C) HubsnotSinaleS© HubspotSyncStr(C) HubspotWebhorv O Pagination© PaginationConfic(C) PadinationStatemistonWindowhelp© Petko KashinskiMessagest Add canvasO FilesWednesday. April 22ndvКакво ставаPetko Kashinski 6:50PMНама плоблеміОправих се ®Lukas Kovallik 6.50 PMPetko Kashinski 12:11 PMЛукадИмаш ли 2 минутки ? (edited)Lukas Kovalik ® 12:13 PMздрасти даPetko Kashinski 12:13 PMМоже ли ла зрінна?Lukas Kovalik M 12:13 PNYou loined the huddle LIVE 12:14 PMIPetko Kashinski is here toolMessage Petko Kashinski+ Аa I© HubSpot/Service.php© SyncRelatedActivityManager.phpI.onpCachedcrmservicebecorator.onp© ProspectCache.phpС RematchActivityOnCrmObjectDetach.ongiVityservice.pnp© MatchCrmData.php*RateLimitexception.phpA12Aneratord$state->totalRecords,round ($state->getElapsedSeconds(), precisioon: 2),st' => $state-›requestCount › 0 ? round( num: $state->getElapsedSeconds()coraLoion(PaginationState $state, int $teamId): boolf...}crateqysetPagination(PaginationState $state, int SresultsPerPage): boolf...}Al Notes: OffLeaveprivate function validateTokenIfNeeded(Client $client, PaginationState $state): void{...}lusageprivate function executeSearchRequest(Client $client, string $objectType, array $payload, PaginationStatetry freturn $client->search($objectType, Spayload);} catch (\Exception $e) {if ($client->isUnauthorizedException(Se)) {Sthis->logger->warning('[Hubspot] Got 401 during pagination, attempting token refresh', I'team_id' => $client->getConfig()->getTeam()->getId(),'error' => $e->getMessage®1);Scuient->ensurevauidTokeno30 ll"suppont Dally • In Zn 40m100% Lz• Mon 11 May 12:14:476 Huddle with Petko KashinskiE custom.log xlaravel.logA SF UA console (PROD]A console (EU]:2026-05-07 14:21:15] local"headers":{"Vace"."Inu,U/ May 2020 14"Transter-Encodinq": |"chun"CF-Ray":"9t80deb8dbo0dcs*= Al Notes: Off27W NI"server-timing": ["hcid; de:cfr; desc=|"9f80deb8e7c6di"x-content-type-options""Set-Cookie":["__cf_bm=S!07-May-26 14:51:15 GMT;"Report-To" : ["{("urz\":\"https:\\/\\/a.nel"group\": \"cf-nel\","max_age\":604800}"],"NEL": ["€("success_fraction\":0.01,("report_to\":\"cf-nel\","max_age\":604800}"],'Server" : ["cLoudflare"]}} {'correlation_id":"95236535-1'trace_id":"c7ab8365-903f-44Leave...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16661
|
|
16662
|
AI Notes: Off
loading…
Petko Kashinski is in the h AI Notes: Off
loading…
Petko Kashinski is in the huddle.: .
SlackFileEditViewGoHistoryWindowHelp<DEV (docker)• жз• Support Daily - in 2h 46 mDOCKERO 81DEV (docker)882APP (-zsh)|masterJY-20818-move-AJ-reports-to-separated-datadog-metricJY-20773-fix-automated-reports-user-pilot-trackingJY-20157-AJ-report-not-send-notificationJY-20508-notify-before-AJ-report-expirationJY-20372-ai-reports-promotion-pagesJY-20352-sync-opportunities-without-a-local-owner-user-id-is-nullJY-20738-debug-AJ-tracking-UPJY-18909-automated-reports-ask-jiminnyJY-20692-fix-integration-app-[API_KEY] laysJY-20698-fix-SF-activity-types-on-new-playbookJY-20543-AJ-report-trackingJY-20384-handle-auto-sync-with-no-access-to-event-typeJY-20458-ask-Jiminny-user-definitionsJY-19666-fix-import-contacts-account-associationJY-19666-HS-import-contacts-and-accounts-batch-jobJY-20458-Ask-Jiminny-ReportsJY-20200-batch-update-CRM-objects-SalesforceJY-19666-HS-webhooks-add-contact-and-companyJY-20348-trigger-setup-DI-layout-on-team-creationJY-20326-refactor-info-message-in-commandJY-20317-fix-auto-log-delay-issue-on-all-channels-disabledJY-20312-remove-on-update-change-last-synced-at-crm-configurationsJY-20306-SF-skip-auto-sync-for-task-based-playbookJY-20192-remove-deleted-team-from-saved-search-filtersJY-20197-import-opportunity-batch-jobJY-20293-enable-status-field-for-pipedrive-dealsJY-20191-remove-commands-interactive-promptsJY-20118-change-default-sync-strategyJY-20183-add-cache-on-auto-log-delayJY-20197-add-import-opportunity-batch-job20118-hs-opportunity-make-webhook-strategy-defaultJY-20118-make-default-hs-opportunity-sync-strategy-webhook-basedJY-20196-handle-opportunity-without-noteJY-20118-improve-opportunity-importJY-20189-handle-activity-search-on-deleted-groupsJY-20160JY-20145-filter-out-converted-leads-when-matchingJY-20150-skip-push-summary-on-summary-ready-1f-autologJY-20132-fix-note-encodingJY-19792-clean-logslukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~/jiminny/app (JY-20725-handle-HS-search-rate-limit) $ devroot@docker_lamp_1:/home/jiminny# ]-zsh84-zsh885100% |8• Mon 11 May 12:14:51181screenpipe"0 ₴6DEV...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16662
|
|
16663
|
AI Notes: Off
loading…
Petko Kashinski is in the h AI Notes: Off
loading…
Petko Kashinski is in the huddle.: .
SlackcalVIewActivityMoreJiminny...v# general# jiminny-bg# platform-tickets# product_launches# random# releasessoha-otnce# support# thank-yous# the_people_of jimi...6- Direct messages.. Petko..Oa 02a. Stefka Stoyanova€. Vasil VasilevC. Nikolay IvanovP. Galya Dimitrova E3 Aneliya Angelova,..2. Stoyan Tanev E@. VesA. Aneliya AngelovaJames Graham. Lukas Kovali.#: Apps6д Huddle with Petko Kashinski~ D OpportunitySyncStiD concernsC) HubspotLastmo(C) =uosootLastMorc) =uosootLastMo(C) HubspotLastMo©HubspotLastMor(C) HubsnotSinaleS© HubspotSyncStr(C) HubspotWebhorv O Pagination© PaginationConfic(C) PadinationStatemistonWindowhelp© Petko KashinskiMessagest Add canvasO FilesWednesday. April 22ndvКакво ставаPetko Kashinski 6:50PMНама плоблеміОправих се ®Lukas Kovallik 6.50 PMPetko Kashinski 12:11 PMЛукасИмаш ли 2 минутки ? (edited)Lukas Kovalik ® 12:13 PMздрасти даPetko Kashinski 12:13 PMМоже ли ла зрінна?Lukas Kovalik M 12:13 PNYou loined the huddle LIVE 12:14 PMIPetko Kashinski is here toolMessage Petko Kashinski+ Аa I© HubSpot/Service.php© SyncRelatedActivityManager.phpI.onpCachedcrmservicebecorator.onp© ProspectCache.phpС RematchActivityOnCrmObjectDetach.ongiVityservice.pnp© MatchCrmData.php*RateLimitexception.phpA12Aneratord$state->totalRecords,round ($state->getElapsedSeconds(), precisioon: 2),st' => $state-›requestCount › 0 ? round( num: $state->getElapsedSeconds()coraLoion(PaginationState $state, int $teamId): boolf...}crateqysetPagination(PaginationState $state, int SresultsPerPage): boolf...}Al Notes: OffLeaveprivate function validateTokenIfNeeded(Client $client, PaginationState $state): void{...}lusageprivate function executeSearchRequest(Client $client, string $objectType, array $payload, PaginationStatetry freturn $client->search($objectType, Spayload);} catch (\Exception $e) {if ($client->isUnauthorizedException(Se)) {Sthis->logger->warning('[Hubspot] Got 401 during pagination, attempting token refresh', I'team_id' = $client->getConfig()->getTeam()->getId(),'error' => $e->qetMessage(1);Scuient->ensurevauidTokeno30 ll"suppont Dally • In Zn 40m100% L28• Mon 11 May 12:14:516 Huddle with Petko KashinskiE custom.log xE laravel.logA SF U# console [PKOb.A console (EU]:2026-05-07 14:21:15] local"headers":{"Vace"."Inu,U/ May 2020 14"Transter-Encodinq": |"chun"CF-Ray": ["9f80deb8db60dc3"server-timing": ["hcid; de:cfr; desc=|"9f80deb8e7c6di"x-content-type-options""Set-Cookie":["__cf_bm=S!07-May-26 14:51:15 GMT;"Report-To" : ["{("urz\":\"https:\\/\\/a.nel"group\": \"cf-nell","max_age\":604800}"],"NEL": ["€("success_fraction\":0.01,("report_to\":\"cf-nel\","max_age\":604800}"],'Server" : ["cLoudflare"]}} {'correlation_id":"95236535-1'trace_id":"c7ab8365-903f-44*= Al Notes: OffLukas Kovalik•*• Petko Kashin3==PSLeave...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16663
|
|
16696
|
Petko Kashinski
Petko Kashinski, Screen share
Petk Petko Kashinski
Petko Kashinski, Screen share
Petko Kashinski
Screen share
Turn on drawing
Fullscreen
Back to grid
View Lukas Kovalik's profile
video is off, audio is on
More actions
Audio
View Petko Kashinski's profile
Petko Kashinski
More actions
Video
loading…
Petko Kashinski is in the huddle.: .
PnostorimINavicatecodeFV faVsco.js?9 JY-20725-handle-HS-search-rateProiect v© UserAutomatedReportsController.php X>D Themesv D UserAutomatedRep© UserAutomatedlv Dv2C) Hubspot/Service.onp© HubspotSyncStrategyBase.phpwDeletecrmenutylrait.ongnoteмatch.php© MatchActivityCrmData.phpC) ACuiVityvzcontrAskAnythingCor© AskJiminnyRepoJob.ohoC) PaqinationState.phoC) MatchCrmData.phpC) CrmObiectsResolver.pho© ProviderRateLimiter.php© PaginationConfia.php(c) DealsvzControllclass UserAutomatedReportsController extends ControllerA14 X2 A Y(C) OnDemandV2CcPlavlistControlle€ PlavlistShareCor2 usagespublic const string SORT_DIRECTION = 'sort_direction';C) PlavlistTrackcor30 0lC) ActionltemsControlC) ActivitvControlier.oC) A CrmNotesControl© BaseController.phpc) ClientTokenControlc) CrmController nhopublic functionconstructdprivate readonly AutomatedReportsRepository SautomatedReportsRepository.private readonly AutomatedReportsService $automatedReportsService,private readonly ApiResponseService $apiResponseServiceprivate readonly Response Sresponseprivate readonly PlanhatService $planhatService,D f..3C) Deall evelPromntseliPOST /api/v1/automated-reports/interest 1 usageoubulc Tunction crackinuerest reouest srecuest. Jsonkesponse© Instantmeeuingcon© LanguageController/** @var User Suser *c LayoutmanagemenCal livoSoodControllorsuser = srequest->usero?© Meeuingscontroller• Messacecontrollerdefer(fn ( => Sthis->planhatService->track(c Meradaracontroller© MobileSettingsConuser: suser.'automated-renorts-track-interest'.c) Momentcontroller.r€ NudgeController.ph)->alwavs@ :) NumberAllocatorec€ OraanizationMemb• OrganizationRetentreturn sthis->response->with0korC) OraanizationRolescl© OrganizationSvncC@ PartnerController.o* Athrows AnnZicationExcentionC) PhoneNumberContg) PlavbackControlle'@ PlavlistController.nlGET lanilv1lautomated-renortspublic function list(Request $request): JsonResponse{...}© ScimController.php@ SidekickController123 09 ›DELETE /api/v1/automated-reports/{uuid}public function delete(Request Srequest, string Suuid): JsonResponsef...}C) SoftnhoneControlle(C) ScoController nhn(C) SubscrintionControe ToamAiAutamatione ToamAiContovtear9a ToamCantrollor nh.(e) TosminciahtcContrsupoont Dally • In Zn 43m100% 12P.• мon 11 May 12-1/•20AskJiminnyReportActivityServiceTest v+0 ..A SF (jiminny@localhost]4 HS_local (jiminny@localhost]# console [PKOb.# console leu)# console [slAGiNg)2026-05-07 14:21:15] local.INF0: [Hubspot] DEBUG Getting headers {MMi9.У"Vace". "Inu,ur May 2020 14.21.19 6Ml"Jn"concenc-lyoe. apolicacion/ison.charser=utt-on"Transfer-Encoding": ["chunked"]."CF-Ray": ["9f80deb8db60dc3a-SOF"]."CF-Cache-Status": L"DYNAMIC"J,"Strict-Transport-Secur1ty":"max-aqe=31536000* 1ncludeSUbDomains: preload"),acceot-encodino"."access-control-allow-credentials": "false"i."server-timing": ["hcid;desc=|"019e02d0-6fd8-7812-bdba-885b7ccb3ee3\",cfr;desc=|"9f80deb8e7c6dc3a-IAD\""],"x-content-tvoe-ootions":"nosniff"."x-hubspot-correlation-id":["019e02d0-6fd8-7812-bdba-885b7ccb3ee3"],"Set-Cookip"." c+hm=Stlirtd0aXVr.kSandas6hzVVKhzTn0BidvMaheCtm0V-1778163675-1.0.107-May-26 14:51:15 GMT; domain=.hubapi.com; Http0nly; Secure; SameSite=None"],"Report-To":["{"endnoints".("url\":"https:\\/\\/a.nel.cloudflare.com\\/report\\/v4?s=NYAlsVTP0fYm32qrSDjxYE4sd2RV("group\":\"cf-nel\".("max_age\":604800}"],"NEL"L"1"success_fraction\":0.01,reportto. "cr-nel,"max agel ":604800}"].'Server":["cloudflare"]}} {"correlation_1d":"95256555-ec98-4541-b9za-adta/Sboyeab","trace_10":"C/AD8565-905t-4604-9405-0e5b551e5545CascadeHubspot Rate Limit ReE. Deaicatea low-concurrency worker poolRun only 5 workers for analytics low so concurrency naturally matches the 5 RPS limitl bashpho artisan queue:work --queue=analvtics low --tries=0 --max-iobs= --processes=5Effect: 5 workers x 1 successful op/sec = 5/sec. No rate-limit storms because we're under the limit by design. Each worker rarely sees a 429.Trade-oris•Slower throughput (still b/sec ceiling = 5.5 hours tor 100k• Other iobs on this queue comnete with the bottlenecWorks, but requires Horizon config changesF. Pre-flight cache check at job entry (mentioned earlier)Eliminates the DB.transaction churn.from.cache-hit cvcles.Doesnit chande.the throughnut.ceilina.but.reduces.cost.during.a.storm.to.almost.nothinaEasy win. Pairs with all other optionsG. Filter unmatchable activities betore dispatchIf manv activities have no email/ohone/name to match. dispatchina them is pure waste.• phpActivity::needsCrmMatch()›whereHas("participants', fn (Sq) = $q->whereNotNull('email")->orWhereNotNull('phone"))-›each(fn ($a) => MatchActivityCrmData::dispatch($a->id)):If 30% of the 100k are unmatchable (no contact info), removing them gets you to 70k - still over 9k cap, but closer.Effort: low if a querv-side filter is feasibleRecommended combinationFor maximum RoI1. A hatch endnoints) — 100x throuahnut. Solves the nroblem2. B (dispatch throttling) - defense in depth. prevents future storms.3. C (lookup caching) - reduces redundant API calls.4. F (pre-flight cache check) - eliminates DB churn during inevitable stormsWith A + B alone, the 100k → 9k problem becomes 100k → 100k completed in ~3-10 minutes, depending on caching efficiency.A is the leverage point. Without batch endpoints, you're brute-forcing through a 5 RPS hose. With them, the hose is 500 matches/sec.SummaryRace window: 5-10 wasted real APl calls per cache iil cycle, Bounded, ~15k calls wastedlin 30 min (vs 441k without cache). Acceptables can be tiahtened with aprobe lock if neededHubSpot-named middleware on multi-CRM iob: no functional issue for HubSpot. Salesforce/Pinedrive rate-limits ao throuch the wrond nath (treated as real100k → 9k bottleneck: not a rate-limiter problem, an architectural one. The fix is batch endpoints + dispatch throttling, not more aggressive retry logic.Ask anvthing (84D)+ « CodeClaude Onus 4.7 Mediumfo 4 spaces...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16696
|
|
16697
|
Petko Kashinski
Petko Kashinski, Screen share
Petk Petko Kashinski
Petko Kashinski, Screen share
Petko Kashinski
Screen share
Turn on drawing
Fullscreen
Back to grid
View Lukas Kovalik's profile
video is off, audio is on
More actions
Audio
View Petko Kashinski's profile
Petko Kashinski
More actions
Video
loading…
Petko Kashinski is in the huddle.: .
SlackFileEditViewGoHistoryWindowHelpPetko KashinskiScreen shareChromeFileEditViewHistoryBookmarksProfilesTabWindowWorkGreetiScorecandre;ws.planhat.com/jiminny/appsD АIKВChatPlayground Al..10 Jiminny - Calenda...M GMailMy Calendly - Eve...+ Back8 App CenterEE All appsQ upAl appsCicatco loyliieG Recently most active& Integrationsd5 AutomationsP Private appsAppUpdate Trial Length12.02 UPDATED (Manager) Leader Change to Slack channel SMB412.02 UPDATED (Manager) Leader Created to Slack channel SMB =4Update License to Churn4 Opportunity Stage Update on Health score4 Event Created/Updated SlackUP ASK Jimnny ecksUP"r"Implementation Specialist UpdateTrial Heid Auto updateActive Jiminny Instance Auto UpdateInitial Phase Update6д Huddle with Petko KashinskiHelpwilsonCall Ar= PH New UI LoginJiminnM InboxGet Starting with J...=Nate R= AрC Apps• Chloe Onboarding....§ Support Daily • in 2h 43 mQBuildinUserp+ CX Journey SMB.....100% C8• Mon 11 May 12:17:288•Mon 11 May 12:17NewtWorkE. PetkoAl credits (300) 'IIII110100011111184 days ago4 days ago6 days ago3 days ago2 years ago2 years agoa few seconds ago62 Huddle with Lukas Kovalik9= Al Notes: OffPetko…ScreenConnections200m77&ГАLeave...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16697
|
|
16747
|
AI Notes: Off
loading…
Petko Kashinski is in the h AI Notes: Off
loading…
Petko Kashinski is in the huddle.: .
SlackFileEditViewGoHistoryWindowHelpSupport Daily • in 2 h 38 ml100% <• Mon 11 May 12:22:246д Huddle with Petko KashinskiAl Notes: Off vail4:53Leave...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16747
|
|
16748
|
AI Notes: Off
loading…
Petko Kashinski is in the h AI Notes: Off
loading…
Petko Kashinski is in the huddle.: .
PhostormVIewINavicarecodeFV faVsco.js°9 JY-20725-handle-HS-search-rate-IiyProiect© UserAutomatedReportsController.phpC) SubscrintionControsynckelatedAcuvilymanager.pnpC) TeamA Automationweinteceinixeereit@ TeamController.phpc) ToaminciahtcContrС) Cпескапакеtгукemotematch.phg( RateLimitException.phpo transcrlpuonconu© TranslationControllC) Client.phpphpidehelper.ph©) PaqinationState.phoC) MatchCrmData.php© CrmObiectsResolver.phcc usercontroller.pnp© VocabularyControll>@ AuthC) ProviderRateLimiter.php©) PaqinationConfia.phpfinal class PlavbackController extends FrontendcontrollenMA6X3AY-customerapl›J Internav D Kioskeams© ActivityController.pAutomatedReportsic) DashboardControllec) ImpersonationContc) OrcanizationscontrC PartnersController.C) ProfileController.oh© SearchController.pt 1ac>• SettingsM Telerhonvv M Wehhook>D Hubspot>D IntegrationAppSub: 10cl© ActivityProviderCor 104© ActivityTranscriptio 107© BaseController.php 10d© CalendarController. 109© ReportController.ph 11dSoftphoneWebhook 111(c. AbstractController.phg 11g® CommentContextinter 113© ConterencesOptinouts 114c) controller.phpExportController.php© FrontendController.ph| 112T FrontendControllerTra 118@ GeocodingController.p 119(C) HealthCheckControlleiP LiveCoachController.pl 120© MissingTeamControlle 120C) MobileController.oho© NotificationController.1 1z4© NotificationProviderCo 145Ye) PlavbackControlier ohg DlavlistController nhn1A4IO Spublic function show Activity Sactivity, PlaybackPageTransformer Stransformer, Request Srequest): arraylstr: ºSdata[ 'playbackData']['masterPlaylist'] = Sthis->qetPreloadedPlavlist(Sactivity):if (! isset(Sdata['playbackData']['tracks'])) {Scatal'olavbackData'"tracks'=* Sending 'playbackVisited' event to Planhat without slowing the* response to the user e.g. after the response is sent backdofen dfn () => $this->planhatService->track(usen. Susenevent: 'playbackVisited',payload: ['activityId' => Sactivity->getIdO'activityUuid' => Sactivity->getUuid.)->alwaysO:return Sthis->render(0"playbackData' =>'activity' => Sdatal'playbackbata''tavorited' => Sdatal'favorited'n'subscribed' => $datal 'subscribed'1Vlew => svlew.private function getPreloadedPlaylist(Activity Sactivity): arrayt...}Othrows AuthorizationEycentionGET Inlavlict[activitv) m2u8 fnlavlictlpublic function playlist(Activity $activity): Response{...}(C) PucherController nhng SlackController nhnlelner Code will hoin INF to underctand vour Laravel ann code II Generate II Don't Show Anvmore (todav Q•08)40suppont Dally • In zn 38m100% Lz• Mon 11 May 12:22:24AskJiminnyReportActivityServiceTest v+0 ..A SF (jiminny@localhost]4 HS_local (jiminny@localhost]# console [PKob.# console leu)# console [slAGiNg)2026-05-07 14:21:15] local.INF0: [Hubspot] DEBUG Getting headers {MMi9 AYheaders'1"Vace". "Inu,ur May 2020 14.21.19 6Ml"Jn"Concent-lvoe". "apolicacionison charser=utt-on"Transfer-Encoding": ["chunked"]."CF-Ray":"9t80deb8dbo0dcsa-S0F"J,"CF-Cache-Status": L"DYNAMIC"J,"Strict-Transport-Secur1ty":"max-aqe=31536000* 1ncludeSUbDomains: preload"),acceot-encodino""access-control-allow-credentials": "false"."server-timing": ["hcid;desc=\"019e02d0-6fd8-7812-bdba-885b7ccb3ee3)",cfr;desc=|"9f80deb8e7c6dc3a-1AD\""J,"x-content-tvoe-ootions":"nosniff"."x-hubspot-correlation-id":["019e02d0-6fd8-7812-bdba-885b7ccb3ee3"],"Set-Cookie":["__cf_bm=StUrtdQgXVrik50pdqF6hZVYKhzTnQBidvMabeCtm0Y-1778163675-[IP_ADDRESS]-May-26 14:51:15 GMT; domain=.hubapi.com; Http0nly; Secure; SameSite=None"],"Report-To":["{"endnoints".("url\":"https:\\/\\/a.nel.cloudflare.com\\/report\\/v4?s=NYAlsVTP0fYm32qrSDjxYE4sd2RV("group\":\"cf-nel\".("max_age\":604800}"],"NEL":["{"success_fraction\":0.01,reportto. "cr-nel,"max agel ":604800}"].'Server": ["cloudflare"]}} {"correlation_1d":"95256555-ec98-4541-b9za-adta/Sboyeab","trace_10":"C/AD8565-905t-4604-9405-0e5b551e5545CascadeHubspot Rate Limit ReE. Deaicatea low-concurrency worker poolRun only 5 workers for analytics low so concurrency naturally matches the 5 RPS limitEbashpho artisan queue:work --queue=analvtics low --tries=0 --max-iobs= --processes=5Effect: 5 workers x 1 successful op/sec = 5/sec. No rate-limit storms because we're under the limit by design. Each worker rarely sees a 429.Trade-oris•Slower throughput (still b/sec ceiling = 5.5 hours tor 100k• Other iobs on this queue comnete with the bottlleneckWorks, but requires Horizon config changesF. Pre-flight cache check at job entry (mentioned earlier)Eliminates the DB.transaction churn.from.cache-hit cvcles.Doesnit chande.the throughnut.ceilina.but.reduces.cost.during.a.storm.to.almost.nothinaEasy win. Pairs with all other optionsG. Filter unmatchable activities betore dispatchIf manv activities have no email/ohone/name to match. dispatchina them is pure waste.• phpActivity::needsCrmMatch()›whereHas("participants', fn (Sq) = $q->whereNotNull('email")->orWhereNotNull('phone"))-›each(fn ($a) => MatchActivityCrmData::dispatch($a->id)):If 30% of the 100k are unmatchable (no contact info), removing them gets you to 70k - still over 9k cap, but closer.Effort: low if a querv-side filter is feasibleRecommended combinationFor maximum RoI1. A hatch endnoints) — 100x throuahnut. Solves the nroblem2. B (dispatch throttling) - defense in depth. prevents future storms.3. C (lookup caching) - reduces redundant API calls.4. F (pre-flight cache check) - eliminates DB churn during inevitable stormsWith A + B alone, the 100k → 9k problem becomes 100k → 100k completed in ~3-10 minutes, depending on caching efficiency.A is the leverage point. Without batch endpoints, you're brute-forcing through a 5 RPS hose. With them, the hose is 500 matches/sec.SummaryRace window: 5-10 wasted real APl calls per cache iil cycle, Bounded, ~15k calls wastedlin 30 min (vs 441k without cache). Acceptables can be tiahtened with aprobe lock if neededHubSpot-named middleware on multi-CRM iob: no functional issue for HubSpot. Salesforce/Pinedrive rate-limits ao throuch the wrond nath (treated as real100k → 9k bottleneck: not a rate-limiter problem, an architectural one. The fix is batch endpoints + dispatch throttling, not more aggressive retry logic.Ask anvthing (84D)+ « CodeClaude Onus 4.7 MediumWN Windsurf Teams101-20UTF.8io 4 spaces...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16748
|
|
16749
|
AI Notes: Off
loading…
Petko Kashinski is in the h AI Notes: Off
loading…
Petko Kashinski is in the huddle.: .
SlackFileEditViewGoHistoryWindowHelp# Support Daily - in 2 h 38 m100% [8• Mon 11 May 12:22:266д Huddle with Petko KashinskiAl Notes: Off vail&ГА4:55Leave...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16749
|
|
16750
|
AI Notes: Off
loading…
Petko Kashinski is in the h AI Notes: Off
loading…
Petko Kashinski is in the huddle.: .
PnostorimFV faVsco.jsProiectC) SubscrintionControC) TeamA Automationweinteceinixeereit@ TeamController.phpc) ToaminciahtcContro transcrlpuonconu© TranslationControll© UserController.php© VocabularyControll>@ Auth-customerapl›J Internav D Kioskeams© ActivityController.pAutomatedReportsic) DashboardControllec) ImpersonationContC) MediaPinelinecontc) OrcanizationscontrC PartnersController.C) ProfileController.oh© SearchController.pt1c>• SettingsM Telerhonvv M Wehhook> M Huhsnot>D IntegrationAppSub: 10cl© ActivityProviderCor 104© ActivityTranscriptio 107© BaseController.php 10d© CalendarController. 109© ReportController.ph 11dSoftphoneWebhool 111(c. AbstractController.phg 11g® CommentContextinter 113© ConterencesOptinouts 114c) controller.phpExportController.php© FrontendController.ph| 112T FrontendControllerTra 118% GeocodingController.p 119(C) HealthCheckControlleiP LiveCoachController.pl 120© MissingTeamControlle 120C) MobileController.oho© NotificationController.1 1z4© NotificationProviderCo 145Ye) PlavbackControlier ohg DlavlistController nhn146 (48 >(C) PucherController nhng SlackController nhnsupoont Dally • In zn 3om100% 12P• мon 11 May 12-22-L1AskJiminnyReportActivityServiceTest v+0 ..© UserAutomatedReportsController.php© SyncRelatedActivityManager.phpС) Cпескапакеtгукemotematch.phg( RateLimitException.phpC) Client.phpphpidehelper.ph©) PaqinationState.phoC) MatchCrmData.php© CrmObiectsResolver.phcC) ProviderRateLimiter.php©) PaqinationConfia.phpfinal class PlavbackController extends FrontendcontrollenMA6X3AYpublic function show Activity Sactivity, PlaybackPageTransformer $transformer, Request Srequest): arraylstr:Sdata[ 'playbackData']['masterPlaylist'] = Sthis->qetPreloadedPlavlist(Sactivity):if (! isset($data['playbackData']['tracks'D)) ?ScatalolavbackData'"tracks'= ?* Sending 'playbackVisited' event to Planhat without slowing the* response to the user e.g. after the response is sent backdofen dfn () => $this->planhatService->track(user: Suser,event: 'playbackVisited',payload: ['activityId' => Sactivity->getIdO'activityUuid' => Sactivity->getUuid.)->alwaysO:return Sthis->render(0"playbackData' =>'activity' => Sdatal'playbackbata'"tavorited => sdatal tavorited''subscribed' => $datal 'subscribed'1Vlew => svlew.A SF (jiminny@localhost]4 HS_local (jiminny@localhost]# console [PKob.# console leu)# console [slAGiNg)2026-05-07 14:21:15] local.INF0: [Hubspot] DEBUG Getting headers {MMi9.Уheaders'1"Vace". "Inu,ur May 2020 14.21.19 6Ml"Jn"concenc-lyoe. apolicacion/ison.charser=utt-on"Transfer-Encoding": ["chunked"]."CF-Ray": ["9f80deb8db60dc3a-SOF"]."CF-Cache-Status": L"DYNAMIC"J,"Strict-Transport-Secur1ty":"max-aqe=31536000* 1ncludeSubDomains: preload")nacceot-encodino""access-control-allow-credentials": "false"."server-timing": ["hcid;desc=\"019e02d0-6fd8-7812-bdba-885b7ccb3ee3\",cfr;desc=|"9f80deb8e7c6dc3a-IAD\""],"x-content-tvoe-ootions":"nosniff"."x-hubspot-correlation-id":["019e02d0-6fd8-7812-bdba-885b7ccb3ee3"],"Set-Cookie":["__cf_bm=StUrtdQgXVrik50pdqF6hZVYKhzTnQBidvMabeCtm0Y-1778163675-[IP_ADDRESS]-May-26 14:51:15 GMT; domain=.hubapi.com; Http0nly; Secure; SameSite=None"],"Report-To":["{"endnoints".("url\":"https:\V/\\/a.nel.cloudflare.com\/report\\/v4?s=NYAlsVTP0fYm32qrSDjxYE4sd2RV("group\":\"cf-nel\".("max_age\":604800}"],"NEL":["{"success_fraction\":0.01,reportto. "cr-nel,"max agel ":604800}"].'Server":["cloudflare"]}} {"correlation_1d":"95256555-ec98-4541-b9za-adta/Sboyeab","trace_10":"C/AD8565-905t-4604-9405-0e5b551e5545CascadeHubspot Rate Limit ReE. Deaicatea low-concurrency worker poolRun only 5 workers for analytics low so concurrency naturally matches the 5 RPS limitl bashpho artisan queue:work -queue=analvtics low --tries=0 --max-iobs=@ --processes=5Effect: 5 workers x 1 successful op/sec = 5/sec. No rate-limit storms because we're under the limit by design. Each worker rarely sees a 429.Trade-oris.•Slower throughput (still b/sec ceiling = 5.5 hours tor 100k• Other iobs on this queue comnete with the bottlleneckWorks, but requires Horizon config changesF. Pre-flight cache check at job entry (mentioned earlier)Eliminates the DB.transaction churn.from.cache-hit cvcles.Doesnit chande.the throughnut.ceilina.but.reduces.cost.during.a.storm.to.almost.nothinaEasy win. Pairs with all other optionsG. Filter unmatchable activities betore dispatchIf manv activities have no email/ohone/name to match. dispatchina them is pure waste.• phpActivity::needsCrmMatch()›whereHas("participants', fn (Sq) = $q->whereNotNull('email")->orWhereNotNull('phone"))-›each(fn ($a) => MatchActivityCrmData::dispatch($a->id)):If 30% of the 100k are unmatchable (no contact info), removing them gets you to 70k - still over 9k cap, but closer.Effort: low if a querv-side filter is feasibleRecommended combinationFor maximum RoI1. A hatch endnoints) — 100x throuahnut. Solves the nroblem2. B (dispatch throttling) - defense in depth. prevents future storms.3. C (lookup caching) - reduces redundant API calls.4. F (pre-flight cache check) - eliminates DB churn during inevitable stormsWith A + B alone, the 100k → 9k problem becomes 100k → 100k completed in ~3-10 minutes, depending on caching efficiency.A is the leverage point. Without batch endpoints, you're brute-forcing through a 5 RPS hose. With them, the hose is 500 matches/sec.SummaryRace window: 5-10 wasted real APl calls per cache iil cycle, Bounded, ~15k calls wastedlin 30 min (vs 441k without cache). Acceptables can be tiahtened with aprobe lock if neededHubSpot-named middleware on multi-CRM iob: no functional issue for HubSpot. Salesforce/Pinedrive rate-limits ao throuch the wrond nath (treated as real100k → 9k bottleneck: not a rate-limiter problem, an architectural one. The fix is batch endpoints + dispatch throttling, not more aggressive retry logic.private function getPreloadedPlaylist(Activity Sactivity): arrayt...}Othrows AuthonizationEycentionGET Inlavlict[activitv) m2u8 fnlavlict1public function playlist(Activity $activity): Response{...}Ask anvthing (84D)+ « CodeClaude Onus 4.7 Mediumfo 4 spaces...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16750
|
|
16751
|
AI Notes: Off
loading…
Petko Kashinski is in the h AI Notes: Off
loading…
Petko Kashinski is in the huddle.: .
SlackFileEditViewGoHistoryWindowHelplalolj Support Daily • in 2h 38 m100% C47 8• Mon 11 May 12:22:286д Huddle with Petko KashinskiY= Al Notes: Off vailLeave...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16751
|
|
16752
|
AI Notes: Off
loading…
Petko Kashinski is in the h AI Notes: Off
loading…
Petko Kashinski is in the huddle.: .
PnostorimFV faVsco.jsProiectC) SubscrintionControC) TeamA Automationweinteceinixeereit@ TeamController.phpc) ToaminciahtcContro transcrlpuonconu© TranslationControll© UserController.php© VocabularyControll>@ Auth-customerapl›J Internav D Kioskeams© ActivityController.pAutomatedReportsic) DashboardControllec) ImpersonationContC) MediaPinelinecontc) OrcanizationscontrC PartnersController.C) ProfileController.oh© SearchController.pt1c>• SettingsM Telerhonvv M Wehhook> M Huhsnot>D IntegrationAppSub: 10cl© ActivityProviderCor 104© ActivityTranscriptio 107© BaseController.php 10d© CalendarController. 109© ReportController.ph 11dSoftphoneWebhool 111(c. AbstractController.phg 11g® CommentContextinter 113© ConterencesOptinouts 114c) controller.phpExportController.php© FrontendController.ph| 112T FrontendControllerTra 118% GeocodingController.p 119(C) HealthCheckControlleiP LiveCoachController.pl 120© MissingTeamControlle 120C) MobileController.oho© NotificationController.1 1z4© NotificationProviderCo 145Ye) PlavbackControlier ohg DlavlistController nhn146 (48 >(C) PucherController nhng SlackController nhnsupoont Dally • In zn 3om100% 12P• мon 11 May 12-2L-24AskJiminnyReportActivityServiceTest v+0 ..© UserAutomatedReportsController.php© SyncRelatedActivityManager.phpС) Cпескапакеtгукemotematch.phg( RateLimitException.phpC) Client.phpphpidehelper.ph©) PaqinationState.phoC) MatchCrmData.php© CrmObiectsResolver.phcC) ProviderRateLimiter.php©) PaqinationConfia.phpfinal class PlavbackController extends FrontendcontrollenMA6X3AYpublic function show Activity Sactivity, PlaybackPageTransformer $transformer, Request Srequest): arraylstr:Sdata[ 'playbackData']['masterPlaylist'] = Sthis->qetPreloadedPlavlist(Sactivity):if (! isset($data['playbackData']['tracks'D)) ?ScatalolavbackData'"tracks'= ?* Sending 'playbackVisited' event to Planhat without slowing the* response to the user e.g. after the response is sent backdofen dfn () => $this->planhatService->track(user: Suser,event: 'playbackVisited',payload: ['activityId' => Sactivity->getIdO'activityUuid' => Sactivity->getUuid.)->alwaysO:return Sthis->render(0"playbackData' =>'activity' => Sdatal'playbackbata'"tavorited => sdatal tavorited''subscribed' => $datal 'subscribed'1Vlew => svlew.A SF (jiminny@localhost]4 HS_local (jiminny@localhost]# console [PKob.# console leu)# console [slAGiNg)2026-05-07 14:21:15] local.INF0: [Hubspot] DEBUG Getting headers {MMi9.Уheaders'1"Vace". "Inu,ur May 2020 14.21.19 6Ml"Jn"concenc-lyoe. apolicacion/ison.charser=utt-on"Transfer-Encoding": ["chunked"]."CF-Ray": ["9f80deb8db60dc3a-SOF"]."CF-Cache-Status": L"DYNAMIC"J,"Strict-Transport-Secur1ty":"max-aqe=31536000* 1ncludeSubDomains: preload")nacceot-encodino""access-control-allow-credentials": "false"."server-timing": ["hcid;desc=\"019e02d0-6fd8-7812-bdba-885b7ccb3ee3\",cfr;desc=|"9f80deb8e7c6dc3a-IAD\""],"x-content-tvoe-ootions":"nosniff"."x-hubspot-correlation-id":["019e02d0-6fd8-7812-bdba-885b7ccb3ee3"],"Set-Cookie":["__cf_bm=StUrtdQgXVrik50pdqF6hZVYKhzTnQBidvMabeCtm0Y-1778163675-[IP_ADDRESS]-May-26 14:51:15 GMT; domain=.hubapi.com; Http0nly; Secure; SameSite=None"],"Report-To":["{"endnoints".("url\":"https:\V/\\/a.nel.cloudflare.com\/report\\/v4?s=NYAlsVTP0fYm32qrSDjxYE4sd2RV("group\":\"cf-nel\".("max_age\":604800}"],"NEL":["{"success_fraction\":0.01,reportto. "cr-nel,"max agel ":604800}"].'Server":["cloudflare"]}} {"correlation_1d":"95256555-ec98-4541-b9za-adta/Sboyeab","trace_10":"C/AD8565-905t-4604-9405-0e5b551e5545CascadeHubspot Rate Limit ReE. Deaicatea low-concurrency worker poolRun only 5 workers for analytics low so concurrency naturally matches the 5 RPS limitl bashpho artisan queue:work -queue=analvtics low --tries=0 --max-iobs=@ --processes=5Effect: 5 workers x 1 successful op/sec = 5/sec. No rate-limit storms because we're under the limit by design. Each worker rarely sees a 429.Trade-oris.•Slower throughput (still b/sec ceiling = 5.5 hours tor 100k• Other iobs on this queue comnete with the bottlleneckWorks, but requires Horizon config changesF. Pre-flight cache check at job entry (mentioned earlier)Eliminates the DB.transaction churn.from.cache-hit cvcles.Doesnit chande.the throughnut.ceilina.but.reduces.cost.during.a.storm.to.almost.nothinaEasy win. Pairs with all other optionsG. Filter unmatchable activities betore dispatchIf manv activities have no email/ohone/name to match. dispatchina them is pure waste.• phpActivity::needsCrmMatch()›whereHas("participants', fn (Sq) = $q->whereNotNull('email")->orWhereNotNull('phone"))-›each(fn ($a) => MatchActivityCrmData::dispatch($a->id)):If 30% of the 100k are unmatchable (no contact info), removing them gets you to 70k - still over 9k cap, but closer.Effort: low if a querv-side filter is feasibleRecommended combinationFor maximum RoI1. A hatch endnoints) — 100x throuahnut. Solves the nroblem2. B (dispatch throttling) - defense in depth. prevents future storms.3. C (lookup caching) - reduces redundant API calls.4. F (pre-flight cache check) - eliminates DB churn during inevitable stormsWith A + B alone, the 100k → 9k problem becomes 100k → 100k completed in ~3-10 minutes, depending on caching efficiency.A is the leverage point. Without batch endpoints, you're brute-forcing through a 5 RPS hose. With them, the hose is 500 matches/sec.SummaryRace window: 5-10 wasted real APl calls per cache iil cycle, Bounded, ~15k calls wastedlin 30 min (vs 441k without cache). Acceptables can be tiahtened with aprobe lock if neededHubSpot-named middleware on multi-CRM iob: no functional issue for HubSpot. Salesforce/Pinedrive rate-limits ao throuch the wrond nath (treated as real100k → 9k bottleneck: not a rate-limiter problem, an architectural one. The fix is batch endpoints + dispatch throttling, not more aggressive retry logic.private function getPreloadedPlaylist(Activity Sactivity): arrayt...}Othrows AuthonizationEycentionGET Inlavlict[activitv) m2u8 fnlavlict1public function playlist(Activity $activity): Response{...}Ask anvthing (84D)+ « CodeClaude Onus 4.7 Mediumfo 4 spaces...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
16752
|
|
23492
|
Steliyan Georgiev, Direct Message, 1 of 7 suggesti Steliyan Georgiev, Direct Message, 1 of 7 suggestions
SlackFile Edit ViewGoHistoryWindowHelp>0 lal§ Support Daily - in 4 h 5 m100% (4 8• Tue 12 May 10:55:486д Huddle with Petko KashinskiY= Al Notes: OffLeave...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
23492
|
|
23493
|
AI Notes: Off
Thread
Every huddle has a thread
Sla AI Notes: Off
Thread
Every huddle has a thread
SlackFileEditViewGoHistoryWindowHelp>O lho6д Huddle with Petko Kashinski§ Support Daily - in 4h 5 m100% C 8• Tue 12 May 10:55:51?= Al Notes: OffThreadX® Every huddle has a threadSend messages, files, and links to everyone in thehuddle. They're saved as a thread in this directmessage with @Petko Kashinski, so you canaccess it even after the huddle is done.Reply...• Also send as direct message+Aa.*•1PS$11Passwordail&ГАLeave...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
23493
|
|
23503
|
AI Notes: Off
Thread
Every huddle has a thread
Sen AI Notes: Off
Thread
Every huddle has a thread
Send messages, files, and links to everyone in the huddle. They’re saved as a thread in this direct message with
@Petko Kashinski
@Petko Kashinski
, so you can access it even after the huddle is done.
Also send as direct message
Also send as direct message
Hide thread
Steliyan Georgiev, Direct Message, 1 of 7 suggestions
FV faVsco.js?9 JY-20725-handle-HS-search-rate-limitProiectC) AutomatedReportGenerated.onp© PlaybackController.phpPlanhatService.php Xus vetur.conng.sM. WEBHOOK FILTERING IMPLEM› ib External Librariesv E° Scratches and Consolesv M Database ConsolesV AEUA console [EU]A DEAL RISKS [EU]A DI (EU]A EU (EUv Ajiminny@localhost& console liminny @localnoA Di [liminny@localhost]A HS local [liminny@localhcA SF [iiminny@localhostlA zoho dev [iiminny@localh&PROD& console PRODII& console 1 PRODIA DI PRODIservicesv natahacoV AEU& consolev &iiminny@localhost4, HS Jocal 1 s 665 msA SFV APROD- console 3$V A STAGINGconsole"Dockenreadonly class PlanhatServicepublic function track(User Suser, string Sevent, array $payload = (): voidpudld -l'name' => $user->getName@'email' => $ue Search in Jlminnv"externalld'' companyExter'action' => $'info' => $paJiminny2results for "olanh"rlannat¿ Profile$planhatResponse->posc unl:'Salesforce log in (planhat.i...-AllItemsSthis->logFailedFbody => Sp? FavoritesSTATUS' ?>'data' => $da.Watchtower‹> Developerh Outoutf liminnv.auto. =moloveeEngineering825 - Enoineerino025 - AllIntearation Accounts14 Aug 2025 - AlL• JiminnvTAGSJun 2025 - Sales T6025 - Sales TeamO 2FAJlun 2025 - Account025 - Aesaunt Mana• CSV Import 28.01.2210 2025 - Spectre Sal(• LastPacs Imnort 111.2'025odtanterv!r25 - Client Success, UK Sales, Support, Product16 t 2025 - A1125 - ALU- Client Succecs13 Sep 2025 - Client Successlient Successen 2025 - Client Success= custom.log=laravel.logA SF (jiminny@localhost]A console (Eul412 V19 AVA console [STAGING]Tx: Autohelo8 Jiminnvo) Emolovee vU Share0 Edit4 HS_local [jiminny@localhost]A console [PROD&So jiminny038 A1 A35 V 64 ^t results where 1d = 19167ts where 10 = 5851nes where id = 87714;1tilters where activity search_1d = 877141bE uuid to bin('8827f672-202d-4162-9d04-73ff5f0566a9') = uuid-4bcb-854f-cc6560290101') = uuid:ons WHERE provider = 'hubspot';_results wherGoodF MEDIAN exor:decimai.))© TIMEDIFF (expr1: datetime, expr2:datetime)Press ^, to choose the selected (or first) suagestion and insert a dot afterwards Next TircascadePlanhat Event PlaybacSearched planhat in ~/iminnylappSearched olavback *visitedivisited."olavback in ~/fiminnvlaoolsupoont Dally • In 40 4m• Tue 12 May 10:56:0$+0 ..find planhat event playback [EMAIL]:/app-eus.olanhat.com•Last edited Wednescav. Juv 5. 2023 at 3:29:20 PMII reason Ypdfpdfpdfpdfodfndfpodcastpdfpodcast<null><null><null><null><nul]>enullsYour included daily usage quota is exhausted. Purchase extra usage to continue using premium models. Quota resets May 12, 11:00isk anything (8AL)<> Code SWE-1.61 pavloadY1 1"team_id":1, "group_ids":L9J,"report_type":"exec_summary","from_date":"2025-04-01700:00:00+00:00","to_date":"2025-081 {"team_id":1,"group_ids":[],"report_type":"product_feedback","from_date":"2025-07-01T00:00:00+00:00","to_date":"20250 {"team_id":1, "group_ids":(],"report_type":"product_feedback" "from_date":"2024-08-01T00:00:00+00:00" "to_date":"20251 <null>1 <nul1>0 1"team_id":702, "group_ids":(1944],"report_type":"coaching_profiles", "from_date":"2025-04-01700:00:00+00:00", "to_date0 {"team_id":702,"group_ids": [1944],"report_type":"exec_summary","from_date":"2025-04-01T00:00:00+00:00","to_date":"2€0 {"team_id":702, "group_ids": (1963],"report_type":"coaching_profiles" "from_date":"2025-04-01T00:00:00+00:00" "to_date0 {"team_id":702, "group_ids": (1963],"report_type":"exec_summary" "from_date":"2025-04-01T00:00:00+00:00" "to_date":"20)0 {"team_id":853, "group_ids":[2309],"report_type":"coaching_profiles", "from_date":"2025-08-01T00:00:00+00:00", "to_date0 {"team_id":853, "group_ids":[2309], "report_type": "product_feedback", "from_date" : "2025-08-01T00:00:00+00:00" , "to_date"0 1"team_id":853,"group_ids":[2309],"report_type":"product_feedback", "from_date":"2025-08-01700:00:00+00:00", "to_date'2 {"team_id":1, "group_ids": [91, 2368,2,457,8],"report_type":"product_feedback", "from_date":"2025-09-01T01:00:05+00:00".1 <null>0 {"team_id":1."group_ids":[]."report type"."exec summarv" "from_date"."2025-09-01T01:00:05+00:00" "to_date"-"2025-09-0 {"team_id":1, "request id"."318d3ce6-c70a-416a-8b1f-aebb9ef594bd" "report type"."product_feedback" "media types":["pd0 {"team id".1 "request id"."4c40a7d6-4697-4b80-83f0-27d7885e2d63" "renort tvne"."exec summary" "media tvnes".["odf"]|A&iteam id".1 "nequest idu.«11a01dh1-7358-4401-a75c-160pf£39cf7d8" "nenont tvno"."exec sum0 {"team_id":1,"request_id":"75fa7c3a-03ae-4836-b0bc-861bb42d2d25" ,"report_type":"coaching_profiles"0 {"team_id":1,"request id":"9a812aee-c2ee-4908-83c3-17478465f014" "report type":"exec_st0 {"team_id":1. "request id"-"9a812aee-c2ee-4908-83c3-17478465f014" "report type"."exec summary" "media types":["odf"."CSVv• response Y"request 1d":94c5+517-6500-4840-00f1-080{"request_id":"9e5217fc-baa3-4c46-bea1-b00{"request_id":"e5067185-66c4-45be-b084-80e<null><null>"request 1d":"3a9d0566-2475-4df2-a2fc-fac"request id".05f6a613-8aa6-445d-h009-d2e{"request_id":"c05d72b5-5d7c-47f3-a911-9d2{"request_id":"7e42dc32-0544-41bd-81e9-399{"request_id". "58625189-70ce-497e-9b64-7c9{"request_id":"4137cb47-4bf4-4976-81C4-3ba1"request_id":"dca01ab8-6065-45c2-91e0-1c2{"request_id":"da504365-0217-43f9-a590-2cd<null>{"request_id"."0d8e747f-cd94-4697-ab00-c53{"request id"."318d3ce6-c70a-416a-8b1f-aeb{"request id"."4c40a7d6-4697-4b80-83f0-27dsinpques+ id".111a01dh1-7358-4401-a75c-169Jlnonuoc+ idi.1754a7c7a-02a0-192kchAhe-941{"request id":"9a812aee-c2ee-4908-83c3-174{"request_id". "9a812aee-c2ee-4908-83c3-174W Windsurf Teams650•10JUTE.A...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
23503
|
|
23504
|
AI Notes: Off
Thread
Every huddle has a thread
Sen AI Notes: Off
Thread
Every huddle has a thread
Send messages, files, and links to everyone in the huddle. They’re saved as a thread in this direct message with
@Petko Kashinski
@Petko Kashinski
, so you can access it even after the huddle is done.
Also send as direct message
Also send as direct message
Hide thread
Steliyan Georgiev, Direct Message, 1 of 7 suggestions
SlackFileEditViewGoHistoryWindowHelp→0 lhl o§ Support Daily • in 4h 4 m100% C 8• Tue 12 May 10:56:106д Huddle with Petko Kashinski7= Al Notes: OffThreadX® Every huddle has a threadSend messages, files, and links to everyone in thehuddle. They're saved as a thread in this directmessage with @Petko Kashinski, so you canaccess it even after the huddle is done.Reply...Also send as direct message+Aa.*•ailLeave...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
23504
|
|
23505
|
AI Notes: Off
Thread
Every huddle has a thread
Sen AI Notes: Off
Thread
Every huddle has a thread
Send messages, files, and links to everyone in the huddle. They’re saved as a thread in this direct message with
@Petko Kashinski
@Petko Kashinski
, so you can access it even after the huddle is done.
Also send as direct message
Also send as direct message
Hide thread
Steliyan Georgiev, Direct Message, 1 of 7 suggestions
Share your screen
=+SlackFileEditViewGoHistoryWindowHelp→ws.planhat.com/jiminny/home/data-explorer/usageJiminnySearch JiminnyContent Explorer7 Metric |Datasetautomated-reports-traEnd UserData ExplorerQ autactivities.automated-reports-Calendar• NotificationsNameOverviewRaw DataTral*• Morev EndUser 1Metricsautomated-reports-track-Sections +CS Day-to-day2 Getting started GuideJust CS Data* Daily Operations05 May06 May07• Weekly prep© Renewals and Upsell:= € Risk and Churn An...Implementation -Impl ProjectsTrial Opps (Under Rev...Stoyan's clientsCommentsAdd a comment> 0al)• Support Daily • in 4h 4 m100% <Tue 12 May 10:56:13→QDescribe what you are looking forJiminny ...Petko Kashinski6 0External connectionsMessagesAdd canvasO Files+Home* Starred& jiminny-x-integrati…..8 platform-inner-team6 ддаYesterday~A huddle happened12:14 PMYou and Petko Kashinski were in the huddle for8m.DMsActivityFilesLater..•More+Channels# ai-chapter# alerts# backend# bugs# confusion-clinic# curiosity_lab# engineering# general# jiminny-bg# platform-tickets# product_launches# random# releases# sofia-office# support# thank-yous# the_people_of jimi...Saved for later • Due 2 hours agoPetko Kashinski 12:21 PMplaybackVisitedToday ~Lukas Kovalik &10:36 AMдобро утроПетко имаш ли минутка да те питам за РНPetko Kashinski 10:52 AMХей ЛукашСлед минутка окей ли е ?Lukas Kovalik @ 10:52 AMразбира сеPetko Kashinski 10:54 AMRdyHuddle ?You joined the huddle (LIVE)Petko Kashinski is here too.10:55 AMMessage Petko Kashinski• Direct messages. Petko..8a 02Stalivan Ganraiov+ Aa.*•6d Huddle with Petko KashinskiAl Notes: OffLeave...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
23505
|
|
23509
|
AI Notes: Off
Thread
Every huddle has a thread
Sen AI Notes: Off
Thread
Every huddle has a thread
Send messages, files, and links to everyone in the huddle. They’re saved as a thread in this direct message with
@Petko Kashinski
@Petko Kashinski
, so you can access it even after the huddle is done.
Also send as direct message
Also send as direct message
Hide thread
Steliyan Georgiev, Direct Message, 1 of 7 suggestions
=+SlackFileEdit→JiminnyContent ExplorerData ExplorerCalendar• Notifications**• MoreSections +CS Day-to-day2 Getting started GuideJust CS Data* Daily Operations• Weekly prep© Renewals and Upsell:5 € Risk and Churn An...ImplementationImpl ProjectsTrial Opps (Under Rev...Stoyan's clientsViewGoHistoryWindowHelp> 0al)Support Daily - in 4h 4 m100% C78• Tue 12 May 10:56:17ws.planhat.com/jiminny/home/data-explorer/usagemetricdef?preview=UsageMetricDef.69f2c6529c9f21b58804Search Jiminny7 Metric |Datasetautomated-reports-track-interestEnd UserQ autactivities.automated-reports-track-interestNameOverviewRaw DataTracev EndUser 1Metricsautomated-reports-track-306 May07 MayFilter by Company05 May08 May®+LukasMay 05, 2026 - May 11, 202609 MayDAYS V10 May11 Mayas aSUM Vacross companiesNo groups found+ Show full listCommentsAdd a comment...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
23509
|
|
23510
|
AI Notes: Off
Thread
Every huddle has a thread
Sen AI Notes: Off
Thread
Every huddle has a thread
Send messages, files, and links to everyone in the huddle. They’re saved as a thread in this direct message with
@Petko Kashinski
@Petko Kashinski
, so you can access it even after the huddle is done.
Also send as direct message
Also send as direct message
Hide thread
Steliyan Georgiev, Direct Message, 1 of 7 suggestions
SlackrTavsco.sVIewMistonWindowHelp?9 JY-20725-handle-HS-search-rate-limit• supoont Dally • In 4n 4m100% 2• Tue 12 May 10:56:17Proiect vus vetur.conng.sM. WEBHOOK FILTERING IMPLEM› ib External Librariesv E° Scratches and Consolesv M Database ConsolesV AEUA console [EU]A DEAL RISKS [EU]A DI (EU]A EU (EU& liminny@localnost& console liminny @localno* Dl liminny@localhostf hs local liminny@localncA SF [iiminny@localhostlA zoho dev [iiminny@localhAPROD& console PRODII¿ console 1 [PROD1A DI PRODIC) AutomatedReportGenerated.php© PlaybackController.php© UserAutomatedReportsController.phpPlanhatService.php xreadonly class PlanhatServicepublic function track(User Suser, string Sevent, array $payload = (]): voidpudld -l= custom.log=laravel.logA SF (jiminny@localhost]4 HS_local [jiminny@localhost]« console [PROD] X# console [eu)412 V19 AVA console [STAGING]cascadePlanhat Event Playbac+0 ..Tx: AutovSo jiminnyfind planhat event playback visited6д Huddle with Petko Kashinski3841 835 X04#= Al Notes: OffThreadn1d = 877141@ Every huddle has a thread4162-9004-75T+51856699' = UU1diSend messages. fles. and llinks to evervone in theuid:huddle. Thev're saved as a threadiin this directmessage with (@Petko Kashinskil, so vou can.access it even after the huddle is doneReolv...Also send as direct messageil';ecimal)1:datetime, expr2:datetime)servicesvmnatahaseV AEU& consolev &iiminny@localhostA HS local 1 s 665 msA SFV APROD- console 3$V A STAGINGconsole"Dockengroup_ids":L9J, "report_type": "exec_:group_ids":[],"report_type":"producgroup_ids":(],"report_type":"produc). "group_ids": [1944),"report_type":"C, "group_ids": [1944],"report_type":"*, "group_ids": (1963],"report_type":"(|, "groupids": (1963],"report_type":"(, "group_ids": [2309], "report_type" :"*"group_ids":[2309],"report_type":, "group_ids": [2309],"report_type":"]leavegroup_ids": [91,2368,2,457,8],"reporipdf<nULL›<nUll><null>0 {"team_id":1."group_ids":[]."report type"."exec si0 {"team_id":1, "request_id"."318d3ce6-c70a-416a-8b1-odfndfpodcastpdfpodcastActivity@ Describe what you are looking forJiminny ...3 Petko KashinskJnExternall connechons* Starred Ijiminny-x-integrati..8 platform-inner-teamMessages12 Add canvasP FilesYesterdav vAnudd le nanbened 12.14 PMYou and Petko Kashinski were in the huddle for.# Channeld# ai-chaptenti alertc# backend# bugs# confusion-clinic# curiosity lab# engineering# general# jiminny-bg# platform-tickets# product launchesi random# releases"sona-oince# support# thank-vous# the people of jimi..• Saved for later • Due 2 hours agoPetko Kachincki 12.21 PMlnlavhackVisitediTodayLukas Kovalik 10:36 AMдооро утроПетко имаш ли минутка да те питам за РНPetko Kashinski 10-52 AMХeй ЛvкаттlСлел минутка окей ли е ?Lukas Kovalik 10:52 AMnazonna cePetko Kashinski 10:54 AMUnddleYou joined the huddleLIVE 10:55 AMMeccage Petka KachinckilA Direct messagesPetko…03 02al Croluen Cooroioulresets Mav 12. 11:001-6500-4849-00f1-980c-baa3-4c46-bea1-b006-2475-40f2-22fc-fac3-8aa6-445d-b009-d2e5-5d7c-47f3-a911-9d22-0544-41bd-81e9-3999-70ce-497e-9b64-7c98-6965-4562-0160-1c2S-0217-43f9-a590-2cdALL16 t 2025 - A1125 - ALU- Client Succecs13 Sep 2025 - Client Successlient Successen 2025 - Client SuccessA Huddle with Dotkn Kochincki0 {"team_id":1,"request_id":"4c40a7d6-4697-4b80-83f0-27d7885e2d63", "report_type":"exec_summary", "media_types": ["pdf"].f-cd94-4697-ab00-c53Al Notec: Offeave6-c70a-416a-8b1f-aeb{"request_id"."4c40a7d6-4697-4b80-83f0-27d<nul]>0 {"team_id":1,"request_id":"11a01db1-7358-4f91-a75c-169ef39cf7d8", "report_type":"exec_summary" "media_types":["pdf"].sinpques+ id".111a01dh1-7358-4401-a75c-160<null>0 {"team_id":1,"request_id":"75fa7c3a-03ae-4836-b0bc-861bb42d2d25" , "report_type":"coaching_profiles" "media_types":["p{"request_id":"75fa7c3a-03ae-4836-b0bc-861<null>0 {"team id":1,"request id":"9a812aee-c2ee-4908-83c3-17478465f014" "report type":"exec summary" "media types":["pdf" "podc {"request id":"9a812aee-c2ee-4908-83c3-1740 {"team_id":1. "request id"."9a812aee-c2ee-4908-83c3-17478465f014" "report type"."exec summary" "media types".["odf"_"{"request_id". "9a812aee-c2ee-4908-83c3-174W Windsurf Teams...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
23510
|
|
23511
|
Steliyan Georgiev, Direct Message, 1 of 7 suggesti Steliyan Georgiev, Direct Message, 1 of 7 suggestions
Screen 1
Screen 2
Screen 1
Screen 2
Cancel
Share
Close
SlackVIewMistonWindowHelprTavsco.s?9 JY-20725-handle-HS-search-rate-limitProiectC) AutomatedReportGenerated.onp© PlaybackController.php(c) UserAutomatedReportscontroller.pnpPlanhatService.php Xus vetur.conng.sM. WEBHOOK FILTERING IMPLEMreadonly class PlanhatServicepublic function track(User Suser, string Sevent, array $payload = (]): voidpudld -l412 V19 AV> fih Sxtemnal Librariesv E° Scratches and Consolesv M Database Consoles6 Huddle with Petko KashinskV AEUA console [EU)A DEAL RISKS (EU]A DI (EU]A EU (EU4= Al Notes: Off& liminny@localnost& console liminny @localno* Dl liminny@localhostA HS local [liminny@localhcA SF [iiminny@localhostlA zoho dev [iiminny@localh&PROD& console PRODII¿ console 1 [PROD1A DI PRODI> AOAServicesvM natahaceV AEU& consolev &iiminny@localhost4,HS_local 1 s 665 msA SFV APROD- console 3$V A STAGINGconsole"DockenShare entire screenWindowScreen 116 t 2025 - A1125 - ALU- Client Succecs13 Sep 2025 - Client Successlient Successen 2025 - Client Successpdfodfndfpodcastpdfpodcast• supoont Dally • In 4n 4m100% 5.• lue 1z May 10:00.19= custom.log=laravel.l0gA SF (jiminny@localhost]4 HS_local [jiminny@localhost]« console [PROD] X# console [eu)cascadeA console [STAGING]Planhat Event Playbac+0 ..Tx: AutovSo jiminnyfind planhat event playback visited338 41 835 X04uhreadn1d = 87714E) Every huddle has a threadSend messages. fles. and links to evervone in the4162-9004-75T+51856689' = UU1diUid:huddle. They're saved as a thread in this directsage with @Petko Kashinski, so you canS5 ll even after the huddle is doneScreen 2CancellShare<nULL›il':ecimal)1:datetime, expr2:datetime)e selected (or first) suacestion and insert a dot aiActivitygroup_ids":L9J, "report_type": "exec_sgroup_ids":[],"report_type":"producgroup_ids":(],"report_type":"produc), "group_ids": [1944), "report_type":"c, "group_ids": [1944],"report_type":"e, "group_ids": (1963],"report_type":"(, "groupids": (1963],"report_type":"e, "group_ids": [2309], "report_type":"o"group_ids": [2309], "report_type":"!, "group_ids": [2309],"report_type":"!Leavegroup_ids": [91,2368,2,457,8],"repori0 {"team_id":1,"group_ids":[]."report type"."exec siQ Describe what you are looking foJiminny ...3 Petko KashinskMessages12 Add canvasP FileslnExternall connechons* Starred IYesterdav vAnudd le nanbened 12.14 PM• jiminny-x-integrati..You and Petko Kashinski were in the huddle for.8 platform-inner-team# Channeld• Saved for later • Due 2 hours agoPetko Kachincki 12.21 PMl# ai-chaptennlavhackVisitedi# alerts# backendToday# bugs# confusion-clinicLukas Kovalik 10:36 AMдооро утро# curiosity labПетко имаш ли минутка да те питам за РН# engineering# generalPetko Kashinski 10-52 AMХeй Лvкаттl# jiminny-bg# platform-ticketsСлел минутка окей ли е ?# product launchesLukas Kovalik 10:52 AMnazonna cei randomPetko Kashinski 10:54 AM# releases"sona-oinceUnddle# support# thank-vousYou joined the huddleLIVE 10:55 AM# the people of jimi..Meccaae Petka KachinckilA Direct messagesPetko…03 02al Crotuen Coorcinresets Mav 12. 11:001-6580-4849-00f1-980c-baa3-4c46-bea1-b005-66ch-45he-hA84-8Ae16-2475-40f2-a2Fc-fac3-8aa6-445d-h009-d2e5-5d7c-47f3-a911-9d22-0544-41bd-81e9-3999-70ce-497e-9b64-7c98-6065-4562-0160-1c2S-0217-43f9-a590-2cdf-cd94-4697-ab00-c53A Huddle with Dotkn KochinckiAl Notec: Offeave0 {"team_id":1, "request_ id"."318d3ce6-c70a-416a-8b1-6-c70a-416a-8b1f-aeb<null>0 {"team_id":1,"request_id":"4c40a7d6-4697-4b80-83f0-27d7885e2d63", "report_type":"exec_summary", "media_types":["pdf"].{"request id"."4c40a7d6-4697-4b80-83f0-27d<nul]>0 {"team_id":1,"request_id":"11a01db1-7358-4f91-a75c-169ef39cf7d8", "report_type":"exec_summary" "media_types":["pdf"].sinpques+ id".111a01dh1-7358-4401-a75c-160<null>0 {"team_id":1,"request_id":"75fa7c3a-03ae-4836-b0bc-861bb42d2d25" , "report_type":"coaching_profiles" "media_types":["p{"request_id":"75fa7c3a-03ae-4836-b0bc-861<null>0 {"team id":1,"request id":"9a812aee-c2ee-4908-83c3-17478465f014" "report type":"exec summary" "media types":["pdf" "podc {"request id":"9a812aee-c2ee-4908-83c3-1740 {"team_id":1. "request id"."9a812aee-c2ee-4908-83c3-17478465f014" "report type"."exec summary" "media types".["odf"_"{"request_id". "9a812aee-c2ee-4908-83c3-174W Windsurf Teams...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
23511
|
|
23512
|
Steliyan Georgiev, Direct Message, 1 of 7 suggesti Steliyan Georgiev, Direct Message, 1 of 7 suggestions
Screen 1
Screen 2
Screen 1
Screen 2
Cancel
Share
Close
=+SlackFileEdit→JiminnyContent ExplorerData ExplorerCalendar• Notifications**• MoreSections +CS Day-to-day2 Getting started GuideJust CS Data* Daily Operations• Weekly prep© Renewals and Upsell:5 € Risk and Churn An...ImplementationImpl ProjectsTrial Opps (Under Rev...Stoyan's clientsViewGoHistoryWindowHelp> 0al)Support Daily - in 4h 4 m100% C78• Tue 12 May 10:56:20ws.planhat.com/jiminny/home/data-explorer/usagemetricdef?preview=UsageMetricDef.69f2c6529c9f21b58804Search Jiminny7 Metric |Datasetautomated-reports-track-interestEnd UserQ autactivities.automated-reports-track-interestNameOverviewRaw DataTracev EndUser 1Metricsautomated-reports-track-306 May07 MayFilter by Company05 May08 May®+LukasMay 05, 2026 - May 11, 202609 MayDAYS V10 May11 Mayas aSUM Vacross companiesNo groups found+ Show full listCommentsAdd a comment...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
23512
|
|
23513
|
AI Notes: Off
Thread
Every huddle has a thread
Sen AI Notes: Off
Thread
Every huddle has a thread
Send messages, files, and links to everyone in the huddle. They’re saved as a thread in this direct message with
@Petko Kashinski
@Petko Kashinski
, so you can access it even after the huddle is done.
Also send as direct message
Also send as direct message
Hide thread
Steliyan Georgiev, Direct Message, 1 of 7 suggestions
Share your screen
SlackVIewMistonWindowHelp• supoont Dally • In 4n 4m100% Lz• lue 1z May 10:00.22rTavsco.s?9 JY-20725-handle-HS-search-rate-limitProiectus vetur.conng.sM. WEBHOOK FILTERING IMPLEM› ib External Librariesv E° Scratches and Consolesv M Database ConsolesV AEUA console [EU]A DEAL RISKS [EU]A DI (EU]A EU (EU& liminny@localnost& console liminny @localno* Dl liminny@localhostf hs local liminny@localncA SF [iiminny@localhostlA zoho dev [iiminny@localhAPROD& console PRODII¿ console 1 [PROD1A DI PRODIC) AutomatedReportGenerated.ong© PlaybackController.php© UserAutomatedReportsController.phpPlanhatService.php Xreadonly class PlanhatServicepublic function track(User Suser, string Sevent, array $payload = (]): voidpudld -l= custom.log=laravel.logA SF (jiminny@localhost]4 HS_local [jiminny@localhost]« console [PROD] X# console [eu)412 M19 A VA console [STAGING]cascadePlanhat Event Playbac+0 ..Tx: AutoySo jiminnyfind planhat event playback visited6д Huddle with Petko Kashinski338 41 835 X04#= Al Notes: OffThread11d = 8/7141@ Every huddle has a thread4162-9004-75T+51856689' = UU1diSend messages. fles. and llinks to evervone in theUid:huddle. Thev're saved as a threadiin this directmessage with @Petko Kashinski, so you canaccess it even after the huddle is doneReolv...Also send as direct messageecimal)1:datetime, expr2:datetime)ActivityservicesvmnatahaseV AEU& consolev &iiminny@localhostA HS local 1 s 665 msA SFV APROD- console 3$V A STAGINGconsole"Dockengroup_ids":L9J, "report_type": "exec_sgroup_ids":[],"report_type":"producoup_ids":(],"report_type":"produc)Chare vour ceroorГAleave, "group_ids": [1944), "report_type":"c, "group_ids": [1944],"report_type":"e,"group_ids": (1963],"report_type":"(,"group_ids": (1963],"report_type":"e, "group_ids": [2309], "report_type" :"*, "group_ids": [2309), "report_type":"!, "group_ids": [2309],"report_type":"!group_ids": [91, 2368,2,457,8], "reportQ Describe what you are looking foJiminny ...3 Petko KashinsklnExternall connechons* Starred I• jiminny-x-integrati..8 platform-inner-team# Channeld# ai-chapten# alerts# backend# bugs# confusion-clinic# curiosity lab# engineering# general# jiminny-bg# platform-tickets# product launchesi random# releases"sona-oince# support# thank-vous# the people of jimi..Messages12 Add canvasP FilesYesterdayvAnudd le nanbened 12.14 PMYou and Petko Kashinski were in the huddle for.• Saved for later • Due 2 hours agoPetko Kachincki 12.21 PMlnlavhackVisitediTodayLukas Kovalik 10:36 AMдооро утроПетко имаш ли минутка да те питам за РНPetko Kashinski 10-52 AMХeй ЛvкаттlСлел минутка окей ли е ?Lukas Kovalik 10.52 AMnazonna cePetko Kashinski 10:54 AMUnddleYou joined the huddleLIVE 10:55 AMMeccaae Petka KachinckilA Direct messagesPetko…03 02al Crotuen Coorcinresets Mav 12. 11:00€ : -1-6580-4849-00f1-980c-baa3-4c46-bea1-b005-66ch-45he-hA84-8Ae16-2475-40f2-a2Fc-fac3-8aa6-445d-h009-d2e5-5d7c-47f3-a911-9d22-0544-41bd-81e9-3999-70ce-497e-9b64-7c98-6065-4562-0160-1c2S-0217-43f9-a590-2cd16 t 2025 - A1125 - ALU- Client Succecs13 Sep 2025 - Client Successlient Successen 2025 - Client Successpdfodfndfpodcastpdfpodcast<nULL›<null><null>0 {"team_id":1,"group_ids":[]."report type"."exec siA Huddle with Dotkn Kochincki0 {"team_id":1, "request_ id"."318d3ce6-c70a-416a-8b1-0 {"team_id":1,"request_id":"4c40a7d6-4697-4b80-83f0-27d7885e2d63", "report_type":"exec_summary", "media_types":["pdf"].f-cd94-4697-ab00-c53Al Notec: Offeave6-c70a-416a-8b1f-aeb{"request id"."4c40a7d6-4697-4b80-83f0-27d<nul]>0 {"team_id":1,"request_id":"11a01db1-7358-4f91-a75c-169ef39cf7d8", "report_type":"exec_summary" "media_types":["pdf"].sinpques+ id".111a01dh1-7358-4401-a75c-160<null><null>0 {"team_id":1,"request_id":"75fa7c3a-03ae-4836-b0bc-861bb42d2d25" , "report_type":"coaching_profiles" "media_types":["p{"request_id":"75fa7c3a-03ae-4836-b0bc-8610 {"team id":1,"request id":"9a812aee-c2ee-4908-83c3-17478465f014" "report type":"exec summary" "media types":["pdf" "podc {"request id":"9a812aee-c2ee-4908-83c3-1740 {"team_id":1. "request id"."9a812aee-c2ee-4908-83c3-17478465f014" "report type"."exec summary" "media types".["odf"_"{"request_id". "9a812aee-c2ee-4908-83c3-174W Windsurf Teams...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
23513
|
|
23528
|
C=+FirefoxFileEditViewHistoryBookmarksProfilesTool C=+FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelpabl§ Support Daily - in 4h 2 m100% (8•Tue 12 May 10:58:42→Cws.planhat.com/jiminny/home/data-explorer/usagemetricdef?preview=UsageMetricDef.69f2c6529c9f21b58804Jiminny vSearch JiminnyContent Explorer7 MetricDatasetautomated-reports-track-interestEnd UserData ExplorerQ autactivities.automated-reports-track-interestCalendarNameNotificationsOverviewRaw DataTrace**• Morev EndUser 1Metricsautomated-reports-track-Sections +CS Day-to-day2 Getting started GuideJust CS Data* Daily Operations05 May06 May07 May08 May• Weekly prep© Renewals and Upsell:5 € Risk and Churn An...ImplementationImpl ProjectsTrial Opps (Under Rev...Stoyan's clients®+LukasFilter by CompanyMay 05, 2026 - May 11, 202609 May10 May11 MayDAYS Vas aSUM Vacross companiesNo groups found+ Show full listCommentsAdd a comment...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
23528
|
|
23529
|
AI Notes: Off
Thread
Every huddle has a thread
Sen AI Notes: Off
Thread
Every huddle has a thread
Send messages, files, and links to everyone in the huddle. They’re saved as a thread in this direct message with
@Petko Kashinski
@Petko Kashinski
, so you can access it even after the huddle is done.
Also send as direct message
Also send as direct message
Hide thread
Steliyan Georgiev, Direct Message, 1 of 7 suggestions
slacksuppont Dally • In 4h z1• lue 1z May 10:00.44FV faVsco.js?9 JY-20725-handle-HS-search-rate-limitProiectus vetur.conng.sM. WEBHOOK FILTERING IMPLEM> dh External Librariesv E° Scratches and Consolesv M Database ConsolesV AEUA console [EU]A DEAL RISKS (EU]A DI (EU]A EU (EU& liminny@localnost& console liminny @localno* Dl liminny@localhostf hs local liminny@localncA SF [iiminny@localhostlA zoho dev [iiminny@localhAPROD& console PRODII¿ console 1 [PROD1A DI PRODIC) AutomatedReportGenerated.php© PlaybackController.phpreadonly class PlanhatServicepublic function track(User Suser, string Sevent, array $payload = (]): voidpudld -lPlanhatService.php X=custom.log=laravel.logA SF (jiminny@localhost]4 HS_local [jiminny@localhost]« console [PROD] X# console [eu)412 V19 AVA console [STAGING]6д Huddle with Petko Kashinski#= Al Notes: OffservicesLukas KovalikScreen sharevmnatahaseV AEU& consolev &iiminny@localhostA HS local 1 s 665 msA SFV APROD- console 3$V A STAGINGconsole"DockenALL16 t 2025 - A1125 - ALU- Client Succecs13 Sep 2025 - Client Successlient Successen 2025 - Client SuccessPlanhat Event Playbac+0 ..Tx: AutovSo jiminnyfind planhat event playback visited3841 835 X04Threadn1d = 877141@ Every huddle has a thread4162-9004-75T+51856689' = UU1diSend messages. fles. and llinks to evervone in theuid:huddle. Thev're saved as a threadiin this directmessage with @Petko Kashinski, so you canaccess it even after the huddle is doneReolv...Also send as direct messageil';ecimal)1:datetime, expr2:datetime)Activitygroup_ids":L9J, "report_type": "exec_sgroup_ids":[],"report_type":"producgroup_ids":(],"report_type":"produc). "group_ids": [1944), "report_type":"c, "group_ids": [1944],"report_type":"e, "group_ids": (1963],"report_type":"(|, "groupids": (1963],"report_type":"e, "group_ids": [2309], "report_type" :"*"group_ids":[2309], "report_type":"!, "group_ids": [2309],"report_type":"!leavegroup_ids": [91,2368,2,457,8],"reporiQ Describe what you are looking foJiminny ...3 Petko KashinsklnExternall connechons* Starred I• jiminny-x-integrati..8 platform-inner-team# Channeld# ai-chapten# alerts# backend# bugs# confusion-clinic# curiosity lab# engineering# general# jiminny-bg# platform-tickets# product launchesi random# releases"sona-oince# support# thank-vous# the people of jimi..Messages12 Add canvasP FilesYesterdayvAnudd le nanbened 12.14 PMYou and Petko Kashinski were in the huddle for.• Saved for later • Due 2 hours agoPetko Kachincki 12.21 PMlnlavhackVisitediTodayLukas Kovalik 10:36 AMдооро утроПетко имаш ли минутка да те питам за РНPetko Kashinski 10-52 AMХeй ЛvкаттlСлел минутка окей ли е ?Lukas Kovalik 10:52 AMnazonna cePetko Kashinski 10:54 AMUnddleYou joined the huddle LIVE 10:55 AMMeccaae Petka KachinckilA Direct messagesPetko...03 02al Crotuen Coorcinresets Mav 12. 11:001-6580-4849-00f1-980c-baa3-4c46-bea1-b005-66ch-45he-hA84-8Ae16-2475-40f2-a2Fc-fac3-8aa6-445d-h009-d2e5-5d7c-47f3-a911-9d22-0544-41bd-81e9-3999-70ce-497e-9b64-7c98-6065-4562-0160-1c2S-0217-43f9-a590-2cd<nULL›<nUll><null>0 {"team_id":1."group_ids":[]."report type"."exec si0 {"team_id":1, "request_id"."318d3ce6-c70a-416a-8b1-A Huddle with Dotkn Kochinckiodfndfpodcastpdfpodcast0 {"team_id":1,"request_id":"4c40a7d6-4697-4b80-83f0-27d7885e2d63", "report_type":"exec_summary", "media_types":["pdf"].f-cd94-4697-ab00-c53Al Notec: Offeave6-c70a-416a-8b1f-aeb{"request id"."4c40a7d6-4697-4b80-83f0-27d<nul]>0 {"team_id":1,"request_id":"11a01db1-7358-4f91-a75c-169ef39cf7d8", "report_type":"exec_summary" "media_types":["pdf"].sinpques+ id".111a01dh1-7358-4401-a75c-160<null>0 {"team_id":1,"request_id":"75fa7c3a-03ae-4836-b0bc-861bb42d2d25" , "report_type":"coaching_profiles" "media_types":["p{"request_id":"75fa7c3a-03ae-4836-b0bc-861<null>0 {"team_id":1,"request id":"9a812aee-c2ee-4908-83c3-17478465f014" "report type":"exec summary" "media types":["pdf" "{"request id":"9a812aee-c2ee-4908-83c3-1740 {"team_id":1. "request id"-"9a812aee-c2ee-4908-83c3-17478465f014" "report type"."exec summarv" "media_types".["odf"_"{"request_id". "9a812aee-c2ee-4908-83c3-174W Windsurf Teams...
|
Slack
|
Huddle: @Petko Kashinski - Jiminny Inc - Slack
|
NULL
|
23529
|
|
21057
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21057
|
|
21058
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21058
|
|
21059
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit
cli.py
cli.py
Added 40 lines
Done. Here's how to run pipes:
How to run pipes
How to run pipes
Via Docker (inside the running container):
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe --list
docker exec -it screenpipe-app python cli.py pipe day-recap
docker exec -it screenpipe-app python cli.py pipe standup-update --date yesterday
Via the API
(once the container is running on port 8766):
Copy code to clipboard
# List pipes
curl http://localhost:8766/api/pipes
# Run a pipe
curl -X POST "http://localhost:8766/api/pipes/day-recap/run"
curl -X POST "http://localhost:8766/api/pipes/standup-update/run?d=2026-04-25"
Rebuild and restart
to pick up the changes:
Copy code to clipboard
cd /volume1/screenpipe/app
docker compose up --build -d
How it works:
Each
pipe.md
file is loaded dynamically — the frontmatter provides metadata and the body becomes the user prompt. Screenpipe data (app usage, browser URLs, OCR, audio) is injected as a Claude system message so the pipe prompt can reference it naturally. The "Read screenpipe skill first" line is stripped automatically.
The pipes directory inside Docker is
/data/pipes...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21059
|
|
21060
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit
cli.py
cli.py
Added 40 lines
Done. Here's how to run pipes:
How to run pipes
How to run pipes
Via Docker (inside the running container):
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe --list
docker exec -it screenpipe-app python cli.py pipe day-recap
docker exec -it screenpipe-app python cli.py pipe standup-update --date yesterday
Via the API
(once the container is running on port 8766):
Copy code to clipboard
# List pipes
curl [URL_WITH_CREDENTIALS] sudo docker exec -it screenpipe-app python cli.py pipe day-recap --date 2026-04-20
Running pipe 'day-recap' for 2026-04-20...
Traceback (most recent call last):
File "/app/cli.py", line 245, in <module>
cli()
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 1161, in __call__
return self.main(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 1082, in main
rv = self.invoke(ctx)
^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 1697, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 1443, in invoke
return ctx.invoke(self.callback, **ctx.params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 788, in invoke
return __callback(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/cli.py", line 225, in pipe
result = run_pipe(pipe_id, target, pipes_dir=pipes_dir)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/consumers/pipes.py", line 130, in run_pipe
message = client.messages.create(
^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/_utils/_utils.py", line 275, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/resources/messages/messages.py", line 953, in create
return self._post(
^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/_base_client.py", line 1336, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/_base_client.py", line 1013, in request
return self._request(
^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/_base_client.py", line 1117, in _request
raise self._make_status_error_from_response(err.response) from None
anthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'invalid x-api-key'}, 'request_id': 'req_011CaSoR75WgV8fTcHTYJMDY'}
Adm1n@DXP4800PLUS-B5F8:/volume1/screenpipe/app$
Thinking
Thinking
The container started before you updated the
.env
, so it's using the old placeholder key. Restart it to pick up the new one:
Copy code to clipboard
cd /volume1/screenpipe/app
sudo docker compose restart screenpipe-app
Then try again:
Copy code to clipboard
sudo docker exec -it screenpipe-app python cli.py pipe day-recap --date 2026-04-20
Message actions
Adm1n@DXP4800PLUS-B5F8:/volume1/screenpipe/app$ sudo docker exec -it screenpipe-app python cli.py pipe day-recap --date 2026-04-20
Running pipe 'day-recap' for 2026-04-20...
Traceback (most recent call last):
File "/app/cli.py", line 245, in <module>
cli()
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 1161, in __call__
return self.main(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 1082, in main
rv = self.invoke(ctx)
^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 1697, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 1443, in invoke
return ctx.invoke(self.callback, **ctx.params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 788, in invoke
return __callback(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/cli.py", line 225, in pipe
result = run_pipe(pipe_id, target, pipes_dir=pipes_dir)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/consumers/pipes.py", line 130, in run_pipe
message = client.messages.create(
^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/_utils/_utils.py", line 275, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/resources/messages/messages.py", line 953, in create
return self._post(
^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/_base_client.py", line 1336, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/_base_client.py", line 1013, in request
return self._request(
^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/_base_client.py", line 1117, in _request
raise self._make_status_error_from_response(err.response) from None
anthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'invalid x-api-key'}, 'request_id': 'req_011CaSoaWfbMTbPTbw5PpBu1'}
Adm1n@DXP4800PLUS-B5F8:/volume1/screenpipe/app$
Message actions...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21060
|
|
21061
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit
cli.py
cli.py
Added 40 lines
Done. Here's how to run pipes:
How to run pipes
How to run pipes
Via Docker (inside the running container):
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe --list
docker exec -it screenpipe-app python cli.py pipe day-recap
docker exec -it screenpipe-app python cli.py pipe standup-update --date yesterday
Via the API
(once the container is running on port 8766):
Copy code to clipboard
# List pipes
curl http://localhost:8766/api/pipes
# Run a pipe
curl -X POST "http://localhost:8766/api/pipes/day-recap/run"
curl -X POST "http://localhost:8766/api/pipes/standup-update/run?d=2026-04-25"
Rebuild and restart
to pick up the changes:
Copy code to clipboard
cd /volume1/screenpipe/app
docker compose up --build -d
How it works:
Each
pipe.md
file is loaded dynamically — the frontmatter provides metadata and the body becomes the user prompt. Screenpipe data (app usage, browser URLs, OCR, audio) is injected as a Claude system message so the pipe prompt can reference it naturally. The "Read screenpipe skill first" line is stripped automatically.
The pipes directory inside Docker is
/data/pipes
(since
/volume1/screenpipe
→
/data
). You can override it with a
PIPES_DIR
env var if needed.
Message actions
pipe.md
pipe.md
where to place api key and can I use different keys
Thinking
Thinking
Bash
Read .env file
IN
cat /volume1/screenpipe/app/.env
Copy code to clipboard
OUT
[ENV_SECRET]
Where to place the key:
app/.env
app/.env
— replace
your_key_here
with your actual key:
Copy code to clipboard
[ENV_SECRET]
That file is loaded by
load_dotenv()
at startup and is excluded from git via
.gitignore
.
Can you use different keys per pipe?
Not currently — all pipes share the one key from
.env
. But you can add per-pipe key support by adding an
api_key...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21061
|
|
21062
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit
cli.py
cli.py
Added 40 lines
Done. Here's how to run pipes:
How to run pipes
How to run pipes
Via Docker (inside the running container):
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe --list
docker exec -it screenpipe-app python cli.py pipe day-recap
docker exec -it screenpipe-app python cli.py pipe standup-update --date yesterday
Via the API
(once the container is running on port 8766):
Copy code to clipboard
# List pipes
curl http://localhost:8766/api/pipes
# Run a pipe
curl -X POST "http://localhost:8766/api/pipes/day-recap/run"
curl -X POST "http://localhost:8766/api/pipes/standup-update/run?d=2026-04-25"
Rebuild and restart
to pick up the changes:
Copy code to clipboard
cd /volume1/screenpipe/app
docker compose up --build -d
How it works:
Each
pipe.md
file is loaded dynamically — the frontmatter provides metadata and the body becomes the user prompt. Screenpipe data (app usage, browser URLs, OCR, audio) is injected as a Claude system message so the pipe prompt can reference it naturally. The "Read screenpipe skill first" line is stripped automatically.
The pipes directory inside Docker is
/data/pipes
(since
/volume1/screenpipe
→
/data
). You can override it with a
PIPES_DIR
env var if needed.
Message actions
pipe.md
pipe.md
where to place api key and can I use different keys
Thinking
Thinking
Bash
Read .env file
IN
cat /volume1/screenpipe/app/.env
Copy code to clipboard
OUT
[ENV_SECRET]
Where to place the key:
app/.env
app/.env
— replace
your_key_here
with your actual key:
Copy code to clipboard
[ENV_SECRET]
That file is loaded by
load_dotenv()
at startup and is excluded from git via
.gitignore
.
Can you use different keys per pipe?
Not currently — all pipes share the one key from
.env
. But you can add per-pipe key support by adding an
api_key
field to the pipe's frontmatter:
Copy code to clipboard
---
title: Meeting Summary
api_key_env: ANTHROPIC_KEY_MEETINGS
---
Then in
consumers/pipes.py
consumers/pipes.py
, read it in
_parse_frontmatter
and pass it through
run_pipe
. Want me to add that?
Message actions
pipe.md
pipe.md
can I use mistral or other llm? or is is build for antrophic only
Thinking
Thinking
Currently it's Anthropic-only — the code calls the
anthropic
SDK directly in both
consumers/pipes.py
consumers/pipes.py
and
consumers/summary.py
consumers/summary.py
.
Adding other providers is straightforward since Mistral, Ollama, OpenRouter, Groq, and most modern LLMs expose an OpenAI-compatible API. The cleanest approach: add the
openai
package and let you configure the provider via
.env
:
Copy code to clipboard
# Anthropic (default)
[ENV_SECRET]
# OR: any OpenAI-compatible provider
LLM_PROVIDER=openai-compatible
LLM_BASE_URL=https://api.mistral.ai/v1
[ENV_SECRET]
LLM_MODEL=mistral-small-latest
This would cover Mistral, Ollama (
http://localhost:11434/v1
), OpenRouter, Groq, etc. with one code path.
Want me to implement that? It's a small change — a
_call_llm(system, user_prompt)
helper in
pipes.py
that branches on
LLM_PROVIDER
, and
openai
added to
requirements.txt
.
Message actions
lets test it with anthropic first, how to run pipe
Thinking
Thinking
Bash
Check if container is running
IN
cd /volume1/screenpipe/app && docker compose ps 2>/dev/null || docker ps --filter name=screenpipe
Copy code to clipboard
OUT
Exit code 1
permission denied while trying to connect to the Docker daemon socket at unix:///var/run/docker.sock: Get "http://%2Fvar%2Frun%2Fdocker.sock/v1.45/containers/json?filters=%7B%22name%22%3A%7B%22screenpipe%22%3Atrue%7D%7D": dial unix /var/run/docker.sock: connect: permission denied
I don't have Docker socket access, so you'll need to run these yourself. Here are your options:
Option A — via Docker (if container is already running):
Copy code to clipboard
# List available pipes
docker exec -it screenpipe-app python cli.py pipe --list
# Run a specific pipe
docker exec -it screenpipe-app python cli.py pipe day-recap
Option B — rebuild first (since we added new files), then run:
Copy code to clipboard
cd /volume1/screenpipe/app
docker compose up --build -d
docker exec -it screenpipe-app python cli.py pipe day-recap
Option C — via the API
(if container is up on port 8766):
Copy code to clipboard
# List pipes
curl http://localhost:8766/api/pipes
# Run a pipe
curl -X POST http://localhost:8766/api/pipes/day-recap/run
The
day-recap
or
standup-update
pipes are the best ones to test first since they use all data sources. Which option works for you?
Message actions
how ot run for specifiday
Thinking
Thinking
Docker exec:
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe day-recap --date 2026-04-25
# or shortcuts:
docker exec -it screenpipe-app python cli.py pipe day-recap --date yesterday
docker exec -it screenpipe-app python cli.py pipe day-recap --date today
API:
Copy code to clipboard...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21062
|
|
21063
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21063
|
|
21064
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit
cli.py
cli.py
Added 40 lines
Done. Here's how to run pipes:
How to run pipes
How to run pipes
Via Docker (inside the running container):
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe --list
docker exec -it screenpipe-app python cli.py pipe day-recap
docker exec -it screenpipe-app python cli.py pipe standup-update --date yesterday
Via the API
(once the container is running on port 8766):
Copy code to clipboard
# List pipes
curl [URL_WITH_CREDENTIALS] sudo docker exec -it screenpipe-app python cli.py pipe day-recap --date 2026-04-20
Running pipe 'day-recap' for 2026-04-20...
Traceback (most recent call last):
File "/app/cli.py", line 245, in <module>
cli()
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 1161, in __call__
return self.main(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 1082, in main
rv = self.invoke(ctx)
^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 1697, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 1443, in invoke
return ctx.invoke(self.callback, **ctx.params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/click/core.py", line 788, in invoke
return __callback(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/cli.py", line 225, in pipe
result = run_pipe(pipe_id, target, pipes_dir=pipes_dir)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/consumers/pipes.py", line 130, in run_pipe
message = client.messages.create(
^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/_utils/_utils.py", line 275, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/resources/messages/messages.py", line 953, in create
return self._post(
^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/_base_client.py", line 1336, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/_base_client.py", line 1013, in request
return self._request(
^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/anthropic/_base_client.py", line 1117, in _request
raise self._make_status_error_from_response(err.response) from None
anthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'invalid x-api-key'}, 'request_id': 'req_011CaSoR75WgV8fTcHTYJMDY'}
Adm1n@DXP4800PLUS-B5F8:/volume1/screenpipe/app$
Thinking
Thinking...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21064
|
|
21065
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21065
|
|
21066
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit
cli.py
cli.py
Added 40 lines
Done. Here's how to run pipes:
How to run pipes
How to run pipes
Via Docker (inside the running container):
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe --list
docker exec -it screenpipe-app python cli.py pipe day-recap
docker exec -it screenpipe-app python cli.py pipe standup-update --date yesterday
Via the API
(once the container is running on port 8766):
Copy code to clipboard...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21066
|
|
21067
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit
cli.py
cli.py
Added 40 lines
Done. Here's how to run pipes:
How to run pipes
How to run pipes
Via Docker (inside the running container):
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe --list
docker exec -it screenpipe-app python cli.py pipe day-recap
docker exec -it screenpipe-app python cli.py pipe standup-update --date yesterday
Via the API
(once the container is running on port 8766):
Copy code to clipboard
# List pipes
curl http://localhost:8766/api/pipes
# Run a pipe
curl -X POST "http://localhost:8766/api/pipes/day-recap/run"
curl -X POST "http://localhost:8766/api/pipes/standup-update/run?d=2026-04-25"
Rebuild and restart
to pick up the changes:
Copy code to clipboard
cd /volume1/screenpipe/app
docker compose up --build -d
How it works:
Each
pipe.md
file is loaded dynamically — the frontmatter provides metadata and the body becomes the user prompt. Screenpipe data (app usage, browser URLs, OCR, audio) is injected as a Claude system message so the pipe prompt can reference it naturally. The "Read screenpipe skill first" line is stripped automatically.
The pipes directory inside Docker is
/data/pipes
(since
/volume1/screenpipe
→
/data
). You can override it with a
PIPES_DIR
env var if needed.
Message actions
pipe.md
pipe.md
where to place api key and can I use different keys
Thinking
Thinking
Bash
Read .env file
IN
cat /volume1/screenpipe/app/.env
Copy code to clipboard
OUT
[ENV_SECRET]
Where to place the key:
app/.env
app/.env
— replace
your_key_here
with your actual key:
Copy code to clipboard
[ENV_SECRET]
That file is loaded by
load_dotenv()
at startup and is excluded from git via
.gitignore
.
Can you use different keys per pipe?
Not currently — all pipes share the one key from
.env
. But you can add per-pipe key support by adding an
api_key
field to the pipe's frontmatter:
Copy code to clipboard
---
title: Meeting Summary
api_key_env: ANTHROPIC_KEY_MEETINGS
---
Then in
consumers/pipes.py
consumers/pipes.py
, read it in
_parse_frontmatter
and pass it through
run_pipe
. Want me to add that?
Message actions
pipe.md
pipe.md
can I use mistral or other llm? or is is build for antrophic only
Thinking
Thinking
Currently it's Anthropic-only — the code calls the
anthropic
SDK directly in both
consumers/pipes.py
consumers/pipes.py
and
consumers/summary.py
consumers/summary.py
.
Adding other providers is straightforward since Mistral, Ollama, OpenRouter, Groq, and most modern LLMs expose an OpenAI-compatible API. The cleanest approach: add the
openai
package and let you configure the provider via
.env
:...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21067
|
|
21068
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21068
|
|
21069
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21069
|
|
21070
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21070
|
|
21071
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
[ENV_SECRET]
[ENV_SECRET]
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit
cli.py
cli.py
Added 40 lines
Done. Here's how to run pipes:
How to run pipes
How to run pipes
Via Docker (inside the running container):
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe --list
docker exec -it screenpipe-app python cli.py pipe day-recap
docker exec -it screenpipe-app python cli.py pipe standup-update --date yesterday
Via the API
(once the container is running on port 8766):
Copy code to clipboard
# List pipes
curl http://localhost:8766/api/pipes
# Run a pipe
curl -X POST "http://localhost:8766/api/pipes/day-recap/run"
curl -X POST "http://localhost:8766/api/pipes/standup-update/run?d=2026-04-25"
Rebuild and restart
to pick up the changes:
Copy code to clipboard
cd /volume1/screenpipe/app
docker compose up --build -d
How it works:
Each
pipe.md
file is loaded dynamically — the frontmatter provides metadata and the body becomes the user prompt. Screenpipe data (app usage, browser URLs, OCR, audio) is injected as a Claude system message so the pipe prompt can reference it naturally. The "Read screenpipe skill first" line is stripped automatically.
The pipes directory inside Docker is
/data/pipes
(since
/volume1/screenpipe
→
/data
). You can override it with a
PIPES_DIR
env var if needed.
Message actions
pipe.md
pipe.md
where to place api key and can I use different keys
Thinking
Thinking
Bash
Read .env file
IN
cat /volume1/screenpipe/app/.env
Copy code to clipboard
OUT
[ENV_SECRET]
Where to place the key:
app/.env
app/.env
— replace
your_key_here
with your actual key:
Copy code to clipboard
[ENV_SECRET]
That file is loaded by
load_dotenv()
at startup and is excluded from git via
.gitignore
.
Can you use different keys per pipe?
Not currently — all pipes share the one key from
.env
. But you can add per-pipe key support by adding an
api_key
field to the pipe's frontmatter:
Copy code to clipboard
---
title: Meeting Summary
api_key_env: ANTHROPIC_KEY_MEETINGS
---
Then in
consumers/pipes.py
consumers/pipes.py
, read it in
_parse_frontmatter
and pass it through
run_pipe
. Want me to add that?
Message actions
pipe.md
pipe.md
can I use mistral or other llm? or is is build for antrophic only
Thinking
Thinking
Currently it's Anthropic-only — the code calls the
anthropic
SDK directly in both
consumers/pipes.py
consumers/pipes.py
and
consumers/summary.py
consumers/summary.py
.
Adding other providers is straightforward since Mistral, Ollama, OpenRouter, Groq, and most modern LLMs expose an OpenAI-compatible API. The cleanest approach: add the...
|
Code
|
Implement and run pipe l… — screenpipe [SSH: nas]
|
NULL
|
21071
|