opencastle 0.10.7 → 0.11.0

package/src/dashboard/seed-data/events.ndjson

@@ -0,0 +1,104 @@
+{"type":"delegation","timestamp":"2026-02-20T08:00:00.000Z","session_id":"feat/tas-43","agent":"DevOps Expert","model":"gpt-5-mini","tier":"standard","mechanism":"sub-agent","tracker_issue":"TAS-43","outcome":"success","retries":1,"phase":1,"file_partition":["libs/queries/","libs/server-utils/"]}
+{"type":"panel","timestamp":"2026-02-20T08:00:00.000Z","panel_key":"auth-review","verdict":"pass","pass_count":2,"block_count":1,"must_fix":0,"should_fix":6,"reviewer_model":"gpt-5.3-codex","weighted":false,"attempt":1,"tracker_issue":"TAS-43","artifacts_count":7,"report_path":"docs/ai-agents/panel/auth-review.md"}
+{"type":"session","timestamp":"2026-02-20T08:00:34.359Z","agent":"Architect","model":"claude-opus-4-6","task":"TAS-46: Fix CORS headers","tracker_issue":"TAS-46","outcome":"success","duration_min":20,"files_changed":9,"retries":1,"lessons_added":["LES-002"],"discoveries":[]}
+{"type":"session","timestamp":"2026-02-20T11:05:05.028Z","agent":"Supabase DB Expert","model":"gpt-5-mini","task":"TAS-56: Fix redirect loop","tracker_issue":"TAS-56","outcome":"partial","duration_min":32,"files_changed":5,"retries":2,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-20T11:38:52.677Z","session_id":"feat/tas-31","agent":"Architect","model":"gpt-5.3-codex","tier":"economy","mechanism":"sub-agent","tracker_issue":"TAS-31","outcome":"success","retries":0,"phase":2,"file_partition":["libs/data-pipeline/"]}
+{"type":"session","timestamp":"2026-02-20T13:16:10.762Z","agent":"Sanity Expert","model":"gpt-5-mini","task":"TAS-51: Fix redirect loop","tracker_issue":"TAS-51","outcome":"success","duration_min":33,"files_changed":11,"retries":1,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-20T15:37:40.293Z","session_id":"feat/tas-59","agent":"Documentation Writer","model":"gemini-3.1-pro","tier":"standard","mechanism":"background","tracker_issue":"TAS-59","outcome":"success","retries":0,"phase":2,"file_partition":["libs/data-pipeline/"]}
+{"type":"session","timestamp":"2026-02-20T15:42:21.649Z","agent":"Architect","model":"gpt-5.3-codex","task":"TAS-48: Add venue suggestions","tracker_issue":"TAS-48","outcome":"success","duration_min":42,"files_changed":6,"retries":1,"lessons_added":["LES-005"],"discoveries":[]}
+{"type":"session","timestamp":"2026-02-20T18:33:39.948Z","agent":"Next.js Developer","model":"gemini-3.1-pro","task":"TAS-45: Add image optimization","tracker_issue":"TAS-45","outcome":"success","duration_min":17,"files_changed":6,"retries":0,"lessons_added":[],"discoveries":[]}
+{"type":"panel","timestamp":"2026-02-20T19:09:32.117Z","panel_key":"security-audit","verdict":"pass","pass_count":2,"block_count":1,"must_fix":0,"should_fix":5,"reviewer_model":"claude-opus-4-6","weighted":false,"attempt":1,"tracker_issue":"TAS-48","artifacts_count":9,"report_path":"docs/ai-agents/panel/security-audit.md"}
+{"type":"delegation","timestamp":"2026-02-20T19:36:10.946Z","session_id":"feat/tas-49","agent":"Data Expert","model":"gemini-3.1-pro","tier":"utility","mechanism":"sub-agent","tracker_issue":"TAS-49","outcome":"partial","retries":0,"phase":3,"file_partition":["libs/queries/","libs/server-utils/"]}
+{"type":"session","timestamp":"2026-02-20T20:50:56.727Z","agent":"UI/UX Expert","model":"claude-opus-4-6","task":"TAS-49: Fix redirect loop","tracker_issue":"TAS-49","outcome":"success","duration_min":29,"files_changed":13,"retries":1,"lessons_added":["LES-002"],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-20T23:09:18.799Z","session_id":"feat/tas-49","agent":"Supabase DB Expert","model":"gpt-5-mini","tier":"utility","mechanism":"background","tracker_issue":"TAS-49","outcome":"failed","retries":1,"phase":3,"file_partition":["libs/ui-kit/","apps/tastebeer.eu/app/"]}
+{"type":"session","timestamp":"2026-02-21T00:05:00.537Z","agent":"Testing Expert","model":"gpt-5-mini","task":"TAS-58: Fix mobile layout","tracker_issue":"TAS-58","outcome":"partial","duration_min":36,"files_changed":5,"retries":1,"lessons_added":[],"discoveries":[]}
+{"type":"session","timestamp":"2026-02-21T01:56:41.910Z","agent":"Supabase DB Expert","model":"gpt-5.3-codex","task":"TAS-42: Optimize bundle size","tracker_issue":"TAS-42","outcome":"partial","duration_min":25,"files_changed":15,"retries":2,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-21T02:23:04.138Z","session_id":"feat/tas-32","agent":"Security Expert","model":"gpt-5-mini","tier":"utility","mechanism":"sub-agent","tracker_issue":"TAS-32","outcome":"success","retries":0,"phase":1,"file_partition":["apps/tastebeer.eu/app/","apps/tastecoffee.eu/app/"]}
+{"type":"session","timestamp":"2026-02-21T05:11:42.700Z","agent":"Security Expert","model":"gpt-5.3-codex","task":"TAS-51: Add image optimization","tracker_issue":"TAS-51","outcome":"success","duration_min":11,"files_changed":5,"retries":1,"lessons_added":["LES-002"],"discoveries":["Refactor auth flow"]}
+{"type":"delegation","timestamp":"2026-02-21T05:52:23.451Z","session_id":"feat/tas-39","agent":"Next.js Developer","model":"gpt-5.3-codex","tier":"utility","mechanism":"sub-agent","tracker_issue":"TAS-39","outcome":"success","retries":0,"phase":4,"file_partition":["apps/cms-studio/"]}
+{"type":"panel","timestamp":"2026-02-21T06:02:55.882Z","panel_key":"perf-review","verdict":"pass","pass_count":3,"block_count":0,"must_fix":0,"should_fix":8,"reviewer_model":"gpt-5-mini","weighted":false,"attempt":1,"tracker_issue":"TAS-37","artifacts_count":16,"report_path":"docs/ai-agents/panel/perf-review.md"}
+{"type":"session","timestamp":"2026-02-21T07:24:02.899Z","agent":"Next.js Developer","model":"gpt-5.3-codex","task":"TAS-42: Update scraper logic","tracker_issue":"TAS-42","outcome":"success","duration_min":24,"files_changed":9,"retries":0,"lessons_added":[],"discoveries":[]}
+{"type":"session","timestamp":"2026-02-21T10:15:19.797Z","agent":"DevOps Expert","model":"gemini-3.1-pro","task":"TAS-53: Update SEO metadata","tracker_issue":"TAS-53","outcome":"success","duration_min":29,"files_changed":11,"retries":0,"lessons_added":[],"discoveries":["Update venue detail"]}
+{"type":"delegation","timestamp":"2026-02-21T10:29:16.394Z","session_id":"feat/tas-41","agent":"Testing Expert","model":"claude-opus-4-6","tier":"utility","mechanism":"background","tracker_issue":"TAS-41","outcome":"success","retries":1,"phase":2,"file_partition":["libs/data-pipeline/","libs/queries/"]}
+{"type":"session","timestamp":"2026-02-21T12:33:24.255Z","agent":"Testing Expert","model":"gemini-3.1-pro","task":"TAS-50: Refactor auth flow","tracker_issue":"TAS-50","outcome":"success","duration_min":29,"files_changed":11,"retries":0,"lessons_added":[],"discoveries":["Add social links"]}
+{"type":"delegation","timestamp":"2026-02-21T14:00:03.752Z","session_id":"feat/tas-50","agent":"Next.js Developer","model":"gpt-5.3-codex","tier":"utility","mechanism":"sub-agent","tracker_issue":"TAS-50","outcome":"success","retries":0,"phase":1,"file_partition":["libs/supabase-auth/"]}
+{"type":"session","timestamp":"2026-02-21T14:54:49.349Z","agent":"Data Expert","model":"gpt-5-mini","task":"TAS-47: Fix slug generation","tracker_issue":"TAS-47","outcome":"partial","duration_min":25,"files_changed":3,"retries":2,"lessons_added":[],"discoveries":[]}
+{"type":"panel","timestamp":"2026-02-21T16:32:56.551Z","panel_key":"a11y-audit","verdict":"block","pass_count":0,"block_count":3,"must_fix":4,"should_fix":3,"reviewer_model":"claude-opus-4-6","weighted":false,"attempt":2,"tracker_issue":"TAS-39","artifacts_count":16,"report_path":"docs/ai-agents/panel/a11y-audit.md"}
+{"type":"delegation","timestamp":"2026-02-21T17:10:13.592Z","session_id":"feat/tas-41","agent":"UI/UX Expert","model":"gpt-5.3-codex","tier":"premium","mechanism":"sub-agent","tracker_issue":"TAS-41","outcome":"success","retries":1,"phase":1,"file_partition":["apps/tastecoffee.eu/app/"]}
+{"type":"session","timestamp":"2026-02-21T18:06:15.985Z","agent":"Sanity Expert","model":"gemini-3.1-pro","task":"TAS-44: Update moderation UI","tracker_issue":"TAS-44","outcome":"success","duration_min":18,"files_changed":4,"retries":1,"lessons_added":["LES-010"],"discoveries":["Fix pagination"]}
+{"type":"session","timestamp":"2026-02-21T20:51:57.384Z","agent":"Performance Expert","model":"claude-opus-4-6","task":"TAS-47: Add geolocation","tracker_issue":"TAS-47","outcome":"partial","duration_min":22,"files_changed":3,"retries":1,"lessons_added":["LES-006"],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-21T21:26:17.711Z","session_id":"feat/tas-58","agent":"Sanity Expert","model":"gpt-5-mini","tier":"utility","mechanism":"background","tracker_issue":"TAS-58","outcome":"success","retries":1,"phase":1,"file_partition":["libs/ui-kit/","apps/tastebeer.eu/app/"]}
+{"type":"session","timestamp":"2026-02-21T22:37:25.143Z","agent":"Sanity Expert","model":"gpt-5.3-codex","task":"TAS-38: Fix header navigation","tracker_issue":"TAS-38","outcome":"success","duration_min":38,"files_changed":3,"retries":0,"lessons_added":[],"discoveries":["Add cache headers"]}
+{"type":"delegation","timestamp":"2026-02-22T00:51:23.821Z","session_id":"feat/tas-33","agent":"DevOps Expert","model":"gpt-5-mini","tier":"utility","mechanism":"background","tracker_issue":"TAS-33","outcome":"failed","retries":2,"phase":1,"file_partition":["apps/tastebeer.eu/app/","apps/tastecoffee.eu/app/"]}
+{"type":"session","timestamp":"2026-02-22T02:04:09.220Z","agent":"Data Expert","model":"gpt-5-mini","task":"TAS-40: Update CMS schema","tracker_issue":"TAS-40","outcome":"failed","duration_min":29,"files_changed":1,"retries":3,"lessons_added":["LES-003"],"discoveries":["Add social links"]}
+{"type":"panel","timestamp":"2026-02-22T03:35:46.612Z","panel_key":"schema-review","verdict":"block","pass_count":0,"block_count":3,"must_fix":5,"should_fix":2,"reviewer_model":"gpt-5-mini","weighted":false,"attempt":2,"tracker_issue":"TAS-54","artifacts_count":20,"report_path":"docs/ai-agents/panel/schema-review.md"}
+{"type":"session","timestamp":"2026-02-22T04:18:52.718Z","agent":"Supabase DB Expert","model":"gemini-3.1-pro","task":"TAS-38: Update scraper logic","tracker_issue":"TAS-38","outcome":"success","duration_min":32,"files_changed":1,"retries":0,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-22T04:53:39.261Z","session_id":"feat/tas-35","agent":"Documentation Writer","model":"gpt-5.3-codex","tier":"utility","mechanism":"background","tracker_issue":"TAS-35","outcome":"success","retries":1,"phase":1,"file_partition":["libs/server-utils/"]}
+{"type":"session","timestamp":"2026-02-22T06:31:31.565Z","agent":"Architect","model":"gemini-3.1-pro","task":"TAS-41: Add unit tests","tracker_issue":"TAS-41","outcome":"success","duration_min":13,"files_changed":14,"retries":0,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-22T08:20:53.525Z","session_id":"feat/tas-59","agent":"DevOps Expert","model":"claude-opus-4-6","tier":"standard","mechanism":"sub-agent","tracker_issue":"TAS-59","outcome":"success","retries":0,"phase":4,"file_partition":["libs/queries/"]}
+{"type":"session","timestamp":"2026-02-22T09:44:33.779Z","agent":"Security Expert","model":"gemini-3.1-pro","task":"TAS-51: Update RLS policies","tracker_issue":"TAS-51","outcome":"failed","duration_min":8,"files_changed":10,"retries":3,"lessons_added":["LES-004"],"discoveries":["Update scraper logic"]}
+{"type":"delegation","timestamp":"2026-02-22T11:43:14.243Z","session_id":"feat/tas-36","agent":"Next.js Developer","model":"gpt-5.3-codex","tier":"economy","mechanism":"sub-agent","tracker_issue":"TAS-36","outcome":"success","retries":0,"phase":1,"file_partition":["libs/server-utils/"]}
+{"type":"session","timestamp":"2026-02-22T12:20:59.680Z","agent":"Testing Expert","model":"gpt-5-mini","task":"TAS-32: Add venue suggestions","tracker_issue":"TAS-32","outcome":"failed","duration_min":21,"files_changed":12,"retries":3,"lessons_added":["LES-001"],"discoveries":["Fix CORS headers"]}
+{"type":"panel","timestamp":"2026-02-22T14:02:10.154Z","panel_key":"api-review","verdict":"pass","pass_count":3,"block_count":0,"must_fix":0,"should_fix":8,"reviewer_model":"gpt-5.3-codex","weighted":true,"attempt":1,"tracker_issue":"TAS-50","artifacts_count":17,"report_path":"docs/ai-agents/panel/api-review.md"}
+{"type":"session","timestamp":"2026-02-22T14:18:43.678Z","agent":"Supabase DB Expert","model":"claude-opus-4-6","task":"TAS-55: Update search API","tracker_issue":"TAS-55","outcome":"success","duration_min":33,"files_changed":12,"retries":1,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-22T15:29:36.510Z","session_id":"feat/tas-54","agent":"Supabase DB Expert","model":"gpt-5.3-codex","tier":"standard","mechanism":"background","tracker_issue":"TAS-54","outcome":"success","retries":0,"phase":4,"file_partition":["apps/cms-studio/"]}
+{"type":"session","timestamp":"2026-02-22T17:34:33.606Z","agent":"Documentation Writer","model":"claude-opus-4-6","task":"TAS-55: Update venue detail","tracker_issue":"TAS-55","outcome":"success","duration_min":6,"files_changed":6,"retries":1,"lessons_added":[],"discoveries":["Add cache headers"]}
+{"type":"delegation","timestamp":"2026-02-22T19:18:04.518Z","session_id":"feat/tas-41","agent":"DevOps Expert","model":"gemini-3.1-pro","tier":"utility","mechanism":"background","tracker_issue":"TAS-41","outcome":"success","retries":1,"phase":3,"file_partition":["libs/server-utils/"]}
+{"type":"session","timestamp":"2026-02-22T20:17:44.211Z","agent":"Supabase DB Expert","model":"claude-opus-4-6","task":"TAS-36: Add price filter","tracker_issue":"TAS-36","outcome":"success","duration_min":19,"files_changed":4,"retries":0,"lessons_added":[],"discoveries":[]}
+{"type":"session","timestamp":"2026-02-22T22:32:33.601Z","agent":"Supabase DB Expert","model":"claude-opus-4-6","task":"TAS-37: Fix pagination","tracker_issue":"TAS-37","outcome":"partial","duration_min":44,"files_changed":2,"retries":1,"lessons_added":[],"discoveries":["Add venue suggestions"]}
+{"type":"delegation","timestamp":"2026-02-22T23:18:07.164Z","session_id":"feat/tas-44","agent":"Next.js Developer","model":"claude-opus-4-6","tier":"premium","mechanism":"sub-agent","tracker_issue":"TAS-44","outcome":"success","retries":1,"phase":2,"file_partition":["libs/server-utils/"]}
+{"type":"panel","timestamp":"2026-02-23T01:09:17.203Z","panel_key":"ui-review","verdict":"block","pass_count":1,"block_count":2,"must_fix":5,"should_fix":6,"reviewer_model":"claude-opus-4-6","weighted":true,"attempt":2,"tracker_issue":"TAS-55","artifacts_count":15,"report_path":"docs/ai-agents/panel/ui-review.md"}
+{"type":"session","timestamp":"2026-02-23T01:26:57.546Z","agent":"Sanity Expert","model":"gpt-5-mini","task":"TAS-52: Add social links","tracker_issue":"TAS-52","outcome":"partial","duration_min":13,"files_changed":3,"retries":0,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-23T02:34:46.644Z","session_id":"feat/tas-30","agent":"Sanity Expert","model":"gemini-3.1-pro","tier":"utility","mechanism":"sub-agent","tracker_issue":"TAS-30","outcome":"failed","retries":2,"phase":4,"file_partition":["apps/tastebeer.eu/app/","apps/tastecoffee.eu/app/"]}
+{"type":"session","timestamp":"2026-02-23T03:16:41.486Z","agent":"Architect","model":"gpt-5.3-codex","task":"TAS-31: Add sort options","tracker_issue":"TAS-31","outcome":"success","duration_min":31,"files_changed":8,"retries":1,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-23T06:21:11.926Z","session_id":"feat/tas-45","agent":"Performance Expert","model":"gpt-5-mini","tier":"utility","mechanism":"sub-agent","tracker_issue":"TAS-45","outcome":"success","retries":1,"phase":4,"file_partition":["libs/ui-kit/","apps/tastebeer.eu/app/"]}
+{"type":"session","timestamp":"2026-02-23T06:22:53.878Z","agent":"Sanity Expert","model":"gemini-3.1-pro","task":"TAS-47: Add price filter","tracker_issue":"TAS-47","outcome":"success","duration_min":19,"files_changed":4,"retries":1,"lessons_added":[],"discoveries":["Fix pagination"]}
+{"type":"session","timestamp":"2026-02-23T09:04:20.943Z","agent":"UI/UX Expert","model":"gpt-5-mini","task":"TAS-34: Add geolocation","tracker_issue":"TAS-34","outcome":"success","duration_min":35,"files_changed":1,"retries":0,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-23T09:50:56.855Z","session_id":"feat/tas-50","agent":"Data Expert","model":"gemini-3.1-pro","tier":"standard","mechanism":"background","tracker_issue":"TAS-50","outcome":"success","retries":1,"phase":2,"file_partition":["libs/supabase-auth/"]}
+{"type":"session","timestamp":"2026-02-23T11:28:05.523Z","agent":"Data Expert","model":"claude-opus-4-6","task":"TAS-36: Update CMS schema","tracker_issue":"TAS-36","outcome":"success","duration_min":15,"files_changed":9,"retries":1,"lessons_added":[],"discoveries":[]}
+{"type":"panel","timestamp":"2026-02-23T11:41:37.464Z","panel_key":"test-coverage","verdict":"pass","pass_count":3,"block_count":0,"must_fix":0,"should_fix":3,"reviewer_model":"gpt-5-mini","weighted":false,"attempt":1,"tracker_issue":"TAS-31","artifacts_count":18,"report_path":"docs/ai-agents/panel/test-coverage.md"}
+{"type":"session","timestamp":"2026-02-23T14:15:53.224Z","agent":"Data Expert","model":"gpt-5.3-codex","task":"TAS-31: Fix redirect loop","tracker_issue":"TAS-31","outcome":"success","duration_min":43,"files_changed":8,"retries":1,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-23T14:28:33.926Z","session_id":"feat/tas-55","agent":"UI/UX Expert","model":"gpt-5-mini","tier":"economy","mechanism":"background","tracker_issue":"TAS-55","outcome":"success","retries":1,"phase":3,"file_partition":["libs/ui-kit/","apps/tastebeer.eu/app/"]}
+{"type":"session","timestamp":"2026-02-23T16:28:00.114Z","agent":"UI/UX Expert","model":"gpt-5-mini","task":"TAS-35: Add cache headers","tracker_issue":"TAS-35","outcome":"success","duration_min":37,"files_changed":14,"retries":1,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-23T17:21:16.023Z","session_id":"feat/tas-34","agent":"Data Expert","model":"claude-opus-4-6","tier":"utility","mechanism":"sub-agent","tracker_issue":"TAS-34","outcome":"partial","retries":1,"phase":4,"file_partition":["libs/ui-kit/","apps/tastebeer.eu/app/"]}
+{"type":"session","timestamp":"2026-02-23T18:44:29.480Z","agent":"Architect","model":"gemini-3.1-pro","task":"TAS-56: Add cache headers","tracker_issue":"TAS-56","outcome":"failed","duration_min":39,"files_changed":12,"retries":2,"lessons_added":[],"discoveries":["Fix SSR hydration"]}
+{"type":"delegation","timestamp":"2026-02-23T21:23:59.785Z","session_id":"feat/tas-54","agent":"Supabase DB Expert","model":"claude-opus-4-6","tier":"standard","mechanism":"background","tracker_issue":"TAS-54","outcome":"success","retries":0,"phase":1,"file_partition":["apps/tastebeer.eu/app/"]}
+{"type":"session","timestamp":"2026-02-23T22:10:16.183Z","agent":"Performance Expert","model":"gpt-5.3-codex","task":"TAS-33: Add price filter","tracker_issue":"TAS-33","outcome":"success","duration_min":37,"files_changed":13,"retries":0,"lessons_added":[],"discoveries":[]}
+{"type":"panel","timestamp":"2026-02-23T22:16:10.866Z","panel_key":"csp-headers","verdict":"pass","pass_count":2,"block_count":1,"must_fix":0,"should_fix":3,"reviewer_model":"gemini-3.1-pro","weighted":false,"attempt":1,"tracker_issue":"TAS-40","artifacts_count":6,"report_path":"docs/ai-agents/panel/csp-headers.md"}
+{"type":"session","timestamp":"2026-02-24T00:09:22.013Z","agent":"Security Expert","model":"gpt-5.3-codex","task":"TAS-48: Update search API","tracker_issue":"TAS-48","outcome":"success","duration_min":15,"files_changed":8,"retries":1,"lessons_added":[],"discoveries":["Update CMS schema"]}
+{"type":"delegation","timestamp":"2026-02-24T01:37:32.832Z","session_id":"feat/tas-45","agent":"UI/UX Expert","model":"gemini-3.1-pro","tier":"economy","mechanism":"background","tracker_issue":"TAS-45","outcome":"success","retries":1,"phase":1,"file_partition":["libs/ui-kit/","apps/tastebeer.eu/app/"]}
+{"type":"session","timestamp":"2026-02-24T03:00:42.606Z","agent":"Testing Expert","model":"gpt-5-mini","task":"TAS-39: Fix cookie consent","tracker_issue":"TAS-39","outcome":"success","duration_min":42,"files_changed":10,"retries":0,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-24T04:36:24.219Z","session_id":"feat/tas-32","agent":"Data Expert","model":"gpt-5.3-codex","tier":"utility","mechanism":"sub-agent","tracker_issue":"TAS-32","outcome":"success","retries":1,"phase":4,"file_partition":["libs/data-pipeline/","libs/queries/"]}
+{"type":"session","timestamp":"2026-02-24T05:18:53.042Z","agent":"Next.js Developer","model":"gemini-3.1-pro","task":"TAS-37: Update contact form","tracker_issue":"TAS-37","outcome":"failed","duration_min":20,"files_changed":11,"retries":2,"lessons_added":[],"discoveries":["Add geolocation"]}
+{"type":"session","timestamp":"2026-02-24T08:11:14.714Z","agent":"Next.js Developer","model":"gemini-3.1-pro","task":"TAS-30: Add unit tests","tracker_issue":"TAS-30","outcome":"partial","duration_min":32,"files_changed":6,"retries":2,"lessons_added":["LES-009"],"discoveries":["Fix SSR hydration"]}
+{"type":"delegation","timestamp":"2026-02-24T08:15:17.039Z","session_id":"feat/tas-49","agent":"Data Expert","model":"gpt-5.3-codex","tier":"premium","mechanism":"sub-agent","tracker_issue":"TAS-49","outcome":"success","retries":1,"phase":3,"file_partition":["libs/data-pipeline/"]}
+{"type":"panel","timestamp":"2026-02-24T09:55:09.030Z","panel_key":"migration-review","verdict":"pass","pass_count":3,"block_count":0,"must_fix":0,"should_fix":5,"reviewer_model":"gemini-3.1-pro","weighted":false,"attempt":1,"tracker_issue":"TAS-53","artifacts_count":6,"report_path":"docs/ai-agents/panel/migration-review.md"}
+{"type":"session","timestamp":"2026-02-24T10:24:49.892Z","agent":"Performance Expert","model":"claude-opus-4-6","task":"TAS-33: Fix cookie consent","tracker_issue":"TAS-33","outcome":"failed","duration_min":39,"files_changed":2,"retries":2,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-24T12:28:28.251Z","session_id":"feat/tas-31","agent":"DevOps Expert","model":"claude-opus-4-6","tier":"premium","mechanism":"background","tracker_issue":"TAS-31","outcome":"partial","retries":0,"phase":4,"file_partition":["libs/ui-kit/","apps/tastebeer.eu/app/"]}
+{"type":"session","timestamp":"2026-02-24T12:54:27.158Z","agent":"Data Expert","model":"claude-opus-4-6","task":"TAS-35: Add filter component","tracker_issue":"TAS-35","outcome":"success","duration_min":13,"files_changed":7,"retries":1,"lessons_added":[],"discoveries":[]}
+{"type":"session","timestamp":"2026-02-24T15:47:57.543Z","agent":"Performance Expert","model":"gpt-5.3-codex","task":"TAS-59: Fix CSP violations","tracker_issue":"TAS-59","outcome":"success","duration_min":25,"files_changed":7,"retries":1,"lessons_added":[],"discoveries":["Add venue suggestions"]}
+{"type":"delegation","timestamp":"2026-02-24T16:03:58.674Z","session_id":"feat/tas-51","agent":"Data Expert","model":"gpt-5-mini","tier":"standard","mechanism":"sub-agent","tracker_issue":"TAS-51","outcome":"success","retries":0,"phase":2,"file_partition":["libs/queries/"]}
+{"type":"session","timestamp":"2026-02-24T18:21:34.626Z","agent":"Testing Expert","model":"claude-opus-4-6","task":"TAS-47: Add image optimization","tracker_issue":"TAS-47","outcome":"success","duration_min":45,"files_changed":1,"retries":1,"lessons_added":["LES-005"],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-24T19:36:47.295Z","session_id":"feat/tas-45","agent":"Security Expert","model":"gpt-5.3-codex","tier":"premium","mechanism":"sub-agent","tracker_issue":"TAS-45","outcome":"success","retries":0,"phase":1,"file_partition":["apps/tastecoffee.eu/app/"]}
+{"type":"panel","timestamp":"2026-02-24T20:15:45.425Z","panel_key":"query-optimization","verdict":"block","pass_count":0,"block_count":3,"must_fix":5,"should_fix":5,"reviewer_model":"gpt-5-mini","weighted":false,"attempt":3,"tracker_issue":"TAS-42","artifacts_count":15,"report_path":"docs/ai-agents/panel/query-optimization.md"}
+{"type":"session","timestamp":"2026-02-24T20:46:38.816Z","agent":"DevOps Expert","model":"gemini-3.1-pro","task":"TAS-36: Add geolocation","tracker_issue":"TAS-36","outcome":"success","duration_min":22,"files_changed":9,"retries":0,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-24T23:22:20.331Z","session_id":"feat/tas-54","agent":"Documentation Writer","model":"gpt-5-mini","tier":"utility","mechanism":"sub-agent","tracker_issue":"TAS-54","outcome":"success","retries":0,"phase":1,"file_partition":["apps/tastebeer.eu/app/","apps/tastecoffee.eu/app/"]}
+{"type":"session","timestamp":"2026-02-24T23:50:07.144Z","agent":"Next.js Developer","model":"claude-opus-4-6","task":"TAS-32: Add price filter","tracker_issue":"TAS-32","outcome":"success","duration_min":15,"files_changed":11,"retries":1,"lessons_added":[],"discoveries":[]}
+{"type":"session","timestamp":"2026-02-25T02:48:10.908Z","agent":"Sanity Expert","model":"claude-opus-4-6","task":"TAS-32: Add cache headers","tracker_issue":"TAS-32","outcome":"failed","duration_min":38,"files_changed":8,"retries":1,"lessons_added":["LES-008"],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-25T03:04:08.793Z","session_id":"feat/tas-42","agent":"Next.js Developer","model":"gpt-5-mini","tier":"premium","mechanism":"sub-agent","tracker_issue":"TAS-42","outcome":"success","retries":1,"phase":4,"file_partition":["apps/cms-studio/"]}
+{"type":"session","timestamp":"2026-02-25T05:22:40.043Z","agent":"Next.js Developer","model":"gemini-3.1-pro","task":"TAS-31: Update contact form","tracker_issue":"TAS-31","outcome":"success","duration_min":8,"files_changed":7,"retries":0,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-25T06:35:46.724Z","session_id":"feat/tas-38","agent":"DevOps Expert","model":"gpt-5.3-codex","tier":"utility","mechanism":"sub-agent","tracker_issue":"TAS-38","outcome":"success","retries":1,"phase":4,"file_partition":["libs/server-utils/"]}
+{"type":"panel","timestamp":"2026-02-25T07:07:18.806Z","panel_key":"deployment-checklist","verdict":"pass","pass_count":3,"block_count":0,"must_fix":0,"should_fix":8,"reviewer_model":"gemini-3.1-pro","weighted":true,"attempt":1,"tracker_issue":"TAS-33","artifacts_count":6,"report_path":"docs/ai-agents/panel/deployment-checklist.md"}
+{"type":"session","timestamp":"2026-02-25T07:56:19.927Z","agent":"Architect","model":"claude-opus-4-6","task":"TAS-57: Fix cookie consent","tracker_issue":"TAS-57","outcome":"success","duration_min":22,"files_changed":9,"retries":0,"lessons_added":[],"discoveries":[]}
+{"type":"panel","timestamp":"2026-02-25T10:00:00Z","panel_key":"instruction-refactoring","verdict":"pass","pass_count":3,"block_count":0,"must_fix":0,"should_fix":5,"reviewer_model":"claude-opus-4-6","weighted":false,"attempt":1,"artifacts_count":14,"report_path":"docs/ai-agents/panel/instruction-refactoring.md"}
+{"type":"session","timestamp":"2026-02-25T10:34:21.652Z","agent":"UI/UX Expert","model":"claude-opus-4-6","task":"TAS-33: Update search API","tracker_issue":"TAS-33","outcome":"failed","duration_min":41,"files_changed":11,"retries":1,"lessons_added":[],"discoveries":[]}
+{"type":"delegation","timestamp":"2026-02-25T10:39:46.727Z","session_id":"feat/tas-38","agent":"Sanity Expert","model":"gemini-3.1-pro","tier":"standard","mechanism":"sub-agent","tracker_issue":"TAS-38","outcome":"success","retries":0,"phase":3,"file_partition":["libs/ui-kit/"]}
+{"type":"session","timestamp":"2026-02-25T13:00:16.014Z","agent":"DevOps Expert","model":"gpt-5-mini","task":"TAS-44: Add geolocation","tracker_issue":"TAS-44","outcome":"failed","duration_min":12,"files_changed":12,"retries":3,"lessons_added":[],"discoveries":["Update venue detail"]}
+{"type":"delegation","timestamp":"2026-02-25T14:30:07.967Z","session_id":"feat/tas-46","agent":"Sanity Expert","model":"gemini-3.1-pro","tier":"utility","mechanism":"sub-agent","tracker_issue":"TAS-46","outcome":"success","retries":1,"phase":4,"file_partition":["apps/tastebeer.eu/app/","apps/tastecoffee.eu/app/"]}
+{"type":"session","timestamp":"2026-02-25T15:48:46.235Z","agent":"UI/UX Expert","model":"claude-opus-4-6","task":"TAS-38: Optimize bundle size","tracker_issue":"TAS-38","outcome":"failed","duration_min":5,"files_changed":12,"retries":3,"lessons_added":[],"discoveries":[]}
+{"type":"review","timestamp":"2026-02-28T10:30:00Z","tracker_issue":"TAS-12","agent":"Developer","reviewer_model":"gpt-5-mini","verdict":"pass","attempt":1,"issues_critical":0,"issues_major":0,"issues_minor":1,"confidence":"high","escalated":false,"duration_sec":38}
+{"type":"review","timestamp":"2026-02-28T14:15:00Z","tracker_issue":"TAS-14","agent":"UI-UX Expert","reviewer_model":"gpt-5-mini","verdict":"pass","attempt":1,"issues_critical":0,"issues_major":1,"issues_minor":2,"confidence":"medium","escalated":false,"duration_sec":52}
+{"type":"review","timestamp":"2026-03-01T09:00:00Z","tracker_issue":"TAS-18","agent":"Developer","reviewer_model":"gpt-5-mini","verdict":"fail","attempt":1,"issues_critical":1,"issues_major":0,"issues_minor":0,"confidence":"high","escalated":true,"duration_sec":41}
+{"type":"review","timestamp":"2026-03-01T09:20:00Z","tracker_issue":"TAS-18","agent":"Developer","reviewer_model":"gpt-5-mini","verdict":"pass","attempt":2,"issues_critical":0,"issues_major":0,"issues_minor":1,"confidence":"high","escalated":false,"duration_sec":35}
+{"type":"review","timestamp":"2026-03-01T11:45:00Z","tracker_issue":"TAS-20","agent":"Database Engineer","reviewer_model":"gpt-5-mini","verdict":"pass","attempt":1,"issues_critical":0,"issues_major":0,"issues_minor":0,"confidence":"high","escalated":false,"duration_sec":28}
+{"type":"review","timestamp":"2026-03-01T16:30:00Z","tracker_issue":"TAS-22","agent":"Security Expert","reviewer_model":"claude-opus-4-6","verdict":"fail","attempt":1,"issues_critical":2,"issues_major":1,"issues_minor":0,"confidence":"high","escalated":true,"duration_sec":65}

package/src/dashboard/src/pages/index.astro

@@ -1285,29 +1285,28 @@ const base = import.meta.env.BASE_URL;
   // ── Export ─────────────────────────────────────────────────
 
   function exportData() {
-    const data = {
-      exported_at: new Date().toISOString(),
-      sessions: rawSessions,
-      delegations: rawDelegations,
-      panels: rawPanels,
-      reviews: rawReviews,
-    };
-    const blob = new Blob([JSON.stringify(data, null, 2)], { type: 'application/json' });
+    const events = [
+      ...rawSessions,
+      ...rawDelegations,
+      ...rawPanels,
+      ...rawReviews,
+    ].sort((a, b) => a.timestamp.localeCompare(b.timestamp));
+    const blob = new Blob([events.map((e) => JSON.stringify(e)).join('\n') + '\n'], { type: 'application/x-ndjson' });
     const url = URL.createObjectURL(blob);
     const a = document.createElement('a');
     a.href = url;
-    a.download = 'opencastle-dashboard-' + new Date().toISOString().slice(0, 10) + '.json';
+    a.download = 'opencastle-events-' + new Date().toISOString().slice(0, 10) + '.ndjson';
     a.click();
     URL.revokeObjectURL(url);
   }
 
   async function main() {
-    const [sessions, delegations, panels, reviews] = await Promise.all([
-      loadNdjson(base + 'data/sessions.ndjson'),
-      loadNdjson(base + 'data/delegations.ndjson'),
-      loadNdjson(base + 'data/panels.ndjson'),
-      loadNdjson(base + 'data/reviews.ndjson'),
-    ]);
+    const events = await loadNdjson(base + 'data/events.ndjson');
+
+    const sessions = events.filter((e) => e.type === 'session');
+    const delegations = events.filter((e) => e.type === 'delegation');
+    const panels = events.filter((e) => e.type === 'panel');
+    const reviews = events.filter((e) => e.type === 'review');
 
     rawSessions = sessions;
     rawDelegations = delegations;

package/src/orchestrator/agents/api-designer.agent.md

@@ -58,4 +58,4 @@ When completing a task, return a structured summary:
 4. **Verification** — Lint, type-check, and test results
 5. **Documentation** — API docs produced or updated
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/architect.agent.md

@@ -121,4 +121,4 @@ When completing a review, return a structured summary:
 4. **Alternatives** — Other approaches considered and why they were rejected or preferred
 5. **Action Items** — Specific changes recommended before proceeding
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/content-engineer.agent.md

@@ -53,4 +53,4 @@ When completing a task, return a structured summary:
 3. **Verification** — Schema deploy result, query test results
 4. **Migration Notes** — Any data migration needed for existing content
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/copywriter.agent.md

@@ -87,4 +87,4 @@ When completing a task, return a structured summary:
 3. **Constraints Met** — Character limits, tone requirements, accessibility considerations
 4. **Context** — Where the copy appears and how it fits the user journey
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/data-expert.agent.md

@@ -59,4 +59,4 @@ When completing a task, return a structured summary:
 3. **Files Created** — Output files with row counts and format
 4. **Import Results** — Records imported, skipped, or failed (with reasons)
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/database-engineer.agent.md

@@ -57,4 +57,4 @@ When completing a task, return a structured summary:
 4. **Rollback Plan** — How to reverse the migration if needed
 5. **Data Impact** — Rows affected, any data transformations applied
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/developer.agent.md

@@ -56,4 +56,4 @@ When completing a task, return a structured summary:
 3. **Acceptance Criteria Status** — Checklist from the tracker issue, each item marked ✅ or ❌
 4. **Assumptions Made** — Decisions you made that weren't explicitly specified
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/devops-expert.agent.md

@@ -53,4 +53,4 @@ When completing a task, return a structured summary:
 4. **Rollback Plan** — How to revert if the deployment causes issues
 5. **Monitoring** — What to watch after deployment
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/documentation-writer.agent.md

@@ -57,4 +57,4 @@ When completing a task, return a structured summary:
 3. **Cross-References** — Links updated or added to maintain doc consistency
 4. **Verification** — Markdown lint results, broken link check
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/performance-expert.agent.md

@@ -54,4 +54,4 @@ When completing a task, return a structured summary:
 4. **Trade-offs** — Any DX or functionality trade-offs introduced
 5. **Further Opportunities** — Additional optimizations identified but not implemented
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/release-manager.agent.md

@@ -62,4 +62,4 @@ When completing a task, return a structured summary:
 5. **Deployment Status** — Production deployment health check results
 6. **Rollback Plan** — Steps to revert if issues arise post-release
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/security-expert.agent.md

@@ -59,4 +59,4 @@ When completing a task, return a structured summary:
 4. **Residual Risk** — Known risks that remain after the fix
 5. **Recommendations** — Follow-up security improvements to consider
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/seo-specialist.agent.md

@@ -58,4 +58,4 @@ When completing a task, return a structured summary:
 4. **Verification** — Lighthouse SEO score, Rich Results Test, crawlability check
 5. **Recommendations** — Further SEO opportunities identified but not implemented
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/session-guard.agent.md

@@ -30,27 +30,21 @@ Run ALL checks. Report each as ✅ or ❌.
 
 ### 1. Delegation Records
 
-For each delegation in the session summary, verify a matching record exists in `.github/customizations/logs/delegations.ndjson`.
+For each delegation in the session summary, verify a matching record exists in `.github/customizations/logs/events.ndjson` (type=delegation).
 
-**How:** `tail -20 .github/customizations/logs/delegations.ndjson` and match agent + task against the summary.
+**How:** `grep '"type":"delegation"' .github/customizations/logs/events.ndjson | tail -20` and match agent + task against the summary.
 
-**Fix command template:**
-```bash
-(Fill in values from the session summary — see the Team Lead agent file for the canonical JSON schema)
-```
+**Fix:** Load the **observability-logging** skill and run the delegation record command (includes a verify step).
 
 Also verify each delegation record includes `session_id` (branch name). Records missing `session_id` should be flagged.
 
 ### 2. Session Record
 
-Verify a session record exists in `.github/customizations/logs/sessions.ndjson` for the current task.
+Verify a session record exists in `.github/customizations/logs/events.ndjson` (type=session) for the current task.
 
-**How:** `tail -5 .github/customizations/logs/sessions.ndjson` and match task description.
+**How:** `grep '"type":"session"' .github/customizations/logs/events.ndjson | tail -5` and match task description.
 
-**Fix command template:**
-```bash
-echo '{"timestamp":"<ISO>","agent":"Team Lead","model":"<model>","task":"<description>","outcome":"success","duration_min":<N>,"files_changed":<N>,"retries":0,"lessons_added":[],"discoveries":[]}' >> .github/customizations/logs/sessions.ndjson
-```
+**Fix:** Load the **observability-logging** skill and run the session record command (includes a verify step).
 
 ### 3. Lessons Captured
 
@@ -66,17 +60,11 @@ If the session summary lists discovered issues, verify they appear in:
 
 ### 5. Review & Panel Records
 
-If the session summary mentions fast reviews or panel reviews, verify matching records exist in `.github/customizations/logs/reviews.ndjson` and/or `.github/customizations/logs/panels.ndjson`.
+If the session summary mentions fast reviews or panel reviews, verify matching records exist in `.github/customizations/logs/events.ndjson` (type=review and/or type=panel).
 
-**How:** `tail -10 .github/customizations/logs/reviews.ndjson` and/or `tail -5 .github/customizations/logs/panels.ndjson`.
+**How:** `grep '"type":"review"' .github/customizations/logs/events.ndjson | tail -10` and/or `grep '"type":"panel"' .github/customizations/logs/events.ndjson | tail -5`.
 
-**Fix command templates:**
-```bash
-# Fast review
-echo '{"timestamp":"<ISO>","agent":"<reviewed-agent>","reviewer_model":"<model>","verdict":"<pass|fail>","attempt":1,"issues_critical":0,"issues_major":0,"issues_minor":0,"confidence":"high","escalated":false,"duration_sec":N}' >> .github/customizations/logs/reviews.ndjson
-# Panel review
-echo '{"timestamp":"<ISO>","panel_key":"<key>","verdict":"<pass|block>","pass_count":N,"block_count":N,"must_fix":0,"should_fix":0,"reviewer_model":"<model>","weighted":false,"attempt":1,"artifacts_count":N}' >> .github/customizations/logs/panels.ndjson
-```
+**Fix:** Load the **observability-logging** skill and run the review/panel record command as applicable (includes a verify step).
 
 ### 6. Uncommitted Changes
 

package/src/orchestrator/agents/team-lead.agent.md

@@ -99,11 +99,7 @@ Synchronous — blocks until result. Use when:
 
 When calling `runSubagent`, always specify which custom agent to use by name: *"Use the **[Agent Name]** agent to [task]."* This routes the sub-agent to the named agent's model and tools instead of inheriting the Team Lead's Premium model. Include objective, file paths, acceptance criteria, and what to return in the result.
 
-**After each sub-agent returns**, log the delegation record before doing anything else (before review, before verification):
-```bash
-echo '{"timestamp":"<ISO-NOW>","session_id":"<branch>","agent":"<name>","model":"<model>","tier":"<tier>","mechanism":"sub-agent","tracker_issue":"<issue-or-N/A>","outcome":"<success|partial|failed>","retries":0,"phase":<N>,"file_partition":["<paths>"]}' >> .github/customizations/logs/delegations.ndjson
-```
-Verify: `tail -1 .github/customizations/logs/delegations.ndjson`
+**After each sub-agent returns**, log the delegation record before doing anything else (before review, before verification). This is a **⛔ hard gate** — do NOT proceed to review or any other action until the delegation is logged. Use the **observability-logging** skill's delegation record command (`--mechanism sub-agent`).
 
 > **`model` and `tier` must come from the agent registry** — not the Team Lead's own model. Look up the agent in [agent-registry.md](../customizations/agents/agent-registry.md) and use their assigned model and tier. For example, delegating to Developer → `"model":"claude-sonnet-4-6","tier":"quality"`, not the Team Lead's `claude-opus-4-6`.
 
@@ -117,11 +113,7 @@ Async in isolated Git worktree. Use when:
 
 Spawn via: Delegate Session → Background → Select agent → Enter prompt with full self-contained context (they cannot ask follow-ups).
 
-**After spawning**, log the delegation record before spawning another agent or doing any other work:
-```bash
-echo '{"timestamp":"<ISO-NOW>","session_id":"<branch>","agent":"<name>","model":"<model>","tier":"<tier>","mechanism":"background","tracker_issue":"<issue-or-N/A>","outcome":"pending","retries":0,"phase":<N>,"file_partition":["<paths>"]}' >> .github/customizations/logs/delegations.ndjson
-```
-Verify: `tail -1 .github/customizations/logs/delegations.ndjson`
+**After spawning**, log the delegation record before spawning another agent or doing any other work. This is a **⛔ hard gate** — do NOT spawn another agent or proceed until the delegation is logged. Use the **observability-logging** skill's delegation record command (`--mechanism background`, `--outcome pending`).
 
 > **`model` and `tier` must come from the agent registry** — see note in Sub-Agents section above.
 
@@ -133,20 +125,11 @@ Parallel agents must never touch the same files. Map file/directory ownership be
 
 ### Budget
 
-| Tier | Model | Est. Tokens | Est. Duration |
-|------|-------|-------------|---------------|
-| **Economy** | GPT-5 mini | ~5K–15K | 2–5 min |
-| **Fast** | GPT-5.3-Codex | ~10K–40K | 5–15 min |
-| **Standard** | Gemini 3.1 Pro | ~15K–50K | 8–20 min |
-| **Quality** | Claude Sonnet 4.6 | ~30K–80K | 10–25 min |
-| **Premium** | Claude Opus 4.6 | ~50K–150K | 15–30 min |
-
-**Quick reference:** Premium for orchestration, Quality for coding/UI/security/architecture, Standard for analysis/schemas/cost-sensitive, Fast for tests/data/terminal, Economy for docs.
+See the **team-lead-reference** skill for model tiers, token estimates, duration estimates, and budget rules.
 
 - Target 5–7 delegations per session. At 8 → warn. At 9 → checkpoint. At 10+ → STOP and save state.
 - Max 3 delegation attempts per task. After 3 failures → Dead Letter Queue + Architect.
 - Max 3 panel attempts. After 3 BLOCKs → dispute record.
-- Full model routing details in **team-lead-reference** skill.
 
 ### Pre-Delegation Checks
 
@@ -191,7 +174,7 @@ Every delegation prompt must include:
 - **File paths** — exact files to read/modify (the agent's partition)
 - **Acceptance criteria** — from the tracker issue
 - **Patterns** — link to existing code examples
-- **Reminder:** *"Read `LESSONS-LEARNED.md` before starting. Add lessons for any retries. Follow the Discovered Issues Policy."*
+- **Reminder:** *"Read `LESSONS-LEARNED.md` before starting. Use the **self-improvement** skill for any lessons. Follow the Discovered Issues Policy."*
 
 For complex tasks (score 5+), load the **decomposition** skill for the Delegation Spec Template.
 
@@ -205,7 +188,7 @@ For complex tasks (score 5+), load the **decomposition** skill for the Delegatio
 For each task:
   1. Move issue → In Progress
   2. Delegate to specialist agent by name (e.g., "Use the Developer agent to...")
-  3. Log delegation to delegations.ndjson (immediately — verify with `tail -1`)
+  3. Log delegation (⛔ hard gate — do NOT proceed until logged. See the **observability-logging** skill for the command and verify step.)
   4. Monitor for drift (load orchestration-protocols skill)
   5. Verify output:
      - Changed files within partition
@@ -216,7 +199,7 @@ For each task:
      - High-stakes: panel review (load panel-majority-vote skill)
      - Discovered issues tracked (not silently ignored)
      - Lessons captured (if agent retried anything)
-  6. PASS → log review, move issue → Done
+  6. PASS → log review (⛔ hard gate — do NOT proceed until logged), move issue → Done
      FAIL → re-delegate with failure details (max 3 attempts)
 ```
 
@@ -248,16 +231,7 @@ See [shared-delivery-phase.md](../agent-workflows/shared-delivery-phase.md) for
 
 ## Observability
 
-> **⛔ HARD GATE — ALL observability logging is mandatory.** No record type is optional.
-> The Session Guard will flag missing records, but do not rely on it — log inline as you go.
-
-| Record | File | When to log | Timing |
-|--------|------|-------------|--------|
-| **Session** | `sessions.ndjson` | Every session — always | Before yielding to user |
-| **Delegation** | `delegations.ndjson` | After each `runSubagent` / background spawn | **Inline** — immediately after each delegation, before review |
-| **Fast review** | `reviews.ndjson` | After each fast review | After review completes |
-| **Panel** | `panels.ndjson` | After each panel majority vote | After panel completes |
-| **Dispute** | `disputes.ndjson` | After each dispute is created | When dispute is filed |
+> **⛔ HARD GATE — ALL observability logging is mandatory.** Load the **observability-logging** skill for record schemas, logging commands, and the pre-response quality gate.
 
 **Self-check before calling Session Guard:** Count delegations, reviews, and panels performed → count records written → numbers must match for each type. If any count is off, fix it before calling the guard.
 
@@ -273,7 +247,7 @@ See [shared-delivery-phase.md](../agent-workflows/shared-delivery-phase.md) for
 8. Never proceed to dependent task until prerequisite is verified
 9. Sub-agents must not spawn other sub-agents (no recursive delegation)
 10. Never push to `main` — feature branch → PR → human merges
-11. Log every delegation inline — immediately after each `runSubagent` or background spawn, not at session end
+11. Log every delegation and review inline — immediately after each `runSubagent` or background spawn, and after each fast review/panel. This is a hard gate — never proceed without logging first
 12. Steer early — don't wait until an agent finishes to redirect when you spot drift
 13. Never exceed session budget without checkpointing — context degrades after 8+ delegations
 14. Read `LESSONS-LEARNED.md` before delegating — include relevant lessons in prompts

package/src/orchestrator/agents/testing-expert.agent.md

@@ -76,4 +76,4 @@ When completing a task, return a structured summary:
 4. **Edge Cases Tested** — List edge cases covered and any known gaps
 5. **Regressions Checked** — Adjacent features/pages verified to still work
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/ui-ux-expert.agent.md

@@ -56,4 +56,4 @@ When completing a task, return a structured summary:
 3. **Responsive** — Breakpoints tested (per project testing config)
 4. **Visual Evidence** — Screenshots at each breakpoint
 
-See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).
+See **Base Output Contract** in the **observability-logging** skill for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/customizations/AGENT-PERFORMANCE.md

@@ -6,45 +6,44 @@ Tracks agent success rates across panel reviews and delegated tasks to inform mo
 ## Data Sources
 
 Performance data is collected automatically via NDJSON session logs:
-- **Session data:** `.github/customizations/logs/sessions.ndjson` — appended by every agent after each session
-- **Delegation data:** `.github/customizations/logs/delegations.ndjson` — appended by the Team Lead after each delegation
+- **All events:** `.github/customizations/logs/events.ndjson` — unified log for all event types (sessions, delegations, reviews, panels, disputes), appended via `opencastle log`
 - **Dashboard:** Run `npx opencastle dashboard` to visualize agent performance
 
 ## Quick Queries
 
 ```bash
 # Sessions per agent
-jq -r '.agent' .github/customizations/logs/sessions.ndjson | sort | uniq -c | sort -rn
+jq -r 'select(.type == "session") | .agent' .github/customizations/logs/events.ndjson | sort | uniq -c | sort -rn
 
 # Success rate by agent
-jq -r '[.agent, .outcome] | @tsv' .github/customizations/logs/sessions.ndjson | sort | uniq -c
+jq -r 'select(.type == "session") | [.agent, .outcome] | @tsv' .github/customizations/logs/events.ndjson | sort | uniq -c
 
 # Delegation tier distribution
-jq -r '.tier' .github/customizations/logs/delegations.ndjson | sort | uniq -c
+jq -r 'select(.type == "delegation") | .tier' .github/customizations/logs/events.ndjson | sort | uniq -c
 
 # Failed delegations
-jq 'select(.outcome == "failed")' .github/customizations/logs/delegations.ndjson
+jq 'select(.type == "delegation" and .outcome == "failed")' .github/customizations/logs/events.ndjson
 ```
 
 ## Panel Review Performance
 
-Panel review data is collected automatically via `.github/customizations/logs/panels.ndjson` (appended by the panel runner after each review — see step 7 in the panel majority vote skill).
+Panel review data is collected automatically in `.github/customizations/logs/events.ndjson` with `type: "panel"` (appended by the panel runner after each review — see step 7 in the panel majority vote skill).
 
 ```bash
 # Total panel reviews
-wc -l .github/customizations/logs/panels.ndjson
+jq 'select(.type == "panel")' .github/customizations/logs/events.ndjson | wc -l
 
 # Pass vs block rate
-jq -r '.verdict' .github/customizations/logs/panels.ndjson | sort | uniq -c
+jq -r 'select(.type == "panel") | .verdict' .github/customizations/logs/events.ndjson | sort | uniq -c
 
 # Reviews by panel key
-jq -r '.panel_key' .github/customizations/logs/panels.ndjson | sort | uniq -c | sort -rn
+jq -r 'select(.type == "panel") | .panel_key' .github/customizations/logs/events.ndjson | sort | uniq -c | sort -rn
 
 # Reviews that required retries (attempt > 1)
-jq 'select(.attempt > 1)' .github/customizations/logs/panels.ndjson
+jq 'select(.type == "panel" and .attempt > 1)' .github/customizations/logs/events.ndjson
 
 # Average SHOULD-FIX items per review
-jq -s 'if length > 0 then (map(.should_fix) | add) / length else 0 end' .github/customizations/logs/panels.ndjson
+jq -s '[.[] | select(.type == "panel")] | if length > 0 then (map(.should_fix) | add) / length else 0 end' .github/customizations/logs/events.ndjson
 ```
 
 ## Usage

package/src/orchestrator/customizations/DISPUTES.md

@@ -86,7 +86,7 @@ Which option the Team Lead recommends and why. Include specific next steps:
 
 Links to evidence for human review:
 - Panel report: `.github/customizations/logs/panel/[panel-key].md`
-- Review log entries: `.github/customizations/logs/reviews.ndjson` (filter by issue)
+- Review log entries: `.github/customizations/logs/events.ndjson` (filter by `type: "review"` and issue)
 - Changed files: [list of files in the last attempt]
 - DLQ entry (if any): `DLQ-XXX`
 ```
@@ -112,7 +112,7 @@ Links to evidence for human review:
 ┌──────────────────────────────────────┐
 │  Team Lead creates dispute record     │
 │  Status: pending                      │
-│  Logs to disputes.ndjson              │
+│  Logs to events.ndjson                │
 │  Links to tracker issue               │
 └──────────────┬───────────────────────┘
                │