docs(observability): capture gateway-origin phase0 live baseline window

This commit is contained in:
William Valentin
2026-02-26 23:50:28 -08:00
parent 4b07a1f166
commit 5a34e986bf
10 changed files with 200 additions and 12 deletions
+30 -6
View File
@@ -67,7 +67,7 @@
"status": "completed",
"date": "2026-02-25",
"updated": "2026-02-27",
"summary": "Updated protocol/docs/diagrams for phase-0 telemetry fields, documented baseline workflow, and replaced the original probe-only baseline workflow with anonymized live channel-session audit artifacts (`phase0_baseline_live_2026-02-27.*`).",
"summary": "Updated protocol/docs/diagrams for phase-0 telemetry fields, documented baseline workflow, replaced the original probe-only baseline workflow with anonymized live channel-session audit artifacts (`phase0_baseline_live_2026-02-27.*`), and added a second gateway-origin live window artifact set (`phase0_baseline_live_gateway_2026-02-27.*`) including cancel-path telemetry.",
"files_modified": [
"README.md",
"docs/api/PROTOCOL.md",
@@ -77,15 +77,18 @@
"docs/plans/artifacts/phase0_baseline_live_2026-02-27.jsonl",
"docs/plans/artifacts/phase0_baseline_live_2026-02-27.md",
"docs/plans/artifacts/phase0_baseline_live_2026-02-27.json",
"docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.jsonl",
"docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.md",
"docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.json",
"docs/plans/state.json"
],
"test_status": "pnpm audit:phase0-baseline:live + pnpm test:run src/audit/phase0LiveBaseline.test.ts src/audit/phase0BaselineSummary.test.ts + pnpm typecheck passing"
"test_status": "pnpm audit:phase0-baseline:live + node --import tsx/esm scripts/capture-phase0-live-baseline.ts --audit ~/.local/share/flynn/audit.log --source gateway --since 1772178440693 --until 1772178442694 --sample-out docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.jsonl --summary-json-out docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.json --summary-md-out docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.md + pnpm test:run src/audit/phase0LiveBaseline.test.ts src/audit/phase0BaselineSummary.test.ts + pnpm typecheck passing"
},
"phase0-live-baseline-capture-tooling": {
"status": "completed",
"date": "2026-02-27",
"updated": "2026-02-27",
"summary": "Added a dedicated live phase-0 baseline capture flow that reads audit logs, filters run/reaction telemetry, excludes probe sessions, anonymizes session/sender/request IDs, and writes sample + summary artifacts for operational refreshes.",
"summary": "Added a dedicated live phase-0 baseline capture flow that reads audit logs, filters run/reaction telemetry, excludes probe sessions, anonymizes session/sender/request IDs, and writes sample + summary artifacts for operational refreshes across both channel-origin and gateway-origin windows.",
"files_modified": [
"src/audit/phase0LiveBaseline.ts",
"src/audit/phase0LiveBaseline.test.ts",
@@ -99,9 +102,30 @@
"docs/plans/artifacts/phase0_baseline_live_2026-02-27.jsonl",
"docs/plans/artifacts/phase0_baseline_live_2026-02-27.md",
"docs/plans/artifacts/phase0_baseline_live_2026-02-27.json",
"docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.jsonl",
"docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.md",
"docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.json",
"docs/plans/state.json"
],
"test_status": "pnpm audit:phase0-baseline:live + pnpm test:run src/audit/phase0LiveBaseline.test.ts src/audit/phase0BaselineSummary.test.ts + pnpm typecheck passing"
"test_status": "pnpm audit:phase0-baseline:live + node --import tsx/esm scripts/capture-phase0-live-baseline.ts --audit ~/.local/share/flynn/audit.log --source gateway --since 1772178440693 --until 1772178442694 --sample-out docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.jsonl --summary-json-out docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.json --summary-md-out docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.md + pnpm test:run src/audit/phase0LiveBaseline.test.ts src/audit/phase0BaselineSummary.test.ts + pnpm typecheck passing"
},
"phase0-live-baseline-gateway-window": {
"status": "completed",
"date": "2026-02-27",
"updated": "2026-02-27",
"summary": "Captured and committed a gateway-origin live phase-0 baseline window with explicit cancel-path coverage (`run.cancel`, `run.state.cancel_requested`, `run.state.cancelled`) plus a paired completion sample, producing anonymized `phase0_baseline_live_gateway_2026-02-27.*` artifacts.",
"files_modified": [
"README.md",
"docs/api/PROTOCOL.md",
"docs/architecture/AGENT_DIAGRAM.md",
"docs/architecture/GATEWAY_SESSIONS_AND_QUEUE.md",
"docs/plans/2026-02-25-phase0-instrumentation-ticket-checklist.md",
"docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.jsonl",
"docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.md",
"docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.json",
"docs/plans/state.json"
],
"test_status": "node --import tsx/esm scripts/capture-phase0-live-baseline.ts --audit ~/.local/share/flynn/audit.log --source gateway --since 1772178440693 --until 1772178442694 --sample-out docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.jsonl --summary-json-out docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.json --summary-md-out docs/plans/artifacts/phase0_baseline_live_gateway_2026-02-27.md + pnpm test:run src/audit/phase0LiveBaseline.test.ts src/audit/phase0BaselineSummary.test.ts + pnpm typecheck passing"
},
"phase0-instrumentation-ticket-checklist": {
"status": "completed",
@@ -7288,8 +7312,8 @@
"deeper_surfaces_phase0_ticket_02": "completed — gateway + daemon routing emit run lifecycle/cancel telemetry and reaction match/skip audit events with filter summaries and cancellation latency, plus focused tests",
"deeper_surfaces_phase0_ticket_03": "completed — gateway metrics now track run-state outcomes, cancel latency samples, and reaction decision counters with routing/gateway emitters",
"deeper_surfaces_phase0_ticket_04": "completed — added phase-0 baseline summary tooling for run outcomes, cancel latency, and reaction decisions with markdown/json CLI output",
"deeper_surfaces_phase0_ticket_05": "completed — documented phase-0 telemetry fields/workflow, refreshed architecture/protocol docs, and generated anonymized live baseline artifacts from real channel audit traffic (probe-only artifact workflow superseded)",
"next_up": "Capture a gateway-origin live phase-0 baseline sample (including run.cancel/cancelled paths) and append as a second live artifact window alongside the channel sample",
"deeper_surfaces_phase0_ticket_05": "completed — documented phase-0 telemetry fields/workflow, refreshed architecture/protocol docs, and generated anonymized live baseline artifacts for both channel-origin and gateway-origin traffic (including cancel-path coverage)",
"next_up": "Phase-0 baseline windows now cover channel and gateway sources; keep both artifact windows refreshed on cadence before additional run-control/reaction semantic changes.",
"pi_embedded_canary_spike": "completed — added optional pi_embedded backend adapter, canary-safe no-tools routing guard, backend success/fallback latency audit events, and docs/diagram updates while native remains default",
"pi_embedded_evaluation_phase": "completed — final decision rollback (applied in runtime config): Window A failed latency/fallback gates (p50 +259ms, p95 +5695ms, fallback 25%, categories: pi_module_interface/empty_assistant_text); Window B remained sample-insufficient; controlled probes verified guard coverage (pi_no_tools_mode/capability_query/attachments_present each hit once)",
"pi_embedded_manual_mode": "completed — added persisted runtime backend controls for manual Pi activation/deactivation (`/runtime` preferred, `/backend` alias; `status`, `activate pi`, `deactivate pi`, `use config`) while keeping config-driven default routing",