will/flynn

Files

T

William Valentin ed53d6d215 docs(memory): revise pi personal assistant memory plan after code review

Key changes from review:
- Use separate _sessionContext field instead of mutating _systemPromptBase
- Parameterize compaction prompt via buildCompactionPrompt() instead of duplicating
- Fix flaky TTL=0 test to use hardcoded past expiry date
- Route memory extraction to {userNamespace}/facts when namespace is set
- Document future considerations (config refactor, concurrent writes, token counting)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-25 12:50:24 -08:00

api

test(voice): cover tts fallback

2026-02-25 11:21:49 -08:00

architecture

test(voice): cover tts fallback

2026-02-25 11:21:49 -08:00

councils

feat(councils): add scaffold prompt hooks and checked-in scaffold files

2026-02-21 11:01:12 -08:00

deployment

refactor(config): generate paas profile from default overlay

2026-02-23 17:11:02 -08:00

operations

docs(audit): add report, google auth runbook, and agent repo map

2026-02-23 17:12:41 -08:00

performance

docs: add proactive context usage and compaction guidance

2026-02-16 15:44:13 -08:00

plans

docs(memory): revise pi personal assistant memory plan after code review

2026-02-25 12:50:24 -08:00

runbooks

Fix whisper compose entrypoint so STT port 18801 is reachable

2026-02-22 20:40:42 -08:00

security

refactor(security): unify elevated mode handling across surfaces

2026-02-19 11:41:53 -08:00

README.md

docs(audit): add report, google auth runbook, and agent repo map

2026-02-23 17:12:41 -08:00

README.md

Flynn Documentation (Start Here)

This documentation is written to be useful to both humans and AI agents. If you want a fast mental model, read the architecture diagram first.

Reading Order

Architecture overview (agent-oriented)
- docs/architecture/AGENT_DIAGRAM.md
- docs/architecture/AGENT_REPO_MAP.md
- docs/architecture/GATEWAY_SESSIONS_AND_QUEUE.md
- docs/architecture/TYPESCRIPT_MAP.md
- docs/architecture/SYMBOL_INDEX.md
- docs/architecture/CONTRIBUTOR_MAP.md
Security boundary (safe-by-default personal agent)
- docs/security/SAFE_PERSONAL_AGENT.md
Gateway API (WebSocket JSON-RPC)
- docs/api/PROTOCOL.md
Tool contracts and policy/execution details
- docs/api/TOOLS.md
Production and performance
- docs/deployment/PRODUCTION.md
- docs/performance/TUNING.md
Operations runbooks
- docs/operations/OPERATOR_PACK.md
- docs/operations/GOOGLE_AUTH.md

Quick Map (One Diagram)

flowchart TD
  U[User on chat surface] --> CA[ChannelAdapter]
  U --> GW[Gateway WS/HTTP + Web UI]

  CA --> RT[Routing + Sessions]
  GW --> RT

  RT --> OR[AgentOrchestrator]
  OR --> NA[NativeAgent tool loop]
  NA --> MR[ModelRouter]
  MR --> MC[ModelClient -> provider]

  NA --> TP[ToolPolicy + ToolRegistry]
  TP --> TE[ToolExecutor\nhooks + enforcement + audit]