Commit Graph

18 Commits

Author SHA1 Message Date
William Valentin 93621bbe6e feat(analytics): add top tools and topics to session analytics 2026-02-16 14:45:45 -08:00
William Valentin 3d7144b2c5 feat(gateway): add system.sessionAnalytics usage snapshot RPC 2026-02-16 14:45:45 -08:00
William Valentin 3f627cc1ad feat(session): add optional end-of-session summarization 2026-02-16 13:18:42 -08:00
William Valentin 948d4ac6d8 chore(lint): burn down remaining warnings to zero 2026-02-15 23:14:21 -08:00
William Valentin 50dcff5ea6 chore: commit unrelated local changes 2026-02-15 21:51:22 -08:00
William Valentin 4f3810ba4c Revert "Use local Whisper compose stack"
This reverts commit 5f833e84a6.
2026-02-13 23:28:49 -08:00
William Valentin 5f833e84a6 Use local Whisper compose stack 2026-02-13 22:22:04 -08:00
William Valentin 9f81c01603 feat(session): persist model tier overrides per session
Store per-session config in SQLite and route /model and /reset through command fast-paths so channel sessions keep independent model selection across reconnects and restarts.
2026-02-13 01:04:26 -08:00
William Valentin 6e8984f788 feat(core): add command, intent, and routing primitives 2026-02-12 22:47:22 -08:00
William Valentin a8a2c59313 feat: implement model persistence with per-session overrides
- Add session_config SQLite table for per-session settings
- Update routing to support session override → agent config → global default resolution chain
- Upgrade WebChat SessionBridge from NativeAgent to AgentOrchestrator
- Add /model, /local, /cloud commands to Telegram adapter
- Add /model command to WebChat gateway handlers
- Clear session overrides on /reset command
- Pass memoryStore and config through to SessionBridge
- Add comprehensive tests for all new functionality

Fixes model persistence bug where TUI model changes didn't affect WebChat/Telegram sessions. Now:
- TUI /model sets global default (persists across restarts, affects all new sessions)
- WebChat/Telegram /model sets session override (only that conversation, cleared on /reset)
- WebChat sessions gain AgentOrchestrator features (delegation, compaction, memory)
2026-02-11 21:51:38 -08:00
William Valentin d62e836b5d feat(audit): Add core audit logging infrastructure
- Add AuditLogger class with rotation support
- Add audit configuration to config schema
- Instrument tool execution with full audit logging
- Instrument session lifecycle (create, message, delete, transfer, compact)
- Add audit logger initialization in daemon
- Add cron scheduler audit logging

Audit events captured:
- tool.start/success/error/denied
- session.create/message/delete/transfer/compact
- cron.trigger/add/remove

All logs go to ~/.local/share/flynn/audit.log (JSON lines)
with rotation (10MB files, 30-day retention)
2026-02-11 15:58:07 -08:00
William Valentin 6090508bad style: auto-fix ESLint issues (curly braces and formatting)
- Add curly braces to all if/else/for/while statements
- Fix indentation and trailing spaces
- Auto-fixed 372 linting errors using eslint --fix
- Remaining issues are warnings only (non-null assertions, explicit any types)
2026-02-11 10:30:24 -08:00
William Valentin ecd3aca7c1 feat(session): add pairing_approved table and getPairingStore() 2026-02-09 21:46:51 -08:00
William Valentin 1c2f54fae3 feat: implement tier 1 quick wins (tool groups, typing, pruning, verbose, think)
Five additive features with no breaking changes:

- Tool groups: group:fs, group:runtime, group:web, group:memory syntactic
  sugar for allow/deny lists in tool policy config
- Typing indicators: Discord sendTyping() and WhatsApp sendStateTyping()
  on message receipt for better UX feedback
- Session pruning: TTL-based auto-cleanup via sessions.ttl config with
  hourly daemon timer and SQLite GROUP BY pruning
- /verbose command: TUI command parser toggle for raw streaming display
- !!think prefix: per-message extended thinking mode wired through
  Anthropic (budget_tokens), OpenAI/GitHub (reasoning_effort), and
  Gemini (thinkingConfig) providers

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-07 13:35:00 -08:00
William Valentin 306e11bd2e feat: add multi-model delegation (Phase 0) and context compaction (Phase 1)
Phase 0 — Multi-Model Delegation:
- AgentOrchestrator wraps NativeAgent with delegate() for stateless
  single-turn calls to any model tier (fast/default/complex/local)
- DelegationConfig maps task types (compaction, classification, etc.)
  to model tiers
- Delegation prompts for compaction, memory extraction, classification,
  and tool summarisation
- Per-tier usage tracking for cost visibility
- Config schema: agents.delegation and agents.primary_tier

Phase 1 — Context Compaction:
- Token estimation (char/4 heuristic) with context window lookup
- shouldCompact() threshold check against context window percentage
- compactHistory() splits old/recent messages, delegates summary to
  fast tier, returns CompactionResult
- Automatic compaction in AgentOrchestrator.process() when configured
- Force-compact via orchestrator.compact() with session persistence
- Session.replaceHistory() with atomic SQLite transaction
- /compact TUI command with feedback on compacted token counts
- Config schema: compaction.enabled, threshold_pct, keep_turns,
  summary_max_tokens

Tests: 385 passing across 50 files (22 new tests in 2 new test files)
2026-02-06 13:17:02 -08:00
William Valentin 2fc07b4bca feat: add timestamps to session messages 2026-02-05 15:51:32 -08:00
William Valentin 2f1c302d85 feat: add SessionManager for multi-frontend session handling 2026-02-05 00:34:25 -08:00
William Valentin 10c848ca2a feat: add SQLite session persistence
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-03 00:27:12 -08:00