 William Valentin
|
776b47f80f
|
feat: wire agent.delegate tool with sub-agent configs
- Export createAgentDelegateTool through builtin/index.ts → tools/index.ts
- Register agent.delegate in routing.ts with lazy orchestrator pattern
- Add agent.delegate + agents.list to messaging and coding policy profiles
- Add group:agents tool group to policy.ts
- Add research/code/comms agent config examples to default.yaml
- Add research/code/comms agent configs to user config.yaml
- Add 11 tests for agent-delegate tool (all pass)
- Typecheck clean, no regressions
|
2026-02-17 10:28:29 -08:00 |
|
|
William Valentin
|
4316dbd3be
|
feat: add P2 features — retry policy, prompt templating, usage tracking, tech debt cleanup
- Extract shared splitMessage() into channels/utils.ts (dedup 4 adapters)
- Add Slack user name resolution with caching (users.info API)
- Add withRetry() with exponential backoff + jitter, isRetryable() filter
- Wire retry config into ModelRouter.chat() (non-streaming only)
- Add assembleSystemPrompt() multi-file template system (SOUL/AGENTS/IDENTITY/USER/TOOLS.md)
- Add usage tracking accumulators in NativeAgent + AgentOrchestrator
- Add estimateCost() with per-model pricing table
- Add /usage TUI command with full usage report formatting
- Add retrySchema and promptSchema to config schema
Tests: 569 passing, typecheck clean
|
2026-02-06 15:12:35 -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 |
|