till/managarten
1
0
Fork 0
mirror of https://github.com/Memo-2023/mana-monorepo.git synced 2026-05-15 00:41:09 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4
managarten/docs/reports
History
Till JS e5d230e599 feat(agent-loop): M1 — policy gate + reminder channel + parallel reads 
Three Claude-Code-inspired primitives for runPlannerLoop, derived from the
reverse-engineering reports in docs/reports/:

1. **Policy gate** (@mana/tool-registry) — evaluatePolicy() gates every tool
   dispatch: denies admin-scope, denies destructive tools not in the user's
   opt-in list, rate-limits per tool (30/60s default), flags prompt-injection
   markers in freetext without blocking. Wired into mana-mcp with a
   per-user rolling invocation log and POLICY_MODE env (off|log-only|enforce,
   default log-only). mana-ai uses detectInjectionMarker only — tool dispatch
   there is plan-only, so rate-limit/destructive checks don't apply yet.

2. **Reminder channel** (packages/shared-ai/src/planner/loop.ts) — new
   reminderChannel callback in PlannerLoopInput. Called once per round with
   LoopState snapshot (round, toolCallCount, usage, lastCall); returned
   strings wrap in <reminder> tags and inject as transient system messages
   into THIS LLM request only. Never pushed to messages[] — the Claude-Code
   <system-reminder> pattern that keeps the KV-cache prefix stable.

3. **Parallel reads** (loop.ts) — isParallelSafe predicate enables
   Promise.all dispatch when every tool_call in a round is parallel-safe,
   in batches of PARALLEL_TOOL_BATCH_SIZE=10. Any non-safe call downgrades
   the whole round to sequential. messages[] always appends in source
   order, never completion order, so the debug log stays linear.
   Default-off (undefined predicate) preserves pre-M1 behaviour.

Tests: 21 new in tool-registry (policy), 9 new in shared-ai (5 parallel,
4 reminder). All 74 green, type-check clean across 4 packages.

Design/plan: docs/plans/agent-loop-improvements-m1.md
Reports: docs/reports/claude-code-architecture.md,
         docs/reports/mana-agent-improvements-from-claude-code.md

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-23 13:56:40 +02:00
..
ai-agent-architecture-comparison.md docs: final report update — 7/10 roadmap items done, all tables consistent 2026-04-16 15:23:37 +02:00
claude-code-architecture.md feat(agent-loop): M1 — policy gate + reminder channel + parallel reads 2026-04-23 13:56:40 +02:00
clubdesk-vs-mana-comparison.md docs(invoices): ClubDesk vs. Mana comparison + invoices module plan 2026-04-20 15:27:57 +02:00
gemini-deep-research.md docs(gemini-deep-research): Mac-Mini deploy log 2026-04-22 2026-04-22 18:22:31 +02:00
mana-agent-improvements-from-claude-code.md feat(agent-loop): M1 — policy gate + reminder channel + parallel reads 2026-04-23 13:56:40 +02:00
web-research-capabilities.md feat(research): add mana-research service — Phase 1 + 2 2026-04-17 14:42:25 +02:00