mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-14 23:21:08 +02:00
e5d230e599
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>
27 lines
720 B
JSON
27 lines
720 B
JSON
{
|
|
"name": "@mana/tool-registry",
|
|
"version": "0.1.0",
|
|
"private": true,
|
|
"type": "module",
|
|
"sideEffects": false,
|
|
"description": "Single-source tool registry consumed by mana-ai (mission runner) and mana-mcp (MCP server). Each module declares its agent-callable operations once; both consumers derive their schemas from here.",
|
|
"main": "./src/index.ts",
|
|
"types": "./src/index.ts",
|
|
"exports": {
|
|
".": "./src/index.ts",
|
|
"./modules": "./src/modules/index.ts"
|
|
},
|
|
"scripts": {
|
|
"type-check": "tsc --noEmit",
|
|
"lint": "eslint .",
|
|
"test": "vitest run"
|
|
},
|
|
"dependencies": {
|
|
"@mana/shared-crypto": "workspace:*",
|
|
"zod": "^3.25.76"
|
|
},
|
|
"devDependencies": {
|
|
"typescript": "^5.9.3",
|
|
"vitest": "^4.1.3"
|
|
}
|
|
}
|