mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-25 14:54:38 +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>
54 lines
1.1 KiB
TypeScript
54 lines
1.1 KiB
TypeScript
export type {
|
|
AnyToolSpec,
|
|
Logger,
|
|
ModuleId,
|
|
PolicyHint,
|
|
ToolContext,
|
|
ToolScope,
|
|
ToolSpec,
|
|
} from './types.ts';
|
|
|
|
export {
|
|
__resetRegistryForTests,
|
|
getRegistry,
|
|
getTool,
|
|
getToolsByModule,
|
|
registerTool,
|
|
} from './registry.ts';
|
|
|
|
export {
|
|
DEFAULT_PER_TOOL_RATE_LIMIT,
|
|
RATE_LIMIT_WINDOW_MS,
|
|
detectInjectionMarker,
|
|
evaluatePolicy,
|
|
type InvocationEvent,
|
|
type PolicyDecision,
|
|
type PolicyInput,
|
|
type UserPolicySettings,
|
|
} from './policy.ts';
|
|
|
|
export type {
|
|
SyncChange,
|
|
SyncClientConfig,
|
|
SyncFieldChange,
|
|
SyncPullResponse,
|
|
SyncPushRequest,
|
|
} from './sync-client.ts';
|
|
|
|
export { pullAll, push, pushInsert } from './sync-client.ts';
|
|
|
|
export {
|
|
MasterKeyClient,
|
|
MasterKeyFetchError,
|
|
ZeroKnowledgeUserError,
|
|
type MasterKeyClientConfig,
|
|
} from './master-key-client.ts';
|
|
|
|
export { decryptRecordFields, encryptRecordFields } from '@mana/shared-crypto';
|
|
|
|
/**
|
|
* Consumers call this to register every bundled tool at once. It is a
|
|
* side-effect-bearing import that pulls in all module files. If a consumer
|
|
* only wants a subset, it can import the individual module barrels directly.
|
|
*/
|
|
export { registerAllModules } from './modules/index.ts';
|