will/flynn
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(subagents): complete queue, budgets, audit, and inspection controls

Browse Source
This commit is contained in:
William Valentin
2026-02-26 13:28:10 -08:00
parent b679261683
commit 3cc9e16ef5
23 changed files with 741 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/architecture/GATEWAY_SESSIONS_AND_QUEUE.md
+1 -1
View File
@@ -17,7 +17,7 @@ If you only want the protocol surface, see `docs/api/PROTOCOL.md`.
- Backend routing outcomes are auditable via `backend.route` / `backend.success` / `backend.fallback`, which enables offline canary evaluation without changing gateway protocol methods.
- Run lifecycle/cancel intent and reaction decisions are emitted to audit logs, and aggregated into `system.metrics` counters (runStates, cancelLatencyMs, reactions) for dashboards.
- Reaction matching is deterministic (priority + cooldown + recursion guard) before intent/agent routing.
- `subagent.*` tools create child orchestrators scoped to the parent conversation (`subagent:<parentSessionId>:<childId>`) with idle TTL cleanup; this is tool-loop behavior, not a separate gateway RPC session lane.
- `subagent.*` tools create child orchestrators scoped to the parent conversation (`subagent:<parentSessionId>:<childId>`) with idle TTL cleanup, per-child queue mode (`followup|interrupt`), and session budgets (turn/token/timeout); this is tool-loop behavior, not a separate gateway RPC session lane.
- Companion `node.*` registration is per WebSocket connection; reconnects must re-register capabilities before invoking node RPC methods.
- Canvas artifacts are persisted per session under the gateway data directory for UI recovery across restarts.
- TTS output is best-effort; synthesis failures fall back to text-only responses.