External/roboco
1
0
Fork 0
mirror of https://github.com/rennf93/roboco.git synced 2026-08-03 07:23:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(runtime): auto-submit is unconditional; refusals brief the fallback PM

Browse Source 
The PR-gate turn cut (#295) already auto-submitted assembled tasks, but
its refusals fell back to a PM spawn silently -- in production the PM
turns the cut was meant to remove kept happening with no visible cause
(live case: an AC-coverage refusal). The flag is gone (the fallback is
the safety net), the umbrella/branchless exclusion uses the canonical
batch predicates, and every refusal reason now rides into the spawned
PM's prompt so the fallback starts informed.
This commit is contained in:
Renn F
2026-07-08 22:16:50 +02:00
parent f48d088c08
commit 5e7c498d00
11 changed files with 209 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/map/_complete_map.md
+4 -4
View File
@@ -4707,8 +4707,8 @@ The AgentOrchestrator is the runtime brain of RoboCo: it owns the per-agent Dock
| AgentOrchestrator._pm_respawn_should_gate | method | roboco/runtime/orchestrator.py:8915 | Per-(slug,task) respawn circuit breaker; tracing_gap rule-following resets (bounded) + durable persist; CEO notify once when tripped. |
| AgentOrchestrator._handle_pm_assigned_task | method | roboco/runtime/orchestrator.py:9084 | Spawn/respawn the PM for an assigned coordination root subject to the respawn gate. |
| AgentOrchestrator._AUTO_SUBMIT_VERB_BY_ROLE | ClassVar[dict] | roboco/runtime/orchestrator.py:10650 | Wave-1 PR-gate turn cut: maps cell_pm -> (cell_pm, submit_up) and main_pm -> (main_pm, submit_root), the flow route+verb that assembles the parent's PR for each coordinator role. |
| AgentOrchestrator._auto_submit_target | method | roboco/runtime/orchestrator.py:10655 | Resolve (role, route, verb, pm_uuid) for an auto-submittable parent; None when `pr_gate_auto_submit_enabled` is off, the parent is branchless coordination (no PR to assemble), the role has no submit verb, or no PM identity resolves. |
| AgentOrchestrator._try_auto_submit | method | roboco/runtime/orchestrator.py:10677 | Wave-1 PR-gate turn cut: run the owning PM's submit_up/submit_root verb system-side via the internal flow API (no PM spawn) when every child of an assembled parent is terminal; True on gate acceptance (fires `task.auto_submitted` audit + `_mark_task_handled`), False on ANY refusal (flag off, branchless parent, unmapped role, gate rejection, or transport error) so the caller falls back to the classic PM closure spawn. |
| AgentOrchestrator._auto_submit_target | method | roboco/runtime/orchestrator.py:10655 | Resolve (role, route, verb, pm_uuid) for an auto-submittable parent; None when the parent is branchless coordination (no PR to assemble), the role has no submit verb, or no PM identity resolves. Unconditional otherwise — no flag (the `pr_gate_auto_submit_enabled` kill-switch was removed post-0.19.0). |
| AgentOrchestrator._try_auto_submit | method | roboco/runtime/orchestrator.py:10677 | PR-gate turn cut: run the owning PM's submit_up/submit_root verb system-side via the internal flow API (no PM spawn) when every child of an assembled parent is terminal; True on gate acceptance (fires `task.auto_submitted` audit + `_mark_task_handled`), False on ANY refusal (branchless parent, unmapped role, gate rejection, or transport error) so the caller falls back to the classic PM closure spawn with the refusal reason threaded into its prompt. |
| AgentOrchestrator._closure_handled_without_pm | method | roboco/runtime/orchestrator.py:10740 | Recover an auto-paused/blocked parent's status first (so the next actor lands on an actionable in_progress parent), then try `_try_auto_submit`; True skips the PM closure spawn entirely. |
| AgentOrchestrator._maybe_spawn_pm_closure | method | roboco/runtime/orchestrator.py:10768 | If this parent task is ready for closure, try the system-side submit turn cut first (`_closure_handled_without_pm`); only spawn its PM when that declines (debounced via _is_recently_paused). |
| AgentOrchestrator._dispatch_dev_work | method | roboco/runtime/orchestrator.py:9733 | Fetch pending/needs_revision/in_progress/claimed code tasks and route each through _dev_dispatch_one. |
@@ -4780,7 +4780,7 @@ stateDiagram-v2
- Rate-limit/overload park-and-probe: `_park_provider_unavailable` (+ grok 75/78 variants) → `_rate_limit_probe_loop` (30s) → `_on_probe_success`/`_on_probe_failure` → `resolve_wait`
- Gateway-health: `_probe_gateway_health` → `_gateway_broken_past_grace` → `_maybe_recover_broken_gateway` (kill+evict)
- Respawn tracker: `_pm_respawn_should_gate` → `_persist_respawn_record` (durable upsert) + `restore_respawn_tracker` at startup
- PM closure / PR-gate turn cut (wave 1): `_maybe_spawn_pm_closure` → `_closure_handled_without_pm` (recover paused/blocked status) → `_try_auto_submit` (system-side submit_up/submit_root via `_AUTO_SUBMIT_VERB_BY_ROLE`, gated by `pr_gate_auto_submit_enabled`); only a gate refusal falls through to an actual PM spawn
- PM closure / PR-gate turn cut: `_maybe_spawn_pm_closure` → `_closure_handled_without_pm` (recover paused/blocked status) → `_try_auto_submit` (system-side submit_up/submit_root via `_AUTO_SUBMIT_VERB_BY_ROLE`, unconditional — no flag); only a gate refusal falls through to an actual PM spawn, with the refusal reason threaded into its prompt
- Default-off loops: `_self_heal_loop`, `_ci_watch_loop`, `_dep_update_loop`, `_release_manager_loop`, `_strategy_engine_loop`, `_external_pr_poll_loop`, `_x_mentions_poll_loop`, `_roadmap_engine_loop`
- Interactive: `start_intake_session` / `_spawn_intake_container` / `_spawn_secretary_container` / `_reap_idle_interactive_sessions`
- Shutdown (`stop`): cancel loops → `stop_agent(release_claim=True)` (skip provider-parked) → `_drain_bg_tasks` → `_stopped`
@@ -4815,7 +4815,7 @@ stateDiagram-v2
- `ROBOCO_ROADMAP_ENGINE_ENABLED` (+ `_interval_seconds` default 604800 / `_min_items_per_cycle` / `_max_items_per_cycle`, default off) — gates `_roadmap_engine_loop`.
- `ROBOCO_X_FEATURE_SPOTLIGHT_ENABLED` (+ `_interval_seconds` default 259200/3d, default off, sub-switch of `x_engine_enabled`) — gates `_x_feature_spotlight_loop`.
- `ROBOCO_FABLE_MODE_ENABLED` (default off) — gates `_fable_hook_groups` (Claude-path hook install) and, via `roboco/agents/factories/_base.py`, the `fable_doctrine_layer` prompt layer; off = byte-for-byte unchanged spawn path.
- `ROBOCO_PR_GATE_AUTO_SUBMIT_ENABLED` (`pr_gate_auto_submit_enabled`, default **True**) — wave-1 PR-gate turn cut: when every child of an assembled parent is terminal, `_try_auto_submit` runs the owning PM's submit_up/submit_root gate system-side instead of spawning the PM for that turn; a gate rejection (freshness/integrity) falls back to the classic PM closure spawn.
- No flag — the PR-gate turn cut is unconditional: when every child of an assembled parent is terminal, `_try_auto_submit` always runs the owning PM's submit_up/submit_root gate system-side instead of spawning the PM for that turn; a gate rejection (freshness/integrity/AC-coverage/race) falls back to the classic PM closure spawn (the sole safety net), with the reason threaded into the PM's closure prompt. The `pr_gate_auto_submit_enabled` kill-switch that gated this through 0.19.0 has been removed.
## Gotchas
- Respawn-tracker rows are restored at startup and re-stamped to live values; terminal/missing-task rows are evicted, so a stale row can't gate a fresh task. The upsert is race-free but fire-and-forget persists are ordered by `_respawn_persist_lock` acquisition (= schedule order); a stale persist resolving after a fresh one would otherwise re-burn the strike threshold on restart.
docs/map/orchestrator.md
+4 -4
View File
@@ -97,8 +97,8 @@ The AgentOrchestrator is the runtime brain of RoboCo: it owns the per-agent Dock
| AgentOrchestrator._pm_respawn_should_gate | method | roboco/runtime/orchestrator.py:8915 | Per-(slug,task) respawn circuit breaker; tracing_gap rule-following resets (bounded) + durable persist; CEO notify once when tripped. |
| AgentOrchestrator._handle_pm_assigned_task | method | roboco/runtime/orchestrator.py:9084 | Spawn/respawn the PM for an assigned coordination root subject to the respawn gate. |
| AgentOrchestrator._AUTO_SUBMIT_VERB_BY_ROLE | ClassVar[dict] | roboco/runtime/orchestrator.py:10650 | Wave-1 PR-gate turn cut: maps cell_pm -> (cell_pm, submit_up) and main_pm -> (main_pm, submit_root), the flow route+verb that assembles the parent's PR for each coordinator role. |
| AgentOrchestrator._auto_submit_target | method | roboco/runtime/orchestrator.py:10655 | Resolve (role, route, verb, pm_uuid) for an auto-submittable parent; None when `pr_gate_auto_submit_enabled` is off, the parent is branchless coordination (no PR to assemble), the role has no submit verb, or no PM identity resolves. |
| AgentOrchestrator._try_auto_submit | method | roboco/runtime/orchestrator.py:10677 | Wave-1 PR-gate turn cut: run the owning PM's submit_up/submit_root verb system-side via the internal flow API (no PM spawn) when every child of an assembled parent is terminal; True on gate acceptance (fires `task.auto_submitted` audit + `_mark_task_handled`), False on ANY refusal (flag off, branchless parent, unmapped role, gate rejection, or transport error) so the caller falls back to the classic PM closure spawn. |
| AgentOrchestrator._auto_submit_target | method | roboco/runtime/orchestrator.py:10655 | Resolve (role, route, verb, pm_uuid) for an auto-submittable parent; None when the parent is branchless coordination (no PR to assemble), the role has no submit verb, or no PM identity resolves. Unconditional otherwise — no flag (the `pr_gate_auto_submit_enabled` kill-switch was removed post-0.19.0). |
| AgentOrchestrator._try_auto_submit | method | roboco/runtime/orchestrator.py:10677 | PR-gate turn cut: run the owning PM's submit_up/submit_root verb system-side via the internal flow API (no PM spawn) when every child of an assembled parent is terminal; True on gate acceptance (fires `task.auto_submitted` audit + `_mark_task_handled`), False on ANY refusal (branchless parent, unmapped role, gate rejection, or transport error) so the caller falls back to the classic PM closure spawn with the refusal reason threaded into its prompt. |
| AgentOrchestrator._closure_handled_without_pm | method | roboco/runtime/orchestrator.py:10740 | Recover an auto-paused/blocked parent's status first (so the next actor lands on an actionable in_progress parent), then try `_try_auto_submit`; True skips the PM closure spawn entirely. |
| AgentOrchestrator._maybe_spawn_pm_closure | method | roboco/runtime/orchestrator.py:10768 | If this parent task is ready for closure, try the system-side submit turn cut first (`_closure_handled_without_pm`); only spawn its PM when that declines (debounced via _is_recently_paused). |
| AgentOrchestrator._dispatch_dev_work | method | roboco/runtime/orchestrator.py:9733 | Fetch pending/needs_revision/in_progress/claimed code tasks and route each through _dev_dispatch_one. |
@@ -170,7 +170,7 @@ stateDiagram-v2
- Rate-limit/overload park-and-probe: `_park_provider_unavailable` (+ grok 75/78 variants) → `_rate_limit_probe_loop` (30s) → `_on_probe_success`/`_on_probe_failure` → `resolve_wait`
- Gateway-health: `_probe_gateway_health` → `_gateway_broken_past_grace` → `_maybe_recover_broken_gateway` (kill+evict)
- Respawn tracker: `_pm_respawn_should_gate` → `_persist_respawn_record` (durable upsert) + `restore_respawn_tracker` at startup
- PM closure / PR-gate turn cut (wave 1): `_maybe_spawn_pm_closure` → `_closure_handled_without_pm` (recover paused/blocked status) → `_try_auto_submit` (system-side submit_up/submit_root via `_AUTO_SUBMIT_VERB_BY_ROLE`, gated by `pr_gate_auto_submit_enabled`); only a gate refusal falls through to an actual PM spawn
- PM closure / PR-gate turn cut: `_maybe_spawn_pm_closure` → `_closure_handled_without_pm` (recover paused/blocked status) → `_try_auto_submit` (system-side submit_up/submit_root via `_AUTO_SUBMIT_VERB_BY_ROLE`, unconditional — no flag); only a gate refusal falls through to an actual PM spawn, with the refusal reason threaded into its prompt
- Default-off loops: `_self_heal_loop`, `_ci_watch_loop`, `_dep_update_loop`, `_release_manager_loop`, `_strategy_engine_loop`, `_external_pr_poll_loop`, `_x_mentions_poll_loop`, `_roadmap_engine_loop`
- Interactive: `start_intake_session` / `_spawn_intake_container` / `_spawn_secretary_container` / `_reap_idle_interactive_sessions`
- Shutdown (`stop`): cancel loops → `stop_agent(release_claim=True)` (skip provider-parked) → `_drain_bg_tasks` → `_stopped`
@@ -205,7 +205,7 @@ stateDiagram-v2
- `ROBOCO_ROADMAP_ENGINE_ENABLED` (+ `_interval_seconds` default 604800 / `_min_items_per_cycle` / `_max_items_per_cycle`, default off) — gates `_roadmap_engine_loop`.
- `ROBOCO_X_FEATURE_SPOTLIGHT_ENABLED` (+ `_interval_seconds` default 259200/3d, default off, sub-switch of `x_engine_enabled`) — gates `_x_feature_spotlight_loop`.
- `ROBOCO_FABLE_MODE_ENABLED` (default off) — gates `_fable_hook_groups` (Claude-path hook install) and, via `roboco/agents/factories/_base.py`, the `fable_doctrine_layer` prompt layer; off = byte-for-byte unchanged spawn path.
- `ROBOCO_PR_GATE_AUTO_SUBMIT_ENABLED` (`pr_gate_auto_submit_enabled`, default **True**) — wave-1 PR-gate turn cut: when every child of an assembled parent is terminal, `_try_auto_submit` runs the owning PM's submit_up/submit_root gate system-side instead of spawning the PM for that turn; a gate rejection (freshness/integrity) falls back to the classic PM closure spawn.
- No flag — the PR-gate turn cut is unconditional: when every child of an assembled parent is terminal, `_try_auto_submit` always runs the owning PM's submit_up/submit_root gate system-side instead of spawning the PM for that turn; a gate rejection (freshness/integrity/AC-coverage/race) falls back to the classic PM closure spawn (the sole safety net), with the reason threaded into the PM's closure prompt. The `pr_gate_auto_submit_enabled` kill-switch that gated this through 0.19.0 has been removed.
## Gotchas
- Respawn-tracker rows are restored at startup and re-stamped to live values; terminal/missing-task rows are evicted, so a stale row can't gate a fresh task. The upsert is race-free but fire-and-forget persists are ordered by `_respawn_persist_lock` acquisition (= schedule order); a stale persist resolving after a fresh one would otherwise re-burn the strike threshold on restart.