Drive the cross-card implement->review->repair->re-review chain from inside
the pod so unattended runs no longer stall once the first implementation card
completes. Today that chain exists only as an external codex-shepherd session;
this adds a bounded in-pod poll loop that reads board state via
hermes_cli.kanban_db and creates Kanban follow-up cards (subscription lanes
only) with no provider/metered path of its own.
- kanban_supervisor.py (I/O shell) + supervisor_policy.py (pure state machine):
impl-done+PR -> review; review SHIP -> mark impl ready-for-human (never
merges/approves/clears WIP); review BLOCK -> bounded repair; repair new
commit -> re-review. Fail-closed on unparseable/ambiguous state; per-
(parent, head_commit) dedup safe beside the external shepherd; bounded review
<->repair cycle count and max concurrent chains.
- Deployed as a hardened non-root sidecar (drop ALL caps, read-only rootfs, no
runtime-access/credential mount) alongside model-steward; scripts packaged in
the coordinator configMapGenerator.
- Gated by new kanban.auto_supervise config key (default false, re-read each
tick like auto_decompose) so it is inert until the external shepherd retires.
- Fix latent goal_max_turns NULL fallback in cli_lane_execution (1 -> documented
default 20).
- 62 new behavioral tests at 100% line+branch on both modules.
Stacks on the merge train (base 5f27e50c).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Based on PR #15 (fix/hermes-result-decomposition-reliability); stacked
on the decomposed cli_lane modules.
- cli_lane_quota: soft-exclude a provider from NEW cli-auto work below
the remaining-quota threshold (both-below prefers more remaining;
fetch failure fails open with a metric).
- cli_lane_health: lane now writes provider health (G7) with classified
failure reasons splitting the capacity conflation (quota/auth/
rate-limit/transport) and cooldown hysteresis; re-admission only on
full cooldown expiry, passed quota reset, or fresh success (G4).
- cli_lane_routing: capacity-limited health now excludes a provider
(G3); cooldown/reset-aware re-admission.
- cli_lane_failover: explicit cli-codex-*/cli-claude-* assignees fail
closed as transient instead of switching providers (G5); fallback
depth stays bounded at two hosted providers (G1) with effort
preserved; Switchyard outages block transient, not capability (G9).
- cli_lane_metrics: route-decision/fallback counters, quota and
soft-exclusion gauges, pod-local scrape server (G6).
- cli_lane_provider: worker env drops ANTHROPIC_API_KEY, CLAUDE_API_KEY,
OPENAI_API_KEY, API_SERVER_KEY so no metered path exists (G10).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Independent review t_5975c06a blocked this branch on a P1: a Kanban write that
failed while a lease expired left a `lease_failed` row that was invisible to
every pass, immortal to garbage collection, and fatal to the coordinator. It
poisoned `reconcile()` forever with a conflicting-duplicate primary key,
produced a spurious capability `block_task` from `dispatch()`, and -- because
startup maintenance ran unguarded before the port bound, against a store on a
PVC -- crash-looped the coordinator with no automatic recovery.
`lease_failed` is now a retryable state that every maintenance pass drains, and
a row only reaches a terminal state on authoritative evidence about its exact
Kanban run, so nothing is collected before its outcome is known and nothing is
silently dropped. Each row, task, and board is processed in isolation, and a
coordinator-side fault is never converted into a Kanban mutation. Startup runs
through the same guarded cycle as the steady-state loop.
The wire protocol and the durable store are now separate modules, and the
maintenance passes moved out of the coordinator, so each file stays under the
managed line ceiling with room for the recovery logic.
Also closes three consequential handoff risks the same review raised:
* mediator-N pinned itself hard to worker-N while sharing a ReadWriteOnce
claim, so a drain or preemption that moved only the lower-priority worker
deadlocked the ordinal on Multi-Attach until an operator deleted a Pod. The
shared workspace is now ReadWriteMany (as the hermes-chat tenant workspaces
already are on the same class), colocation is a preference, and the mediator
shares the worker's preemption priority, so each Pod reschedules on its own.
* the broker permits only branch creation, so a retry that added commits could
never submit and the run's work was discarded with the failure. Submission
now targets a fresh attempt- or content-scoped ref in the same reviewed
namespace -- never an update -- and is idempotent under replay. A refused
submission downgrades the result and says why instead of unwinding the run.
* the provider CLIs were reinstalled into an emptyDir on every Pod start inside
the 10m Flux health window for the whole hermes app. They now install once
per pinned version onto a durable volume, re-verified against the real
binaries and time-bounded, and the best-effort pool no longer gates the
health of the app its dependents wait on.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The distributed worker pool stacks on exactly two open pull requests, in this
order: PR 14 supplies the broker-only SCM boundary the mediators route through
and the hermes-scm-boundary-v2 ConfigMap they mount, and PR 15 supplies the
cli_lane_* decomposition -- including canonical_run_id and the eligibility
predicate on claim_ready -- that the coordinator depends on. Neither can be
dropped without breaking a fixed P0 boundary, so both are carried here as
prerequisites and this branch must not merge before them.
PR 16 (agent image release lane) and PR 19 (full-handoff acceptance harness)
are NOT prerequisites and are deliberately absent, so reviewing this branch no
longer means approving them.
PR 14 and PR 15 conflict with each other in nine paths. Each is resolved to the
resolution already reviewed on this branch at 4d4cf1bd.
evaluate_names_absent returned PASS when its step exited 0 with no output,
so five mandatory checks - the ones asserting that provider API keys, forge
credentials, a cluster-admin binding, and shared coordinator state are
absent - could report a pass on no evidence and turn a NO_GO into a GO.
Both name rules now resolve their step through one guard in _line_step, so
zero observations are NOT_RUN. Regressions pin all five real catalog specs
plus both reachable silence paths: a POSIX pipeline whose status comes from
its last stage, and a drifted kubectl -o jsonpath. The pool claim projection
emits one <volume>=<claim> line per template volume so a volume without a
PVC still counts as an observation rather than reading as drift.
Also closes the review's reachable hardening and evidence defects:
- pin Gitea paths to atlas/titan-iac on an exact segment boundary and
reject relative segments, including percent-encoded ones
- forbid impersonation structurally in every mode and vantage; the inner
command of kubectl exec is re-checked rather than exempted, and
validate_catalog no longer guards only the operator vantage
- drop flux and helm from the binary allowlist; they had no pinned release
digest, so no allowlisted binary can now be admitted that the executor
would refuse to attest
- remove the inert --concurrency and --expect-telegram-sessions flags and
the dead concurrency bound; Telegram continuity stays mandatory
- read the ephemeral pull index page by page, treat the create response as
an authoritative source for the pull number, close every number either
source names, and surface residue_ref plus exact manual_cleanup commands
when creation is uncertain
- keep executable_path and executable_sha256 on unrecorded bulk-evidence
steps so withholding bytes never withholds binary attestation
- revert the repo-wide hygiene legacy-exception mechanism; the contract
change here is purely additive and the four pre-existing over-cap files
are left to the canonical contract change in PR #14/#15
- correct the runbook ruff format scope so the documented command passes
Split hermes_handoff_arming.py out of hermes_handoff_ephemeral.py to keep
both modules under the 500-line cap. All 16 handoff modules hold at least
95% line and branch coverage; the mutation gate is 13/13.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
