ariadne

bstein/ariadne

Fork 0

Commit Graph

Author	SHA1	Message	Date
codex	8c65b7bd60	feat(hermes-triage): retry_transient_infra action for connectivity failures Second entry in the action registry, proving it is a real extension point. No cluster mutation: the action is one Jenkins rebuild. - hermes_infra_signals: reviewable marker set across DNS/connectivity, image pull, upstream 5xx and agent-channel loss; Ariadne independently confirms a marker in the evidence before any retry, and records which marker justified it. "no space left on device" is deliberately excluded because a retry lands on the same full volume. - decision: classification -> action registry (action_classifications), falling back to the previous single-classification behavior - repair: retry_build posts to /build for unparameterized real jobs and buildWithParameters for the fixture demo job - orchestrator: retry path records requested/accepted/executed and moves the incident to awaiting_rebuild so the existing success path resolves it; one action per incident still enforced, so a retry cannot loop - events layer split out of the orchestrator to stay under the LOC cap Motivated by real failures tonight: pip DNS resolution and a Gitea 443 connect timeout, plus live incident metis/271 (SCM checkout timeout). 30 new tests; 368 pass in the hermes suite. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-08-05 20:42:48 -03:00
codex	c8d9ab2015	feat(hermes-autotriage): closed-loop demo triage via Hermes Agent API Adds the automated failure-to-repair loop for the hermes-triage-demo Jenkins job: - hermes_autotriage_logs: bounded kube-* OpenSearch evidence (fixed query, incident-ID correlation with window fallback, sanitization, byte caps) - hermes_agent_client: async /v1/runs client (bearer auth, poll, auto-deny approvals, lost-run and timeout handling) - hermes_autotriage_decision: frozen response schema parser + nine-gate action authorization (allowlist, confidence, idempotency, kill switch) - hermes_autotriage_evidence: Jenkins wfapi/testReport/console bundle assembly + failure-signature detection - hermes_autotriage_repair: hardcoded repair Job executor + one rebuild with SEED_FAILURE=false - hermes_autotriage: orchestrator state machine (detected -> diagnosed -> repairing -> awaiting_rebuild -> resolved \| human_required \| failed), bounded-label triage metrics, incident dedupe via storage events - settings/app: ARIADNE_HERMES_* config (default off) + 1m schedule task 126 new tests; all quality gates pass locally. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-08-05 17:06:16 -03:00

Author

SHA1

Message

Date

codex

8c65b7bd60

feat(hermes-triage): retry_transient_infra action for connectivity failures

Second entry in the action registry, proving it is a real extension point.
No cluster mutation: the action is one Jenkins rebuild.

- hermes_infra_signals: reviewable marker set across DNS/connectivity,
  image pull, upstream 5xx and agent-channel loss; Ariadne independently
  confirms a marker in the evidence before any retry, and records which
  marker justified it. "no space left on device" is deliberately excluded
  because a retry lands on the same full volume.
- decision: classification -> action registry (action_classifications),
  falling back to the previous single-classification behavior
- repair: retry_build posts to /build for unparameterized real jobs and
  buildWithParameters for the fixture demo job
- orchestrator: retry path records requested/accepted/executed and moves
  the incident to awaiting_rebuild so the existing success path resolves
  it; one action per incident still enforced, so a retry cannot loop
- events layer split out of the orchestrator to stay under the LOC cap

Motivated by real failures tonight: pip DNS resolution and a Gitea 443
connect timeout, plus live incident metis/271 (SCM checkout timeout).

30 new tests; 368 pass in the hermes suite.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-08-05 20:42:48 -03:00

codex

c8d9ab2015

feat(hermes-autotriage): closed-loop demo triage via Hermes Agent API

Adds the automated failure-to-repair loop for the hermes-triage-demo
Jenkins job:

- hermes_autotriage_logs: bounded kube-* OpenSearch evidence (fixed query,
  incident-ID correlation with window fallback, sanitization, byte caps)
- hermes_agent_client: async /v1/runs client (bearer auth, poll, auto-deny
  approvals, lost-run and timeout handling)
- hermes_autotriage_decision: frozen response schema parser + nine-gate
  action authorization (allowlist, confidence, idempotency, kill switch)
- hermes_autotriage_evidence: Jenkins wfapi/testReport/console bundle
  assembly + failure-signature detection
- hermes_autotriage_repair: hardcoded repair Job executor + one rebuild
  with SEED_FAILURE=false
- hermes_autotriage: orchestrator state machine (detected -> diagnosed ->
  repairing -> awaiting_rebuild -> resolved | human_required | failed),
  bounded-label triage metrics, incident dedupe via storage events
- settings/app: ARIADNE_HERMES_* config (default off) + 1m schedule task

126 new tests; all quality gates pass locally.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-08-05 17:06:16 -03:00

2 Commits