Commit Graph
29 Commits
Author SHA1 Message Date
root cd9ec6a0df fix: correct key-lifecycle contracts to match measured reality
- hermes-key-enforcement.prose.md:
  - State that expiry must be set EXPLICITLY at creation with duration
  - Record that config default is NOT honoured by LiteLLM 1.99.1
  - Describe daily audit as AUDIT-ONLY (reports non-expiring and soon-to-expire)
  - State that renewal is NOT implemented
  - Document exclusions: abiba-pi and all crewmate keys stay WITHOUT expiry
  - koby is report-only

- litellm-api-keys.prose.md:
  - Replace literal master key with retrieval path (docker exec + infisical)
  - State that literal values must never be trusted again (key rotates)
  - Add live-key check (200 from /key/list)

Signed-off-by: Abiba
2026-09-15 02:59:19 +00:00
root 9a789ab76d fix(hermes): separate policy observations from fault findings
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 5s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 7s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 7s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 6s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 3s
Contract design defect: 'uses a non-harness provider' (POLICY) and
'cannot authenticate' (FAULT) were printed as the same violation class.
A policy observation must never be phrased as if the agent were broken.

Changes:
1. Added 'Violation Classification' section to all three contracts
2. Separated POLICY (observation only) from FAULT (requires request-level evidence)
3. Rules:
   - Do NOT infer runtime credential resolution from config text alone
   - Require request-level evidence before calling a FAULT: observed auth failure
     or absence of successful calls
   - If calls are succeeding, output is 'POLICY: uses <provider> directly; calls
     succeeding' - not a violation
   - State what you OBSERVED, not what the field implies

Files changed (3):
- hermes-key-enforcement.prose.md
- hermes-config-template.prose.md
- hermes-agent-baseline.prose.md
2026-09-14 12:32:06 +00:00
root 4e34b7a2a2 fix(hermes): wire all three contracts to reachability helper
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 4s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 5s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 5s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 6s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 1s
The helper was correct but dead code - nothing called it. This commit:
1. Makes the helper runnable standalone: scripts/hermes-reachability-check.sh <host> <pattern> <path>
2. Wires all THREE contracts to it:
   - hermes-key-enforcement.prose.md
   - hermes-config-template.prose.md
   - hermes-agent-baseline.prose.md
3. Each contract now explicitly instructs to run the helper and interpret the three outcomes
4. States that the bug this replaces was deriving reachability from the remote grep's exit code

Files changed (4):
- scripts/hermes-reachability-check.sh (standalone mode added)
- hermes-key-enforcement.prose.md (reachability section added)
- hermes-config-template.prose.md (reachability section added)
- hermes-agent-baseline.prose.md (reachability section added)
2026-09-14 12:01:32 +00:00
root 8210fd905c fix: align contracts to 4-name LiteLLM registry (2026-09-12)
PR Pipeline — Authorize → Validate → Review → Merge / auth (push) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / validate (push) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / lint (push) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (push) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / gate (push) Successful in 1s
- Remove retired names (qwen3.6-27B-code, qwen3.6-35B-udq4) from live alias claims
- Update Strix Halo model to Carnice-Qwen3.6-MoE-35B-A3B-Q4_K_M.gguf (strix-moe, 256K ctx)
- Fix litellm-health step 7 probe to gpu-vision (monitor key scoped)
- Move qwen3.6-27B-code/35B-udq4 from raw-but-live to non-resolving in audit
- Fold in pm2-self-heal: remove spoton-service (live PM2 set is 4/4)
- Update hermes templates, key enforcement, timeout tables to live names
2026-09-12 21:39:54 +00:00
root ce48070f21 no-mistakes(review): Derive model fields recursively; fix historical latency and key claims 2026-09-12 16:33:58 +00:00
root 9e581ab203 no-mistakes(review): Complete retired-alias field coverage; fix misleading example labels 2026-09-12 16:26:14 +00:00
root 9cac3589cf no-mistakes(review): Fix compression example alias; make retired aliases fail audit 2026-09-12 16:19:43 +00:00
abiba 221f9f79f3 fix(audit): reject retired aliases; sweep gpu-light/gemma-4-12b to gpu-vision
audit-hermes-config.py Rule 8 required auxiliary.vision.model and
auxiliary.web_extract.model to equal the retired 'gpu-light', so a config
adopting the live canonical 'gpu-vision' FAILED our own audit - the audit was
enforcing a dead alias (400 Invalid model name). Rule 8 now requires
gpu-vision; retired names gpu-light/crew-auto join the raw-name rejection set;
the guidance message names the live aliases.

Sweep of the remaining references: gpu-self-heal stops canonicalizing
gpu-light; hermes-config-template, hermes-agent-baseline, hermes-key-enforcement,
inference-optimization, litellm-client-timeouts and gpu-fleet now use the live
gpu-vision alias. Where a file restated model/rpm/weight/fallback state it now
points at CT 116 /opt/inference-harness/litellm_config.yaml instead of
duplicating it. koby's .129 config is report-only and recorded, not edited.

Adds tests/test_audit_hermes_config_alias.py: executes the audit CLI and asserts
gpu-vision passes while gpu-light and gemma-4-12b fail.
2026-09-12 16:11:46 +00:00
mumuni-bot e898048baf fix: repoint Mumuni refs from CT100/.24 to kagentz CT105/.14 post-migration
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 4s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 0s
Mumuni migrated off Abiba CT100 (192.168.68.24, purged) to dedicated
CT kagentz (192.168.68.14) on minipve. Verified live on kagentz:
- Gateway: systemd unit hermes-gateway.service (User=hermes), active
- Hermes home: /home/hermes/.hermes
- gateway_state.json present at ~/.hermes/gateway_state.json

Updates Mumuni rows/references in 9 contracts. Abiba-owned refs
(.24 pi agent, GPU monitor, infrastructure-control CRITICAL file)
and historical runs/ logs intentionally left unchanged.

Per relay #738 follow-ups. Refs #735-#738.
2026-08-29 21:41:07 +00:00
root 994ae1b7ac fix: standardize base URLs to authenticated /litellm/v1 path in remaining contracts
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 1s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 2s
- Update hermes-agent-baseline.prose.md: change /v1 → /litellm/v1 in all base_url references
- Update hermes-key-enforcement.prose.md: change workaround section base_url to /litellm/v1
- Ensures all contracts consistently use the authenticated LiteLLM path
- DeepSeek harness exemption remains documented for external providers
2026-08-28 15:32:24 +00:00
root 9f0a940cee Fix no-mistakes warnings: prose out of YAML fence, Rule 16 rename, table cell fix
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 1s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 5s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 1s
2026-08-11 18:02:08 +00:00
root 5c3ba31b17 Ship: Koby external-agent ruling (Resolve conflict and merge master)
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 4s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 4s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 5s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 1s
2026-08-11 17:48:36 +00:00
root d0144d6db6 Ship: Koby external-agent ruling (fix api_key_env hygiene + docs)
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 0s
2026-08-11 17:22:25 +00:00
root 38a32f8b32 Ship: enforcement-rules-reality-fix (captain directive 2026-08-09)
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 1s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 1s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 1s
2026-08-10 13:28:53 +00:00
root 93fb0d8e1e feat(contracts): add MCP URL validation and verify virtual keys on LiteLLM
PR Pipeline — Authorize → Validate → Review → Merge / auth (push) Successful in 5s
PR Pipeline — Authorize → Validate → Review → Merge / validate (push) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / lint (push) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (push) Successful in 4s
PR Pipeline — Authorize → Validate → Review → Merge / gate (push) Successful in 2s
2026-08-07 21:33:59 +00:00
root 3b6cf44a30 fix: update all Mumuni IP references from .123 to .24 (inside Abiba CT100)
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 4s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 1s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 5s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 0s
Mumuni CT114 destroyed. Mumuni now runs inside Abiba CT100 at 192.168.68.24. Updated all contract files and agent-health-check.py.
2026-07-28 08:56:45 +00:00
Abiba 15a826457e vault: canonical Production Vault Access Process + sync vault + migrate koby/koonimo
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 5s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 1s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 0s
- Vault SYNCED: mumuni/koby/koonimo rotated keys written to Infisical (all validate 200).
  Vault is source of truth again (was stale since session-13 rotations).
- Koby (.129) + Koonimo (.114) migrated from hardcoded systemd drop-ins to
  infisical-gateway.sh wrapper (live vault injection, .env fallback safety net).
  4/5 agents now vault-backed (abiba/mumuni/koby/koonimo).
- New § Production Vault Access Process: canonical 7-step pattern, migration status
  table, key rotation procedure, why-it's-non-fail rationale.
- Fixed stale notes: 'vault sync PENDING' (now synced), 'Abiba key IS master key'
  (now a proper agent key sk-sxbphLvk1OU).
- Tanko (user jerome, not systemd) documented as pending migration.
- hermes-key-enforcement: cross-ref to canonical process, drop-ins deprecated.
2026-07-16 17:51:53 +00:00
root 79d4a73895 docs: lessons learned from 2026-07-12 session
- gpu-fleet: Corrected architecture (direct GPU, no router in path).
  Updated context values (RTX 3090=256K, not 128K). Added api-key
  standardization requirement.
- gpu-self-heal: Added Lessons Learned section with 5 critical findings:
  L1: API key standardization (RTX 5070 sk-loc...5678 vs not-needed)
  L2: Fallback chain cascading failure loop detection
  L3: Verify running state, not documentation
  L4: Infisical fallback requirement (.env must have uncommented key)
  L5: Zulip event queue can silently die after ~40 reconnects
- litellm-self-heal: Updated status manual-only→deployed, cron schedule
- litellm-api-keys: Added Infisical token expiry warning + .env fallback
- hermes-config-template: Rule 3 updated with .env fallback requirement
2026-07-12 22:49:39 +00:00
root 35e864bdb7 audit: all 4 Hermes agents verified — no master key, api_key workaround applied
PR Pipeline — Authorize → Validate → Review → Merge / auth (push) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / validate (push) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / lint (push) Successful in 4s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (push) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / gate (push) Successful in 1s
Agent audit (2026-07-05):
  Tanko    CT 112: sk-CggiHWlamQyShxWC3Hx6uw  — vision+compression patched
  Mumuni   CT 114: sk-VrqCNlwUgzoNGOpikJ7nwQ  — vision patched
  Tdunna   CT 111: sk-6sbCNjz2T6lTVDBdlNHXsA  — vision+compression patched
  Baggy    CT 113: sk-krnw_zGBwvvL5b7l2t-s-A  — vision+compression patched

All 4 agents: zero master key references, dedicated LiteLLM keys,
api_key workaround applied to bypass auxiliary_client bug.
2026-07-05 23:36:00 +00:00
root 53d4290886 docs: document auxiliary_client api_key_env bug + workaround
PR Pipeline — Authorize → Validate → Review → Merge / auth (push) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / validate (push) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / lint (push) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (push) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / gate (push) Successful in 0s
_resolve_task_provider_model() in agent/auxiliary_client.py ignores
api_key_env for auxiliary tasks (vision, compression). The custom
provider path resolves it, but aux tasks take a different code path.

Workaround: set api_key directly alongside api_key_env.
Applied to Tanko (vision + compression).
2026-07-05 23:17:37 +00:00
root c8dcd8b63d fix: Tanko key regenerated, Mumuni key verified from /etc/environment
PR Pipeline — Authorize → Validate → Review → Merge / auth (push) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / validate (push) Successful in 1s
PR Pipeline — Authorize → Validate → Review → Merge / lint (push) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (push) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / gate (push) Successful in 1s
Tanko: old key sk-620a05e95a... was from docker-compose router config,
not LiteLLM key DB. Deleted + regenerated via LiteLLM API:
  sk-CggiHWlamQyShxWC3Hx6uw  (alias: tanko, budget: $100)

Mumuni: verified via pct-run 114 — key is sk-VrqCNlwUgzoNGOpikJ7nwQ
(was previously listed as sk-XY2aUfvy2... in contracts)
2026-07-05 20:18:05 +00:00
root 5c90eb8f6c rename: Koonimo→Baggy, Koby→Tdunna — match hostnames
PR Pipeline — Authorize → Validate → Review → Merge / auth (push) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / validate (push) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / lint (push) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (push) Successful in 4s
PR Pipeline — Authorize → Validate → Review → Merge / gate (push) Successful in 0s
Standardize agent names across all contracts and pct-run.sh.
No functional changes — same CT IDs, same keys, same nodes.
2026-07-05 20:04:22 +00:00
root 0db95a4d1c fix: correct IPs, CT IDs, and key status across all contracts
PR Pipeline — Authorize → Validate → Review → Merge / auth (push) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / validate (push) Failing after 2s
PR Pipeline — Authorize → Validate → Review → Merge / lint (push) Has been skipped
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (push) Has been skipped
PR Pipeline — Authorize → Validate → Review → Merge / gate (push) Has been skipped
hermes-key-enforcement.prose.md:
  - Add IP column to verified agents table
  - Fix Tanko status: was using master key via systemd drop-in (not compliant)
  - Add detection query step 2: check systemd drop-ins for master key leaks
  - Add step 3: verify running process env against dedicated key
  - Mark Mumuni, Koby, Koonimo as Unverified (last check was surface-level only)

gpu-fleet.prose.md:
  - Add CT ID column to agent table for cross-reference
  - Fix Abiba IP .24 → .65 (pi agent runs on RA-H OS host)
  - Update Abiba LiteLLM key to match actual models.json key
  - Set Koonimo IP to unknown (was .114 — incorrect per user)
  - Fix pi-specific paths .24 → .65

hermes-config-template.prose.md:
  - Set Koonimo IP to unknown

infrastructure-control.prose.md:
  - Set Koonimo IP to unknown
  - Fix Koonimo CT reference
2026-07-05 19:58:14 +00:00
root 7ce6cad01f fix: incorporate Mumuni review — recursive detection query + safe-mutate cross-reference
Test results:
- Test #1: Recursive grep finds sub-profile violations old query missed (2/2 vs 1/2)
- Test #2: safe-mutate step correctly positioned in Violation Response, YAML valid
2026-07-05 08:49:58 +00:00
root 889f4e4dd1 docs: update key enforcement — all agents named keys, systemd fix, CI pipeline
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 2s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Failing after 3s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Has been skipped
- All 4 Hermes agents now have dedicated named LiteLLM keys (tanko, mumuni, koby, koonimo)
- Documented systemd drop-in pattern fix (litellm-key.conf)
- Added one-step rotation procedure
- Added CI pipeline and branch protection documentation
- Removed old mumuni keys, generated fresh keys for koby/koonimo
2026-07-04 23:28:59 +00:00
root b669d1becf fix: remove Node.js dependency from CI pipeline + add enforcement kind
PR Pipeline — Authorize → Validate → Review → Merge / auth (push) Successful in 0s
PR Pipeline — Authorize → Validate → Review → Merge / validate (push) Successful in 0s
PR Pipeline — Authorize → Validate → Review → Merge / lint (push) Successful in 1s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (push) Successful in 1s
PR Pipeline — Authorize → Validate → Review → Merge / gate (push) Successful in 1s
- Removed actions/checkout@v4 (requires Node.js, unavailable on runner)
- Gitea act runner provides repo checkout automatically
- Added 'enforcement' to valid kind list for hermes-key-enforcement
- All steps are now pure shell — zero external dependencies
2026-07-04 22:54:42 +00:00
root ae5fb4d335 ci: verify pipeline with Node.js on runner CT 110
PR Pipeline — Authorize → Validate → Review → Merge / auth (push) Failing after 1s
PR Pipeline — Authorize → Validate → Review → Merge / validate (push) Has been skipped
PR Pipeline — Authorize → Validate → Review → Merge / lint (push) Has been skipped
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (push) Has been skipped
PR Pipeline — Authorize → Validate → Review → Merge / gate (push) Has been skipped
2026-07-04 22:53:25 +00:00
root 895858c60a feat: LiteLLM API key management contract + longevity policy
- New contract: litellm-api-keys.prose.md — create/rotate/verify named API keys
- Renamed tanko key alias from tanko-jul2026 to tanko (bare name)
- Added Key Longevity Policy: permanent keys (duration:null), event-driven rotation
- Added default_key_generate_params to litellm config (permanent + 00 budget)
- Updated hermes-key-enforcement verified agents table for 2026-07-04
2026-07-04 22:48:48 +00:00
Abiba c1bdbbc491 2026-07-03: Hermes key enforcement contract + Stirling-PDF docs + config standardization
- hermes-key-enforcement.prose.md: NEW contract enforcing api_key_env for all harness/LiteLLM providers, exempting external providers
- hermes-config-template.prose.md: Updated with full fix log (15 total fixes across Koby/Koonimo/Mumuni/Tanko), model:auto detection rule, key-to-agent mapping
- infrastructure-control.prose.md: Added Stirling-PDF service details (port 8989, credentials, API key, Swagger URL) replacing Bento-PDF
2026-07-03 18:19:41 +00:00