Alexander Whitestone
39faa6b862
fix: reconcile registry locations with fleet-routing.json, add missing agents
...
CI / test (pull_request) Failing after 52s
Review Approval Gate / verify-review (pull_request) Successful in 10s
CI / validate (pull_request) Failing after 48s
- Aligned 7 location mismatches between identity-registry.yaml and
fleet-routing.json (allegro, ezra, bezalel, bilbobagginshire,
substratum, fenrir, kimi)
- Added carnice (active, local ollama agent) to registry
- Added allegro-primus (deprecated) to registry
Audit results: 16 findings → 7 info-only (ghost agents intentionally
kept for audit trail). Zero warnings. Registry VALID.
2026-04-13 20:20:57 -04:00
Timmy (NEXUSBURN)
66c010301d
feat: fleet audit tool — deduplicate agents, one identity per machine
...
CI / test (pull_request) Failing after 38s
Review Approval Gate / verify-review (pull_request) Failing after 5s
CI / validate (pull_request) Failing after 34s
Closes #1144 . Builds a fleet audit pipeline that detects duplicate
agent identities, ghost accounts, and authorship ambiguity across
all machines.
Deliverables:
bin/fleet_audit.py — Full audit tool with four checks:
- Identity registry validation (one name per machine, unique gitea_user)
- Git authorship audit (detects ambiguous committers from branch names)
- Gitea org member audit (finds ghost accounts with zero activity)
- Cross-reference registry vs fleet-routing.json (orphan/location mismatch)
fleet/identity-registry.yaml — Canonical identity registry:
- 8 active agents (timmy, allegro, ezra, bezalel, bilbobagginshire,
fenrir, substratum, claw-code)
- 7 ghost/deprecated accounts marked inactive
- Rules: one identity per machine, unique gitea_user, required fields
tests/test_fleet_audit.py — 11 tests covering all validation rules.
Usage:
python3 bin/fleet_audit.py # full audit -> JSON
python3 bin/fleet_audit.py --identity-check # registry only
python3 bin/fleet_audit.py --git-authors # authorship only
python3 bin/fleet_audit.py --report out.json # write to file
2026-04-13 18:51:31 -04:00
Mimo Swarm (mimo-code-1146)
60af11ec2f
fix: [DEFERRED] Hermes Trismegistus — New Wizard Proposal ( closes #1146 )
...
CI / test (pull_request) Failing after 9s
CI / validate (pull_request) Failing after 13s
Review Approval Gate / verify-review (pull_request) Failing after 3s
- Added fleet/hermes-trismegistus/README.md with full proposal
- Added fleet/hermes-trismegistus/lane.md with routing definition
- Filled in acceptance criteria from issue #1146
- Status remains DEFERRED — unblock conditions documented
Automated by mimo-v2-pro swarm.
2026-04-10 16:14:13 -04:00
34862cf5e5
feat(fleet): promote Ollama to first-class provider, assign Gemma 4 across fleet
...
Deploy Nexus / deploy (push) Failing after 3s
Staging Verification Gate / verify-staging (push) Failing after 3s
- lazarus-registry.yaml: replace big_brain/RunPod with local ollama/gemma4:12b
- fleet-routing.json: assign ollama:gemma4:12b to carnice, bilbobagginshire, substratum
- intelligence/deepdive/config.yaml: local model -> gemma4:12b
2026-04-07 15:55:52 +00:00
Alexander Whitestone
37b006d3c6
feat: Fleet management ( #910 ), retry logic ( #896 ), morning report ( #897 )
...
Deploy Nexus / deploy (push) Has been cancelled
CI / validate (pull_request) Failing after 10s
- fleet/fleet.sh: cross-VPS health, status, restart, deploy
- nexus/retry_helper.py: retry decorator, dead letter queue, checkpoints
- nexus/morning_report.py: automated 0600 overnight activity report
- fleet/allegro/archived-scripts/README.md: burn script archive placeholder
Fixes #910
Fixes #896
Fixes #897
Fixes #898
2026-04-06 23:09:49 -04:00
8602dfddb6
[claude] Add canonical fleet routing table with agent verdicts ( #836 ) ( #889 )
Deploy Nexus / deploy (push) Has been cancelled
2026-04-06 18:08:32 +00:00
d00bb8cbe9
docs(allegro): Mark deploy cycle complete and add claim-deliver cycle ( #884 )
CI / validate (pull_request) Failing after 11s
2026-04-06 15:40:06 +00:00
Allegro (Burn Mode)
56d4d58cb3
infra(allegro): deploy installer and update cycle state for #845
...
CI / validate (pull_request) Failing after 13s
- Add install.sh to copy self-improvement files to ~/.hermes/
- Update allegro-cycle-state.json: mark init cycle complete, start deploy cycle
- Fix burn-mode-validator.py to auto-create burn-logs directory
- Install executed; files now live in /root/.hermes/
Refs #845 #842
2026-04-06 15:36:42 +00:00
Allegro (Burn Mode)
e4b1a197be
infra: Allegro self-improvement operational files
...
CI / validate (pull_request) Has been cancelled
Creates the foundational state-tracking and validation infrastructure
for Epic #842 (Allegro Self-Improvement).
Files added:
- allegro-wake-checklist.md — real state check on every wakeup
- allegro-lane.md — lane boundaries and empty-lane protocol
- allegro-cycle-state.json — crash recovery and multi-cycle tracking
- allegro-hands-off-registry.json — 24-hour locks on STOPPED/FINE entities
- allegro-failure-log.md — verbal reflection on failures
- allegro-handoff-template.md — validated deliverables and context handoffs
- burn-mode-validator.py — end-of-cycle scoring script (6 criteria)
Sub-issues created: #843 #844 #845 #846 #847 #848 #849 #850
2026-04-05 21:20:40 +00:00
