222 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
root	d0144d6db6	Ship: Koby external-agent ruling (fix api_key_env hygiene + docs)	2026-08-11 17:22:25 +00:00
jerome	96b0caa0b3	Merge pull request 'Ship: pm2-zulip contract fixes (captain ruling 2026-08-09)' (#44) from ship/pm2-zulip-contract-fixes into master ... Reviewed-on: #44	2026-08-10 01:10:13 +00:00
jerome	ea17f64bb4	Merge pull request 'Ship: monitoring contract fixes (2026-08-09)' (#43) from ship/monitoring-contract-fixes into master ... Reviewed-on: #43	2026-08-10 01:08:07 +00:00
root	c13a15acad	Ship: pm2-zulip contract fixes (captain ruling 2026-08-09)	2026-08-09 22:11:27 +00:00
root	68f9ebff74	Ship: monitoring contract fixes (2026-08-09)	2026-08-09 21:57:44 +00:00
root	93fb0d8e1e	feat(contracts): add MCP URL validation and verify virtual keys on LiteLLM	2026-08-07 21:33:59 +00:00
mumuni-bot	cb6efa81c3	Merge pull request 'fix(contracts): memory-fixer executes decisions to completion (v2.0.0)' (#42) from fix/memory-fixer-execution-v3 into master	2026-08-04 12:32:56 +00:00
mumuni-bot	2dc77ee7da	fix(contracts): memory-fixer executes decisions to completion ... Rewrite memory-fixer to v3 semantics: when Kwame replies to an escalation, execute the action fully - set state (archived/active), clear or rename the [REVIEW:] tag, and bump updated_at so the node exits the stale window and is not re-flagged on the next run. Bump version 1.1.0 -> 2.0.0.	2026-08-04 12:30:37 +00:00
jerome	561c4d98c9	Merge pull request 'fix: correct SearXNG endpoint from dead storepve hostname to live VM109 IP' (#40) from fix/searxng-endpoint into master ... Reviewed-on: #40	2026-08-02 16:20:49 +00:00
root	8f719ca7c7	fix(contracts): Pulse port 3001→7655 (verified), jdownloader decommissioned from docker-vm → CT 118 LXC (.20)	2026-08-01 20:28:50 +00:00
root	c243fcddc3	no-mistakes(document): docs: fix stale SearXNG endpoint in monitoring checks	2026-08-01 15:19:15 +00:00
root	50114f32c0	fix: correct SearXNG endpoint from dead storepve hostname to live VM109 IP (192.168.68.7:8888) ... storepve (192.168.68.6) has no service on :8888. SearXNG runs on VM 109 (docker-vm) at 192.168.68.7:8888 (verified HTTP 200). Aligns with every other contract reference. Missed in PR #39.	2026-08-01 14:56:45 +00:00
jerome	4dc59633b3	Merge pull request 'fix(agent-health): vault token fallback + strix-server service name' (#39) from fix/agent-health-check into master ... Reviewed-on: #39	2026-08-01 14:20:02 +00:00
root	b3193e5e1b	fix(agent-health): 14 stale-reference fixes (Mumuni CT100/.24, Koby .129, Koonimo CT113, wrapper paths)	2026-08-01 14:10:52 +00:00
root	f1490b656e	no-mistakes(document): docs: fix stale ornith refs to strix-server/strix-moe	2026-08-01 13:35:21 +00:00
root	b56501a1cf	no-mistakes(review): Guard infisical-token fallback read against OSError crashes	2026-08-01 13:27:41 +00:00
root	1921937bee	fix(agent-health): vault token fallback + strix-server service name	2026-08-01 13:24:38 +00:00
root	245a4ffbea	Merge PR #38: feat: add Level 0 auto-delete for heartbeat log orphans	2026-07-29 21:52:14 +00:00
root	7c0adefdeb	Merge PR #38: feat: add Level 0 auto-delete for heartbeat log orphans	2026-07-29 21:50:19 +00:00
root	88b8cb96a5	feat: add Level 0 auto-delete for heartbeat log orphans	2026-07-28 23:30:33 +00:00
mumuni-bot	2623e05752	Merge pull request 'docs: add gitea-logger implementation example' (#37) from fix/gitea-logger-docs into master	2026-07-28 21:23:24 +00:00
root	42a1d0bd91	docs: add gitea-logger implementation example to litellm-self-heal	2026-07-28 21:23:04 +00:00
mumuni-bot	e052a069cb	Merge pull request 'fix: redirect health check logs from knowledge graph to Gitea (hard rule)' (#36) from fix/health-logs-to-gitea into master	2026-07-28 21:21:46 +00:00
root	c9359e1808	fix: redirect health check logs from knowledge graph to Gitea (hard rule) ... Logs (LITELLM-HEALTH, GPU-SELF-HEAL, PM2) now pushed to SyslogSolution/health-logs instead of creating orphan nodes in the shared knowledge graph. - litellm-self-heal: Phase 4 now calls gitea-logger instead of kg-logger - gpu-self-heal: Reporting section updated to Gitea path - pm2-self-heal: Log step redirected to Gitea - 271 existing orphan nodes remain in graph (no delete tool available)	2026-07-28 21:20:56 +00:00
mumuni-bot	6a0af728e9	Merge pull request 'fix: update all Mumuni IP references from .123 to .24 (inside Abiba CT100)' (#35) from fix/mumuni-ip-abiba into master	2026-07-28 08:57:05 +00:00
root	3b6cf44a30	fix: update all Mumuni IP references from .123 to .24 (inside Abiba CT100) ... 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
mumuni-bot	835647e241	Merge pull request 'fix: correct quant to UD-Q3_K_XL (Q4 too large for 24GB VRAM)' (#34) from fix/gpu-dense-q3-correction into master	2026-07-27 20:26:13 +00:00
root	22b015e182	fix: correct quant to UD-Q3_K_XL (Q4 too large for 24GB VRAM)	2026-07-27 20:25:51 +00:00
mumuni-bot	29e32340a4	Merge pull request 'fix: swap gpu-dense to SmartCode-Fable-5 (ThinkingCap + Fable 5 CoT)' (#33) from fix/gpu-dense-smartcode-fable5 into master	2026-07-27 16:43:46 +00:00
root	179529de71	fix: swap gpu-dense to SmartCode-Fable-5 (ThinkingCap + Fable 5 CoT) ... gpu-dense on RTX 3090 swapped from qwen3.6-27B-code to SmartCode-Fable-5-CoT-Reasoning-QKVO-Qwen-3.6-27B-Distilled (UD-Q4_K_XL, ~17.9GB).\n\nImprovements:\n- ~50% fewer thinking tokens via ThinkingCap finetune\n- Fable 5 CoT distillation for improved coding reasoning\n- Same 27B base, fits RTX 3090 at ~73% VRAM\n- Recommended samplers: temp 0.9, top-p 0.95, top-k 60\n- Context: 128K (fleet standard)	2026-07-27 16:43:29 +00:00
mumuni-bot	fb45007ace	Merge pull request 'fix: remove mumuni from health check — now inside Abiba CT 100' (#32) from fix/update-health-check-remove-mumuni into master	2026-07-26 12:37:35 +00:00
root	0f572ff9f2	fix: remove mumuni from health check — now inside Abiba CT 100	2026-07-26 12:37:07 +00:00
mumuni-bot	3a8e7d9b3a	Merge pull request 'fix: remove CT 114 (mumuni) — destroyed, moved inside CT 100' (#31) from fix/remove-mumuni-ct114 into master	2026-07-26 12:36:31 +00:00
root	0fb54926f6	fix: remove CT 114 (mumuni) — destroyed, moved inside CT 100	2026-07-26 12:36:02 +00:00
mumuni-bot	146abf7f82	Merge pull request 'fix: agent health check v2 — CT liveness, config validation, wrapper integrity, vault emptiness' (#30) from fix/agent-health-check-v2 into master	2026-07-26 12:27:20 +00:00
root	c869e75c61	ci: trigger recheck	2026-07-26 12:24:05 +00:00
root	47aa92bee3	fix: verification protocol findings — CT 118 static IP, .110 llama-server restored ... Verification protocol run 2026-07-26: - CT 118 (jdownloader): DHCP had moved it to .131 post-reboot. Now set to static .20. - RTX 5070 (.110) llama-server: was stopped (disabled unit). Started and verified — gemma-4-12b responding through LiteLLM. - All 6 PVE nodes confirmed at correct IPs. - All 18 CTs confirmed at correct IPs on correct nodes. - All public endpoints responding (meet, chat, git, litellm, vault, auth). - Container counts verified: docker-vm 14 ctrs, CT 116 10 ctrs, VPS 5 ctrs.	2026-07-26 12:20:58 +00:00
root	de9adb13cf	fix: agent health check v2 — CT liveness, config validation, wrapper integrity, vault emptiness ... Gaps fixed: - Koby (.129) and Koonimo (.114) now have SSH hosts — no longer skipped - Agent key lookup uses correct {NAME}_LITELLM_API_KEY format - New CT liveness check via pct status on PVE nodes - New config YAML integrity check via yaml.safe_load() - New wrapper/CLI integrity check (hermes wrapper, infisical path, hermes-real) - New vault secret non-emptiness check - Ops escalation: failures produce ALERT lines for cron capture	2026-07-26 12:06:32 +00:00
root	2ace79fcab	no-mistakes(document): Update 5→6 node references and fix CT ID contradictions	2026-07-24 21:36:38 +00:00
root	87b4d67067	no-mistakes(review): Fix 5 review findings: duplicate table header, hwepve specs/Wave2 target, dangling ref, Authentik port	2026-07-24 21:31:28 +00:00
root	7d1db62a8e	no-mistakes(document): Fix stale CT placements across 5 docs matching infrastructure-control updates	2026-07-24 20:21:03 +00:00
root	9943be5e68	no-mistakes(test): Lint, shell syntax, and all 13 user-intent constraints pass on 3 changed files. One mode fix: netbird-add-domain.sh 644→755	2026-07-24 20:16:57 +00:00
root	fa26b7a579	no-mistakes(test): Fixed 7 cross-table inconsistencies: kagentz placement, mumuni placement, stale 5-node references	2026-07-24 20:14:49 +00:00
root	c380196fab	fix: address review findings ... - Remove kagentz from amdpve node table (belongs on hwepve) - Fix kagentz pct-run table: hwepve (was amdpve) - Fix mumuni pct-run table: hwepve (was minipve) - Fix Zulip recovery command: wrap in single SSH call	2026-07-24 20:11:32 +00:00
root	b17c60f997	fix: contract accuracy updates post fleet-wide reboot ... infrastructure-control.prose.md: - Add hwepve as 6th Proxmox node - Fix Gitea IP: .17 (was .110) - Fix AdGuard IP: .10 on minipve (was .102 on acerpve) - Fix Abiba placement: hwepve (was amdpve) - Fix Mumuni placement: hwepve (was minipve) - Fix Authentik port: add :9000 - Add CT 118 (jdownloader), CT 119 (infisical-vault) - Add last-verified date (2026-07-24) infrastructure-update.prose.md: - Add post-reboot CT sweep procedure - Add Zulip Docker network recovery steps - Add WireGuard tunnel verification scripts/netbird-add-domain.sh: - New script to register domains in Netbird proxy store.db	2026-07-24 20:01:43 +00:00
abiba-bot	2f0c3c1850	fix: update contracts for hwepve 6th node + Mumuni recovery	2026-07-23 18:47:17 +00:00
jerome	cedbdc465d	Merge branch 'master' into fm/mumuni-recovery-hwepve	2026-07-23 18:11:06 +00:00
abiba-bot	8b09c78efd	Merge: PR #26 conflict resolution — hwepve 6th node + qwen model ref	2026-07-23 18:10:36 +00:00
root	767ab25128	merge: resolve PR #26 conflict — keep qwen model ref + add hwepve node	2026-07-23 18:10:18 +00:00
root	cd479caeec	Fix: update compression model to syslog-auto across contract and audit (Rule 7) ... - Updated hermes-config-template.prose.md: all references to strix-moe for compression changed to syslog-auto to match operational decision on 2026-07-23 (prevents sustained Strix Halo thermal load via weighted pool). - Updated audit-hermes-config.py Rule 7 to expect syslog-auto instead of strix-moe, ensuring Abiba's next run validates against the correct baseline.	2026-07-23 18:02:56 +00:00