29 Commits

Include renames

Author	SHA1	Message	Date
root	88e9243ce4	fix(alignment): clarify tanko's live LiteLLM proxy status in health-check description	2026-09-28 12:38:42 +00:00
root	9a789ab76d	fix(hermes): separate policy observations from fault findings ... 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 ... 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	bd0065bb31	no-mistakes(review): Fix monitor-key scope, Strix context, retired delegation names	2026-09-12 22:02:58 +00:00
root	8210fd905c	fix: align contracts to 4-name LiteLLM registry (2026-09-12) ... - 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	de1428b4ae	no-mistakes(review): Harden GC gate key aliases, fail closed, fix baseline	2026-09-12 18:42:36 +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
agent-zero	c26255f5ff	fix(router): decommission legacy GPU router across contracts and fleet scripts ... Router container, image, and config are purged on CT 116 (verified: no container, no image, inference-harness-router:latest removed, :9000 free, 11 containers healthy, 7 models, live syslog-auto completion OK). Updates: - gpu-fleet.prose.md: topology diagram rebuilt without the router tier - gpu-monitor / gpu-self-heal / litellm-health / litellm-self-heal: router steps dropped - infrastructure-control.prose.md: container inventory + litellm row corrected - scripts/daily-infra-report.py, scripts/prose-ai-review.sh: host-scoped checks Verified: 40/40 anchors matched uniquely, 0 U+FFFD across changed files, daily-infra-report.py compiles, no stray harness-router references remain.	2026-09-11 14:20:18 -04:00
root	2dfc3e1530	Merged PR #50: fix/gpu-dense-docs	2026-08-30 12:16:39 +00:00
root	79af0ae7a3	Merged PR #52: fix/tanko-runtime	2026-08-30 12:16:28 +00:00
mumuni-bot	e898048baf	fix: repoint Mumuni refs from CT100/.24 to kagentz CT105/.14 post-migration ... 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 ... - 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
kagentz-bot	44f7008302	docs: reflect hwepve removal from Tabiri cluster (5 nodes + standalone London node) ... - Remove hwepve from cluster member lists/diagrams in infrastructure-control, proxmox-monitor, infrastructure-update, litellm-health, mumuni-delegation - CTs 100 (abiba) and 105 (kagentz) moved to minipve; CT 114 (mumuni) no longer exists (Mumuni runs inside Abiba CT 100) - Add standalone London role + NetBird routing peer description for hwepve - Update scripts: agent-health-check.py, pct-run.sh, prose-ai-review.sh - Update disk-gc CT access table, hermes baselines/restore host references	2026-08-15 20:03:02 -04:00
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	2ace79fcab	no-mistakes(document): Update 5→6 node references and fix CT ID contradictions	2026-07-24 21:36:38 +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	1c44bf1259	contract updates: ornith decommissioned, 256K→128K context, Mumuni Discord disabled ... Change 1: Strix Halo — ornith decommissioned - gpu-fleet: Genesis Hermes V3 APEX → qwen3.6-35B-udq4 throughout - inference-optimization: ornith→strix-moe/qwen3.6-35B-udq4 - gpu-monitor: ornith status → Strix Halo status - infrastructure-control: Strix Halo — ornith → qwen3.6-35B-udq4 - infrastructure-update: ornith→strix-moe via router - proxmox-monitor: Strix Halo LLM (ornith) → (qwen3.6-35B-udq4, strix-moe) Change 2: GPU context 256K→128K fleet-wide - hermes-agent-baseline: frontmatter description updated - litellm-health: GPU Fleet Topology table 256K→128K - litellm-self-heal: GPU Fleet Topology, engine flags, VRAM alert - inference-optimization: compress threshold 256K→128K compact at 85K - gpu-fleet: instability note updated Change 3: Mumuni Discord platform disabled - gpu-fleet: Mumuni platforms: removed discord	2026-07-23 09:00:42 +00:00
root	9f0e04f22c	fix: update contracts for hwepve 6th node + Mumuni migration (lxc/114 on hwepve) ... - proxmox-monitor: 5→6 nodes, add hwepve (.4, Huawei Matebook 16), note Mumuni (lxc/114) placement - zulip-health: add dual-gateway collision detection to B2, note Mumuni on hwepve - hermes-agent-baseline: fix Mumuni node minipve→hwepve - hermes-zulip-restore: add hwepve Proxmox column for Mumuni - mumuni-delegation: fix CT 118/storepve/.6 → lxc/114/hwepve/.123, 5→6 nodes - pm2-self-heal: verified — no Mumuni references, no changes needed Post-migration discoveries: - Mumuni container migrated from minipve to hwepve (6th node, 192.168.68.4) - IP preserved (192.168.68.123), hostname 'mumuni' unchanged - Dual gateway collision (PID 1442 --replace + PID 2924 --force) resolved by container restart at 10:07; gateway restarted clean at 13:06 with fresh Zulip queue (errors=0, reconnects=0)	2026-07-20 17:08:58 +00:00
root	17a77e6b3f	fix: fleet config issues from 2026-07-18 relay review ... - hermes-agent-baseline: add gpu-dense and gpu-light to models list - hermes-config-template: fix pgrep traps (exclude infisical wrapper) + add vault empty-key guard documentation in Rule 13 - litellm-api-keys: fix pgrep pattern in auditable check - scripts/agent-health-check: fix pgrep to exclude infisical bash wrapper Addresses issues found during relay inbox resolution session: 1. pgrep -f 'hermes_cli.main gateway run' matches both the real python gateway and the infisical bash wrapper, causing false health readings 2. infisical vault stores empty key silently — no guard/monitoring 3. gpu-dense/gpu-light stable aliases missing from baseline config	2026-07-18 17:39:46 +00:00
root	8215b84f88	merge: resolve conflicts with master (delegation delete + gpu-fleet)	2026-07-16 21:22:34 +00:00
root	b7e23e2592	vault: Infisical cleanup + contract sync (WAL #1316) ... - litellm-api-keys: vault audit, tanko/koby/koonimo migration, key rotation log - gpu-fleet: ornith-1.0-35b→strix-moe (remaining refs) - hermes-agent-baseline: 256K all GPUs, CT IPs updated, Shumba retired - delegation-prose-contract: removed (renamed to mumuni-delegation) - contract-registry.yaml + cron-prompts-review.md: from feat/contract-registry	2026-07-16 21:17:09 +00:00
Abiba	dc572889f8	contracts: sync to ground truth — ornith-1.0-35b→strix-moe, 256K all GPUs, real LiteLLM timeouts ... Verified on ground 2026-07-16 against CT 116 litellm_config.yaml + GPU hosts: - AMD host serves qwen3.6-35B-udq4 (LiteLLM alias strix-moe); ornith-1.0-35b does NOT exist - All 3 GPUs at 256K ctx, parallel 2 (RTX 3090 was listed 128K/parallel 1) - LiteLLM timeouts: qwen 300s, gemma 120s, strix 300s (were stale 90s/120s) - Added LiteLLM model surface + key scoping to litellm-self-heal - Patched health-check script path ref Files: litellm-self-heal, litellm-health, gpu-fleet, gpu-self-heal, zulip-adapter-lessons, abiba-zulip-restore, hermes-agent-baseline, delegation-prose-contract, mumuni-delegation-prose-contract	2026-07-16 17:02:44 +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	776df418ca	gpu-fleet: July 8 optimization sweep — parallel 2 fleet-wide, 128K ctx on NVIDIA, LiteLLM timeout fixes ... - All GPUs: --parallel 1 → 2 (6 concurrent slots, was 3) - .8 RTX 3090: ctx 256K→128K, VRAM 96%→83%, turbo4 KV cache - .110 RTX 5070: ctx 256K→128K, ubatch 4096→512 (was inverted), VRAM 90%→77%, q4_0 KV - .15 Strix Halo: parallel 1→2, 256K ctx (41GB free), q8_0 KV, AMD metrics via /sys/class/drm - LiteLLM: gemma timeout 25→120s, qwen timeout 40→90s, syslog-auto (qwen) 40→90s - Agent configs: context_length 262144 for syslog-auto, 131072 for direct qwen/gemma - Updated health-check operation, agent config implications, benchmark table (fixed model↔GPU mapping)	2026-07-08 17:25:42 +00:00
jerome	f6e8791352	fix(ci): change kind from reference to template in hermes-agent-baseline.prose.md ... The validate job was failing because 'reference' is not an allowed kind. Changed to 'template' since this document serves as a canonical baseline template for restoring agent configurations.	2026-07-07 20:57:48 -04:00
root	5aa93117de	docs: capture all session changes — port conflict, health check, streaming ... Updated contracts to reflect all infrastructure changes made 2026-07-05/06: gpu-fleet.prose.md: - Port conflict detection on all 3 GPU wrappers - Ghost process root cause documented (.8 stale pid 25836) infrastructure-control.prose.md: - Section 7: Agent Health Check (consolidated, non-disruptive) - Disabled scripts documented (zulip-watchdog, zulip-monitor) hermes-agent-baseline.prose.md: - Health verification section + GPU port conflict detection - Change log updated zulip-health.prose.md: - Streaming support section (edit_message + PATCH API)	2026-07-06 02:46:41 +00:00
root	2ea9cac23a	docs: hermes-agent-baseline — canonical good-state reference ... Single source of truth for all 4 Hermes agents. Captures: - Agent map (CT, IP, key, alias) - Key architecture and config patterns - Mandatory api_key workaround with explanation - Known bug: auxiliary_client ignores api_key_env - Audit procedure (full audit, leak check, key verification) - Systemd patterns - Attachment cache locations	2026-07-05 23:37:56 +00:00