80 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
jerome	a8354e88bc	rename: delegation-prose-contract → mumuni-delegation-prose-contract ... Contract is Mumuni-specific operating doctrine — different agents have different architectures and don't need this. Renamed file and frontmatter to reflect that.	2026-07-09 03:18:29 -04:00
jerome	98d8ce6772	fix: add topology section to satisfy lint checks ... Added cluster/node topology section referencing all 5 Proxmox nodes and clarifying that the contract is infrastructure-agnostic — defines the who and when, not the where.	2026-07-09 02:53:44 -04:00
jerome	548e421fa1	feat: add delegation-prose-contract pattern — manager operating doctrine for worker delegation ... Defines when to delegate, worker selection matrix, verification protocol, kanban board, and failure handling. Addresses the context overflow and iteration exhaustion issues where the manager was doing all work itself instead of delegating to the 6 worker profiles.	2026-07-09 02:29:42 -04:00
jerome	c0191c9edc	feat: hermes-zulip-restore contract — restore Zulip on any Hermes agent ... Deploys zulip-platform adapter to bundled plugin path, verifies env credentials, restarts gateway, and validates Zulip connection. Covers Mumuni (CT114), Tanko (CT112), Koby (CT111). Includes _strip_html slash-command fix, known failure modes, and owner-aware restart paths.	2026-07-08 03:19:01 -04:00
root	2d2259035a	Merge branch 'fix/mumuni-review-suggestions': tested changes ... - Recursive detection query catches sub-profile violations (verified) - safe-mutate cross-reference added to Violation Response (verified)	2026-07-05 08:50:02 +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	0147ac2abb	Revert "fix: incorporate Mumuni review — recursive detection query + safe-mutate cross-reference" ... This reverts commit c4ab31e56b.	2026-07-05 08:49:23 +00:00
root	c4ab31e56b	fix: incorporate Mumuni review — recursive detection query + safe-mutate cross-reference	2026-07-05 08:46:32 +00:00
root	9cf6304e23	fix: remove hardcoded LiteLLM defaults — rely on Gitea secrets	2026-07-04 23:33:34 +00:00
root	91ec7ea3d2	Merge PR #1: docs: update key enforcement — all agents named keys, systemd fix, CI pipeline	2026-07-04 23:32:19 +00:00
root	e59f59d776	fix: ai-review gracefully skips when LiteLLM secrets not configured	2026-07-04 23:30:25 +00:00
root	889f4e4dd1	docs: update key enforcement — all agents named keys, systemd fix, CI pipeline ... - 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	cd7d038f91	ci: verify branch protection — abiba-bot push should work	2026-07-04 23:15:56 +00:00
root	b3ab3a6850	fix: remove all Gitea expression syntax from ai-review script	2026-07-04 23:09:29 +00:00
root	105844cf7b	fix: ai-review script — handle Gitea env vars + push event diffs	2026-07-04 23:08:19 +00:00
root	52566ff36e	fix: remove test file, add missing descriptions to zulip-health + memory-audit-maintenance	2026-07-04 23:06:40 +00:00
root	36da6cb1f7	fix: use http://git.sysloggh.net for checkout (no TLS inside network)	2026-07-04 23:00:55 +00:00
root	3dd2698ef8	fix: add native git checkout + fix validator increment/exit bugs ... - Replaced actions/checkout@v4 with native git clone (no Node.js needed) - Fixed FAILED counter: increment instead of resetting to 1 - Fixed exit condition: -gt 0 instead of -eq 1 (caught >1 violation) - Test-violations.prose.md still present — pipeline should now catch it	2026-07-04 23:00:03 +00:00
root	89af42fa4c	test: intentional violations — should fail pipeline	2026-07-04 22:58:15 +00:00
root	b669d1becf	fix: remove Node.js dependency from CI pipeline + add enforcement kind ... - 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	2026-07-04 22:53:25 +00:00
root	d27892f7a5	ci: trigger pipeline — Node.js installed on runner CT 110	2026-07-04 22:52:37 +00:00
root	031a8253c7	fix: add push trigger for master branch to CI pipeline ... Previously the pipeline only triggered on pull_request events. Direct pushes to master bypassed all validation (auth, lint, ai-review). Now push to master also triggers the pipeline.	2026-07-04 22:50:02 +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
root	4eec96b851	docs: link authoring guide from AGENTS.md	2026-07-04 22:31:44 +00:00
root	436f583882	docs: add prose contract authoring guide (Anthropic-inspired) ... NEW: docs/AUTHORING-GUIDE.md — canonical style guide for writing contracts Patterns borrowed from Anthropic's frontend-design skill: - Ground it in the subject: verify live state before writing - Two-pass process: draft → critique → revise → ship - Restraint: one contract, one concern; cut one thing before shipping - Self-critique: would an agent trust this at 3am with 30s of context? Core rules: - Specificity over generality (lists rot, vagueness is invisible) - Live-state fields in tables, not prose (grep-able) - Descriptions answer: what, to what, why care? - Templates for function and responsibility contracts - CI enforces structure; author enforces quality Linked from AGENTS.md for agent discovery.	2026-07-04 22:31:33 +00:00
root	57605c6f16	docs: add AGENTS.md + authorization enforcement gates ... NEW: AGENTS.md — complete agent workflow documentation - Step-by-step PR workflow for all agents - Authorization matrix (who can change which contracts) - Emergency bypass procedure - Quick start commands NEW: scripts/prose-auth-check.sh — authorization enforcement - Blocks unauthorized agents from changing CRITICAL contracts - infrastructure-control, proxmox-monitor: abiba only - hermes-config-template: abiba, mumuni, tanko - zulip-health: abiba, mumuni - All scripts: abiba only - Fails CI if unauthorized changes detected UPDATED: .gitea/workflows/pr-pipeline.yaml - Added Stage 0: auth check (runs first) - Added gate job that confirms all 4 checks passed - Expanded trigger paths to include scripts/*.sh UPDATED: branch protection — now requires 4 contexts: pr-pipeline / auth, validate, lint, ai-review	2026-07-04 22:25:05 +00:00
root	263c4080f3	ci: add automated PR validation pipeline + fix regressions ... NEW: Gitea Actions CI pipeline (.gitea/workflows/pr-pipeline.yaml) - Stage 1 (validate): YAML frontmatter validation for all .prose.md files - Stage 2 (lint): Structural checks + regression detection * /grafana/ nginx route (reverted 2026-07-02) * Stale CT IDs (122→112, no 123) * Verified: .19/.122/.123 = correct bridge IPs - Stage 3 (ai-review): LiteLLM-powered diff review against ground truth - Stage 4 (auto-merge): Gate — safe to merge when all green NEW: scripts/prose-lint.sh — contract structure + regression checker NEW: scripts/prose-ai-review.sh — AI review via syslog-auto model FIXES FOUND BY LINT: - gpu-fleet.prose.md: removed /grafana/ from nginx routing diagram - gpu-fleet.prose.md: removed /grafana/ from config file description - infrastructure-control.prose.md: CT 122→112 in topology diagram - scripts/prose-lint.sh: updated to not flag .19 (verified correct IP)	2026-07-04 22:13:51 +00:00
root	dd985f0e49	pm2-self-heal: migrate alerts from Zulip to Telegram ... - abiba-zulip PM2 process decommissioned (2026-07-04) - Replace Zulip stream alerts (agent-hub > alerts-pm2) with Telegram DM - Remove stale abiba-zulip monitoring block (process no longer exists) - Retain abiba-telegram auto-restart (critical — sole communication bridge) - Token sourced from extension .env, not hardcoded	2026-07-04 22:07:35 +00:00
root	0d0215e9dd	prose: annotate infrastructure-monitoring with current deployment status ... - Core stack (Prometheus + Grafana + pve/node/docker exporters) already deployed by proxmox-monitor contract (Jul 2) - GPU exporters (.8/.110/.15) NOT yet live — gpu-exporter crash-loops, sidecars never deployed - Strike nginx /monitoring/ proxy suggestion (sub-path pattern already tried and reverted for /grafana/ per proxmox-monitor) - Add cross-reference: this contract defines target state, proxmox-monitor is the as-built	2026-07-04 21:55:43 +00:00
jerome	0a3b62a598	hermes-config-template: update to v2.1.0 — max_tokens, auxiliary consistency, compression threshold ... - Add model.max_tokens: 4096 (thermal safety — Rule 6) - Add context_length: 262144 to template - Add Rule 7: Auxiliary model consistency (gemma-4-12b + base_url + api_key_env) - Add Rule 8: Compression threshold for 256K models (0.65, not 0.25) - Fix compression section: threshold 0.65, max_context_window 262144, protect_last_n 40 - Remove stray api_key_env from compression block (not propagated) - Update agent Keys table to show key aliases instead of redacted values - Add base_url and timeout to all auxiliary service configs - Add auxiliary: compression: section matching main compression config - Update version 2.0.0 → 2.1.0	2026-07-04 17:54:43 -04:00
root	253e19f680	prose: review, fix, and consolidate infrastructure contracts ... - DELETE infrastructure-monitoring.prose.md (redundant — proxmox-monitor already deployed this) - FIX infrastructure-control.prose.md: remove /grafana/ nginx route (reverted Jul 2, broke gpu-fleet) - FIX infrastructure-update.prose.md: wrong CT IDs (122→112 Tanko, 123→114 Mumuni, .19→storepve Zulip) - FIX infrastructure-update.prose.md: Strix Halo :8080→router health check (firewalled to .116 only) - FIX proxmox-monitor.prose.md: stale /grafana/ URLs→:3001 (post-revert cleanup) - ADD disk-gc-threat-response.prose.md: verified run (2026-07-04, reclaimed 35.67GB from kagentz) - ADD infrastructure-update.prose.md, pi-approval-architecture.prose.md, zulip-approval-fix.prose.md, zulip-self-heal.prose.md - UPDATE hermes-config, litellm-health/self-heal, pm2-self-heal, zulip-* contracts - ADD runs/20260704-005804-51f9a9 (disk-gc-threat-response run artifacts) All contracts verified against live PVE API, nginx config, and firewall state.	2026-07-04 21:47:33 +00:00
Abiba	3077fda0b7	README: surface verify-before-mutate doctrine, field trust levels, verify-before-fix pattern ... - New 'Operating Doctrine (read first)' section with the .117 rule, safe-mutate wrapper usage, field trust taxonomy, and contract-native verify-before-fix flow - Added hermes-key-enforcement to templates table - Added stirling-pdf-agent-access to functions table - Noted VERIFY-BEFORE-USE labels on infrastructure-control	2026-07-03 20:54:42 +00:00
Abiba	d31ae0c25a	Verify-before-mutate doctrine: annotate live-state fields, fix stale Zulip IP (.117→.19) ... - Added FIELD TRUST convention to frontmatter (live-state vs policy fields) - Marked credentials/IPs with VERIFY-BEFORE-USE labels - Fixed 3 stale Zulip IP references (.117 → .19) that caused the 2026-07-03 outage - Added verify-before-mutate skill reference - See knowledge graph node #604 for post-mortem	2026-07-03 20:10:45 +00:00
Abiba	ae143d7a88	Add Stirling-PDF agent API access contract + skill. OAuth2 configured but disabled (needs license).	2026-07-03 19:10:22 +00:00
Abiba	8dfbad5415	Remove stale Bento-PDF reference from migration note	2026-07-03 18:20:08 +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
jerome	a985748994	Update hermes-config-template.prose.md ... update wrong searxng address	2026-07-03 17:59:39 +00:00
Abiba	e991fc7ea0	fix(hermes-config-template): remove stale key table, add Key Management section ... - REMOVED hardcoded Agent Keys table (keys became stale after LiteLLM downgrade). - ADDED Key Management section: verify loop, rotate + deploy procedure, key deployment rules (plaintext in /etc/environment only, api_key_env pattern), current aliases (2026-07-02 rotation). - LiteLLM DB is the single source of truth for keys; contracts never store plaintext. - Mumuni sub-agent profiles documented (6, all inherit auth from main config).	2026-07-02 20:49:14 +00:00
Abiba	57178e4647	feat(zulip-health): v3 rewrite — full OpenProse responsibility structure ... - kind: contract -> responsibility (valid kind fix) - Add Requires, Maintains (JSON schema), Strategies, Invariants, Continuity - Merge Platform A/B/C into structured Step 1-6 under Execution - Add response_pipeline, queue_healthy, agent_busy_duration diagnostics - Add restart debounce (300s) and PM2 crash-loop safety invariants - Add runtime_contract: 2 versioning	2026-07-02 20:47:17 +00:00
Abiba	b0c0331727	feat: infrastructure-control network-verification + IP-first doctrine, plus 3 supporting contracts ... - infrastructure-control: add Section 5.3 (Network Verification & Routing) with dual-path checks, NetBird ingress health, DNS drift detection, and routing regression alerts. Add Section 7 (Configuration Doctrine — IP-First) mandating LAN IPs for all configs/agents, URLs reserved for human browser access only. Also enrich access matrix (Mumuni, Koonimo, LiteLLM Admin, Grafana entries), reachability matrix, and CT 116 nginx routing + Prometheus targets. - build-zulip-plugin: fold Success Criteria into Maintains postconditions. - pi-approval-architecture: new reference doc — pi approval model vs Hermes, architectural limits, /approve and /deny stub commands. - zulip-approval-fix: new responsibility — documents the Zulip HTML/prefix bug that broke /approve and /deny, and the one-line fix applied.	2026-07-02 20:39:40 +00:00
Abiba	c1d993fe01	fix: GPU table correction + OpenProse v0.15 alignment + self-heal rules 7-9 ... - hello-world: Ensures -> Maintains (v0.15.0 rename). - zulip-mention-reliability: fold Success Criteria into Maintains postconditions. - litellm-self-heal: swap gemma/qwen GPU hosts to match actual deployment; add Strix Halo 64GB UMA detail; add Rules 7 (roster stuck), 8 (agent keys invalid/401), 9 (stale Redis active counter).	2026-07-02 20:39:17 +00:00
Abiba	dfacab12f5	docs: reorganize README — all 17 contracts listed, grouped by domain & kind ... - All 17 contracts now documented (was 7). Grouped by domain (Infra, GPU, LiteLLM, Zulip, Memory, Ops, Agent-config) and kind (responsibility/function/pattern). - Patterns split: 'Instantiable Templates' vs 'Reference Documents' for clarity. - Contract Structure section now distinguishes responsibility/function/pattern section sets (was incorrectly claiming all contracts share one structure). - Scripts table now covers all 3 scripts/ files (was missing daily-infra-report and zulip-monitor). - Functions: litellm-health, infrastructure-monitoring, hello-world. Templates: hermes-config-template. Reference: infrastructure-control, pi-approval-architecture, zulip-adapter-lessons.	2026-07-02 20:36:37 +00:00
Abiba	9101026a0d	chore: move pm2-self-heal.sh into scripts/ ... All companion scripts now live under scripts/ for a single, discoverable location.	2026-07-02 20:36:37 +00:00
Abiba	bb20637b32	fix: align contract name fields to filenames (litellm-health, infrastructure-monitoring) ... - litellm-health: 'check-litellm-health' -> 'litellm-health' - infrastructure-monitoring: 'deploy-monitoring-stack' -> 'infrastructure-monitoring' Fixes 'prose run <filename>' mismatch. No external references broken.	2026-07-02 20:35:44 +00:00
root	b15771bfd9	prose: add Strix Halo thermal safeguard (-n 8192 cap) to gpu-fleet ... Runaway request from .123 (Mumuni) decoded 39,868 tokens over 24 min, pushing Tctl to 98°C (9°C past critical) and throttling 70->29 t/s. Server-side -n 8192 hard cap now bounds generation. Documented connection source (all from .116/LiteLLM) and the thermal constraint (fanless APU).	2026-07-02 03:51:36 +00:00
root	3700b3bf46	prose: fix proxmox-monitor access to direct :3001 (revert sub-path) ... Revert the /grafana/ nginx sub-path I wrongly added — it broke the existing http://192.168.68.116:3001/d/gpu-fleet URL. Restored direct 0.0.0.0:3001 LAN access. Contract is now the source of truth: no GF_SERVER_SERVE_FROM_SUB_PATH, no nginx /grafana/ route. gpu-fleet + 3 new dashboards all at :3001.	2026-07-02 02:56:27 +00:00
root	4df2fa8329	prose: add proxmox-monitor contract (Grafana Pulse replacement) ... - New proxmox-monitor.prose.md: pve-exporter + node_exporter(5) + docker-stats-exporter - Replaces Pulse with file-provisioned Grafana dashboards (cluster/node/docker) - Documents cAdvisor/Docker-29 incompatibility + custom exporter workaround - PVE API token, access URL, config file map, operations	2026-07-02 02:50:59 +00:00
root	a07ff2d96a	prose: align all contracts with Vulkan rebuild + Koby key regen ... - gpu-fleet: Koby key updated (sk-lDTsWy7H3T...), config table (ornith service + masked services), benchmarks (prompt 209→532 tok/s), ROCm→Vulkan status - gpu-monitor: topology (sidecars :8090 removed, .15 via router), subsystem polling (router /health/unified as source of truth), execution steps, alert threshold (sidecar-unreachable downgraded from critical)	2026-07-02 00:29:10 +00:00
root	49e8d968f5	gpu-fleet: Strix Halo Vulkan rebuild + LiteLLM alignment (2026-07-01) ... - ornith now on Vulkan build 4fc4ec5, 256K ctx, ~70 tok/s - Fixed GPU_MOE_URL bug in docker-compose (.110→.15) - Added router sidecar fallback for health-checks - Updated roster context 4096→262144 + correct model_path - Documented port 8080 firewall (restricted to .116)	2026-07-02 00:01:56 +00:00