prose-contracts/hermes-config-template.prose.md

kind, name, description

kind	name	description
template	hermes-config-template	Standard Hermes configuration template for Syslog Solution LLC agents. Enforces shared infrastructure setup (Firecrawl, SearXNG, local models, RA-H OS MCP) while keeping agent-specific API keys and model choices. UPDATED 2026-07-16: Compression model is the stable alias `strix-moe` (NOT `ornith-1.0-35b`, which LiteLLM does not serve). All 3 GPUs verified 256K (RTX 5070 bumped 131K→256K on Jul 15). Added Rule 12 (Context-Issue Diagnostic) + Rule 13 (.env fallback enforcement) from the 2026-07-16 Mumuni root-cause investigation (WAL #1300). UPDATED 2026-07-12: GPU workload redistributed. Compression → Strix Halo. RTX 3090 context verified at 256K. Infisical .env fallback required (Rule 3/13).

Maintains

• template_version: "2.1.0"
• last_applied: timestamp
• agents_configured: ["tanko", "mumuni", "abiba", "koby", "koonimo", "kagenz0"]
• agent_keys: map (see Agent Keys section)
• infra_endpoints_verified: array

Agent Keys (LiteLLM — Current 2026-07-11)

Each agent has a unique LiteLLM API key (virtual key) generated against the LiteLLM PostgreSQL DB via POST /key/generate on CT 116. Keys are stored in the DB. The env var LITELLM_API_KEY is injected at runtime via infisical run -- wrapper (project=agents, env=production). /etc/environment and ~/.hermes/.env are NO LONGER used for agent keys — stripped and tagged # [INFISICAL] post-migration. Sub-agent profiles inherit auth from the main config — no separate keys needed.

Agent	Key Alias	Host	SSH	Sub-Agents
Tanko	tanko-*	192.168.68.122	jerome@.122	—
Mumuni	mumuni	192.168.68.123	root@.123	6 profiles ✱
Abiba	abiba-pi	192.168.68.24	local	—
Koby	koby	CT 111 (tdunna)	Zulip	—
Koonimo	koonimo	CT 113 (baggy)	Zulip	—
Kagenz0	kagenz0-*	?	Zulip	—

CT hostnames (tdunna, baggy) differ from agent identities (koby, koonimo).

✱ Mumuni sub-agents: syslog-code, syslog-devops, syslog-email, syslog-research, syslog-review, syslog-writer — all at /root/.hermes/profiles/<name>/config.yaml

Infrastructure Stack

Component	Endpoint	Purpose
Firecrawl	http://192.168.68.7:3002/	Web content extraction
SearXNG	http://storepve:8888	Privacy-respecting web search
LiteLLM	http://192.168.68.116/v1	Unified model gateway (via nginx)
LiteLLM (NetBird)	https://litellm.sysloggh.net/v1	Alternative (may have 502 issues)
RA-H OS MCP	http://192.168.68.65:3100/mcp	Knowledge graph bridge
Context7 MCP	http://localhost:8079/mcp	Documentation queries

API Key Rules

• api_key_env: LITELLM_API_KEY — Use env var for main model auth (preferred) Key is injected at runtime via infisical run -- wrapper — never in /etc/environment
• api_key: '' — Sub-agents leave empty to inherit from main config's custom_provider
• api_key: sk-... — Hardcoded key only as fallback when env var not possible
• Store LITELLM_API_KEY in Infisical vault (project=agents, env=production)
• Sub-agents NEVER get their own key — they share the host agent's key
• Restart Hermes gateway after updating vault secret (key auto-injected via wrapper)

Sub-Agent Profiles (Mumuni pattern)

Mumuni has 6 sub-agent profiles in /root/.hermes/profiles/<name>/config.yaml:

profiles/
├── syslog-code/config.yaml      # Code generation
├── syslog-devops/config.yaml     # DevOps/infrastructure
├── syslog-email/config.yaml      # Email processing
├── syslog-research/config.yaml   # Research & analysis
├── syslog-review/config.yaml     # Code review
└── syslog-writer/config.yaml     # Content writing

Sub-agent profile rules:

1. api_key must be empty — api_key: '' or omitted entirely
2. base_url must be empty — inherits from main config's custom_provider
3. provider is auto or harness — routes through the shared LiteLLM gateway
4. model is agent-specific — each sub-agent can have its own default model
5. Auxiliary tasks (vision, compression, etc.) also leave api_key empty
6. Never hardcode a key in sub-agent profiles

This ensures all 6 sub-agents use the same LiteLLM key injected via infisical run -- wrapper. When the key is rotated, only the env var needs updating — all 7 configs (main + 6 subs) work immediately after restart.

Template — Required Sections

# ─── Model Selection ───
model:
  default: <agent_model>          # e.g., strix-moe, qwen3.6-27B-code, syslog-auto
  provider: harness
  base_url: http://192.168.68.116/v1
  api_key_env: LITELLM_API_KEY    # Injected via infisical run -- wrapper
  max_tokens: 4096                # ⚠️ CRITICAL: Prevents unbounded generation
  context_length: 262144          # For syslog-auto (all GPUs support 256K).
                                  # Set 131072 if using gemma-4-12b directly (12GB VRAM constraint).

fallback_providers:
  provider: deepseek
  model: deepseek-chat
  api_key_env: DEEPSEEK_API_KEY

# ─── Web Stack (SHARED INFRA — DO NOT CHANGE) ───
web:
  backend: firecrawl
  search_backend: searxng
  extract_backend: firecrawl
  firecrawl:
    base_url: http://192.168.68.7:3002/

# ─── MCP Servers (SHARED INFRA) ───
mcp_servers:
  context7:
    connect_timeout: 60
    timeout: 300
    url: http://localhost:8079/mcp
  ra-h-os:
    url: http://192.168.68.65:3100/mcp
    timeout: 120
    connect_timeout: 60

# ─── Compression ───
compression:
  enabled: true
  model: strix-moe               # ⚠️ Must match auxiliary.compression.model. Stable alias (gpu-fleet § Stable Role-Based Aliases). NOT ornith-1.0-35b (LiteLLM does not serve that name).
  provider: harness
  max_context_window: 262144      # MUST match actual GPU capacity. All 3 GPUs are 256K (Jul 15).
  threshold: 0.65                 # Fires at ~170K for 262K window, ~85K for 128K
  target_ratio: 0.30
  protect_last_n: 40
  hygiene_hard_message_limit: 350
  protect_first_n: 3
  abort_on_summary_failure: false

# ─── Auxiliary Tasks (CONSISTENCY RULE) ───
# All auxiliary services MUST use identical model, base_url, and api_key_env:
#   model: gpu-light                 # stable alias (NOT raw "gemma-4-12b")
#   base_url: http://192.168.68.116/v1
#   api_key_env: LITELLM_API_KEY
# Do NOT use syslog-auto for auxiliary tasks — it routes to the primary GPU.
# gpu-light = RTX 5070 (12B), freeing the Strix Halo for agent reasoning.
# Heavy aux (delegation, x_search) use gpu-dense (RTX 3090) instead.
# NEVER use raw model names (gemma-4-12b, qwen3.6-27B-code, qwen3.6-35B-udq4)
# in agent configs — use the stable aliases so model swaps don't break agents.
auxiliary:
  vision:
    provider: harness
    model: gpu-light            # stable alias for RTX 5070 (was raw gemma-4-12b)
    base_url: http://192.168.68.116/v1
    api_key_env: LITELLM_API_KEY
    timeout: 60
    download_timeout: 30
  web_extract:
    provider: harness
    model: gpu-light            # stable alias for RTX 5070
    base_url: http://192.168.68.116/v1
    api_key_env: LITELLM_API_KEY
    timeout: 30
  compression:
    provider: harness
    model: strix-moe              # MUST match compression.model above. Stable alias for Strix Halo.
    base_url: http://192.168.68.116/v1   # Rule 5: /v1 NOT /litellm/v1
    api_key_env: LITELLM_API_KEY
    timeout: 300                 # gpu-fleet: 300s for large-history summarization (was 60)

# ─── Delegation / Heavy Aux (use gpu-dense = RTX 3090) ───
# delegation.model and x_search.model use gpu-dense (NOT raw qwen3.6-27B-code).

delegation:
  model: gpu-dense              # stable alias for RTX 3090 (was raw qwen3.6-27B-code)
  provider: harness
  base_url: http://192.168.68.116/v1
  api_key_env: LITELLM_API_KEY

# ─── Custom Provider ───
custom_providers:
  - name: harness
    model: syslog-auto            # weighted pool (default)
    base_url: http://192.168.68.116/v1
    api_key_env: LITELLM_API_KEY
    api_mode: chat_completions

Key Update Procedure

When LiteLLM keys are regenerated (e.g., after infrastructure changes):

1. If SSH available: Update Infisical vault: infisical secrets set LITELLM_API_KEY=sk-<NEW> --project=agents --env=production, then ssh <host> "systemctl restart hermes-gateway"
2. If SSH unavailable: Send Zulip DM via abiba-bot with update command
3. After update: Restart Hermes on the agent host
4. Verify: curl -H "Authorization: Bearer sk-<KEY>" http://192.168.68.116/v1/models

Configuration Rules

Rule 1: Shared Infra Is Locked

The following MUST be identical across ALL profiles:

• web.backend, web.search_backend, web.extract_backend
• web.firecrawl.base_url
• mcp_servers.ra-h-os.url
• custom_providers[0].base_url

Rule 2: Model Choice Is Free

• model.default — per agent
• fallback_providers.model — per agent
• custom_providers[0].model — per agent

Rule 3: API Keys via Environment

• Prefer api_key_env: LITELLM_API_KEY over hardcoded keys
• Hardcoded keys in config.yaml become stale after key rotation
• Infisical vault secrets persist across config updates / reinstalls
• NEW (July 2026): Always keep a local .env fallback. Infisical service tokens can expire/404 (tanko incident: token not found, gateway ran without key for hours). The .env file should have the key uncommented as a fallback:

  LITELLM_API_KEY=sk-...
  # [INFISICAL] Also sourced from vault.sysloggh.net
  

• Restart Hermes after env var updates

Rule 4: Sub-Agent Profiles Inherit Auth

• Sub-agent profiles (/root/.hermes/profiles/*/config.yaml) must have:
  • api_key: '' — inherit from main config's custom_provider
  • base_url: '' — inherit from main config
  • Auxiliary tasks: api_key: '', provider: harness
• Never hardcode a key in sub-agent profiles
• When main config uses api_key_env, sub-agents automatically use it
• This means key rotation only touches ONE vault secret (LITELLM_API_KEY)

Rule 5: Main Config Base URL

|- Use direct IP: http://192.168.68.116/v1 |- NOT the NetBird URL (litellm.sysloggh.net) — can cause 502 when NetBird is down |- NOT the old path (/litellm/v1) — nginx now routes /v1 directly

Rule 6: max_tokens Is Required (Thermal Safety)

• Every Hermes config MUST set model.max_tokens: 4096 — this is non-negotiable
• Prevents unbounded generation that caused the July 2 Strix Halo GPU thermal incident
• The value flows through: config → agent.max_tokens → transport build_kwargs → API max_tokens
• Even though the server now has -n 8192 hard cap (set by Abiba), the client cap is the first line of defense
• Apply to BOTH main config AND all sub-agent profiles
• For agents needing longer outputs: raise to 8192, but never omit

Rule 7: Auxiliary Model Consistency (UPDATED 2026-07-16)

• Vision and web_extract use gemma-4-12b (RTX 5070 — 12GB, vision-optimized)
• Compression uses strix-moe (stable alias for Strix Halo — 64GB, 256K ctx, compression-optimized)
• strix-moe is the only valid compression model name — LiteLLM does NOT serve ornith-1.0-35b (it serves strix-moe, qwen3.6-35B-udq4, gpu-dense, gpu-light, syslog-auto, gemma-4-12b, qwen3.6-27B-code). Old configs with ornith-1.0-35b cause 403/model-not-found on compression calls.
• All auxiliary services MUST use identical routing:
  • base_url: http://192.168.68.116/v1 (Rule 5: /v1, NOT /litellm/v1)
  • api_key_env: LITELLM_API_KEY
• Do NOT use syslog-auto for auxiliary tasks — it routes unpredictably
• Compression on Strix Halo: The strix-moe alias routes to Strix Halo (64GB UMA, 256K context) — the designated compression GPU. This frees the RTX 5070 for vision and web search, and the RTX 3090 for heavy reasoning.
• The compression: block's model MUST match auxiliary: compression: model
• The compression: max_context_window: 262144 MUST match Strix Halo's actual capacity

Rule 8: GPU Workload Distribution (UPDATED 2026-07-16)

• RTX 3090 (24GB, 256K ctx, qwen3.6-27B-code): Heavy reasoning, code gen, long conversations
• RTX 5070 (12GB, 256K ctx, gemma-4-12b): Vision, web search, quick tasks, web_extract (bumped 131K→256K Jul 15; IQ4_NL+MTP, 88% VRAM)
• Strix Halo (64GB, 256K ctx, strix-moe): Context compression, summarization, long docs
• Agent profiles MUST route auxiliary tasks to the correct GPU:
  • auxiliary.vision.model: gemma-4-12b (RTX 5070)
  • auxiliary.web_extract.model: gemma-4-12b (RTX 5070)
  • auxiliary.compression.model: strix-moe (Strix Halo)
• Default model (model.default) and custom_provider remain syslog-auto for auto-routing
• For 262K context window: threshold: 0.65 (fires at ~170K tokens)
• Do NOT use threshold: 0.25 — this fires at 65K, causing premature context loss
• Do NOT use threshold: 0.80 — this delays until 209K, risking the gateway hygiene layer
• max_context_window: 262144 MUST match the model's actual capacity
• See devops-hermes-compression skill for full reference

Rule 9: Compression Threshold for 256K Models

• For 262K context window: threshold: 0.65 (fires at ~170K tokens)
• Do NOT use threshold: 0.25 — this fires at 65K, causing premature context loss
• Do NOT use threshold: 0.80 — this delays until 209K, risking the gateway hygiene layer
• max_context_window: 262144 MUST match the model's actual capacity (Strix Halo = 256K)
• See devops-hermes-compression skill for full reference

Rule 10: Default Model Must Be syslog-auto (All Agents)

• Hermes agents: model.default: syslog-auto, custom_providers[0].model: syslog-auto
• pi agents: defaultModel: syslog-auto in settings.json, first model in models.json
• syslog-auto is the LiteLLM routing model — it load-balances between strix-moe and qwen3.6-27B-code, with gemma-4-12b as fallback. Using it protects against:
  • Model name typos that cause 403 errors and silent worker failures
  • Single GPU downtime (routing falls back automatically)
  • Key/model authorization mismatches
• Exception: Sub-agent profiles (Mumuni's 6 profiles) may specify explicit models for specialized tasks, but MUST validate those models exist in the key's authorized list

Rule 11: Validate Model IDs Before Deployment (pi Agents)

• After configuring a pi agent's models.json, verify every model ID:

  curl -s http://192.168.68.116:4000/v1/models \
    -H "Authorization: Bearer <AGENT_KEY>" | jq '.data[].id'
  

• All model IDs in models.json MUST appear in the LiteLLM response
• The agent's API key may have a SUBSET of the full model catalog — check per-key
• A non-existent model ID causes 403 errors that silently break the pi RPC worker (no agent_end emitted, worker stays "busy", Zulip messages pile up unprocessed)

Rule 12: Context-Issue Diagnostic Checklist (ADDED 2026-07-16, WAL #1300)

When an agent shows "context issues" (premature compression, 401s, 504s, DeepSeek fallback), verify ALL FOUR of these against the live config. They are the only root causes found in production:

1. max_context_window correct? — BOTH compression.max_context_window AND context.max_context_window MUST be 262144 (all GPUs are 256K). A value of 131072 causes premature compression at ~83K instead of ~170K. Check: grep -n max_context_window ~/.hermes/config.yaml
2. base_url uses /v1 NOT /litellm/v1? — custom_providers[0].base_url, delegation.base_url, and ALL auxiliary.*.base_url MUST be http://192.168.68.116/v1 (Rule 5). nginx /litellm/ has a 60s default timeout → 504 on any inference >60s; /v1/ has 600s. Check: grep -n 'litellm/v1' ~/.hermes/config.yaml (must return NOTHING)
3. LITELLM_API_KEY valid? — The key must be a real LiteLLM key (sk- + 64 hex, 67 chars). Malformed values (e.g. sk-_SWAl_Vu_…, 47 chars) return 401 → DeepSeek fallback. Verify: curl -s -o /dev/null -w '%{http_code}' -H "Authorization: Bearer $LITELLM_API_KEY" http://192.168.68.116/v1/models (must be 200)
4. custom_providers aligned? — model: syslog-auto (Rule 10), api_mode: chat_completions (NOT responses). A wrong api_mode causes silent request failures.

One-line agent health check (run on the agent host):

PID=$(pgrep -f "python -m hermes_cli.main gateway run" | head -1)
cat /proc/$PID/environ | tr '\0' '\n' | grep ^LITELLM_API_KEY= | sed 's/=.*/<set>/'
curl -s -o /dev/null -w 'key_health: %{http_code}\n' -H "Authorization: Bearer $(cat /proc/$PID/environ | tr '\0' '\n' | grep ^LITELLM_API_KEY= | cut -d= -f2)" http://192.168.68.116/v1/models

Rule 13: API Key Injection — Two Patterns (UPDATED 2026-07-16, WAL #1300)

Agents inject LITELLM_API_KEY via ONE of two mechanisms. Both are valid; the contract requirement is that the key is a valid LiteLLM virtual key (HTTP 200 on /v1/models).

Pattern A — systemd drop-in (Koby, Koonimo, and any agent without infisical wrapper): A systemd drop-in /etc/systemd/system/hermes-gateway.service.d/litellm-key.conf sets the key:

[Service]
Environment="LITELLM_API_KEY=sk-<VALID_KEY>"

The service unit hermes-gateway.service runs python -m hermes_cli.main gateway run --replace directly (no infisical). Apply with systemctl daemon-reload && systemctl restart hermes-gateway.

• Koonimo (CT113/.114): service = hermes-gateway.service, drop-in has the key.
• Koby (CT111/.129): service = hermes-gateway.service (created 2026-07-16), ExecStart uses --replace to win the lock against stray hermes gateway restart invocations. Key also in /etc/environment.

Pattern B — infisical-gateway.sh wrapper (Mumuni): The wrapper sources ~/.hermes/.env then exports LITELLM_API_KEY="$<AGENT>_LITELLM_API_KEY". See litellm-api-keys.prose.md § Machine Identity for Vault Writes for vault sync.

Verification (all agents):

GP=$(pgrep -f "python -m hermes_cli.main gateway run" | head -1)
K=$(cat /proc/$GP/environ | tr '\0' '\n' | grep '^LITELLM_API_KEY=' | cut -d= -f2)
curl -s -o /dev/null -w '%{http_code}' -H "Authorization: Bearer $K" http://192.168.68.116/v1/models  # must be 200

• /etc/environment is NO LONGER the canonical key source (stale values there caused 401s).
• Do NOT leave a hardcoded stale key in /etc/environment — it shadows the drop-in/wrapper.

Execution

1. Check current config — Read the target agent's config.yaml
2. Compare against template — Identify missing or divergent sections
3. Apply shared infra — Lock web/MCP/compression sections to template values
4. Apply agent key — Set from agent_keys table above
5. Set model choice — Per agent's workload
6. Verify — curl all shared endpoints, test the model with the new key
7. Report — What was changed, preserved, custom