Contracts: Mumuni context-fix (WAL #1300) — strix-moe, 256K all GPUs, Rule 12/13, machine-identity vault procedure

gpu-fleet.prose.md

@@ -67,7 +67,7 @@ triggers:
 │ CT 8     │  │ CT 110      │  │ CT 15     │  │ pi (.24)     │
 │ RTX 3090 │  │ RTX 5070    │  │ Strix Halo│  │ GPU Monitor  │
 │ 24GB     │  │ 12GB        │  │ 64GB UMA  │  │ :9100        │
-│ 256K ctx │  │ 131K ctx    │  │ 256K ctx  │  │ Watchdog     │
+│ 256K ctx │  │ 256K ctx    │  │ 256K ctx  │  │ Watchdog     │
 │ qwen3.6  │  │ gemma-4-12b │  │ ornith35B │  │ Prometheus   │
 │ 27B-code │  │ :8080       │  │ :8080     │  │ exporter     │
 │ :8080    │  │ :9400 (exp) │  │ :9400(exp)│  │ :9401        │
@@ -94,7 +94,7 @@ but are deprecated for agent configs. Only the stable aliases survive model swap
 | Model | GPU | Host | VRAM | Ctx | KV Cache | Parallel | Batch/Ubatch | Status |
 |-------|-----|------|------|-----|----------|----------|-------------|--------|
 | qwen3.6-27B-code (MTP) | RTX 3090 | .8 (llm-gpu) | 22.2/24.6GB (90%) | **256K** 🚀 | turbo4 | 2 | default | ✅ 63 tok/s |
-| gemma-4-12b | RTX 5070 | .110 (ocu-llm) | 10.0/12.2GB (82%) | 131K | q4_0 | 2 | 2048/1024 | ✅ healthy |
+| gemma-4-12b | RTX 5070 | .110 (ocu-llm) | 10.0/12.2GB (82%) | 256K | q4_0 | 2 | 2048/1024 | ✅ healthy |
 | qwen3.6-35B-udq4 | Strix Halo Vulkan | .15 (amdpve) | ~9GB/64GB | 256K | q8_0 | 2 | 2048/512 | ✅ healthy |
 
 ## Routing Configuration (LiteLLM — July 2026)
@@ -306,7 +306,7 @@ Mumuni (CT114, 192.168.68.123) is the primary business assistant. This profile i
 | `aux.vision.model` | `gpu-light` | Vision tasks (RTX 5070) |
 | `aux.web_extract.model` | `gpu-light` | Web extraction |
 | `delegation.model` | `gpu-dense` | Sub-agent reasoning (RTX 3090) |
-| `context.max_context_window` | 131072 (128K) | Kept at 128K to avoid compression timeout |
+| `context.max_context_window` | 262144 (256K) | Fixed 2026-07-16 (was 131072 — caused premature compression, WAL #1300) |
 | `compression.threshold` | 0.65 | Triggers at ~85K |
 | `compression.target_ratio` | 0.3 | Compresses to ~38K |
 | `compression.protect_last_n` | 40 | Preserves last 40 messages |

hermes-config-template.prose.md

@@ -5,10 +5,12 @@ description: >
   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 2026-07-12: GPU workload redistributed. Compression → Strix Halo (ornith-1.0-35b).
+  UPDATED 2026-07-16: Compression model is the stable alias `strix-moe` (NOT `ornith-1.0-35b`,
-  RTX 3090 context verified at 256K (was incorrectly documented as 128K).
+  which LiteLLM does not serve). All 3 GPUs verified 256K (RTX 5070 bumped 131K→256K on Jul 15).
-  RTX 5070 stays at 131K for vision/web. Infisical .env fallback required (Rule 3).
+  Added Rule 12 (Context-Issue Diagnostic) + Rule 13 (.env fallback enforcement) from the
-  Parallel counts corrected (RTX 3090=1, RTX 5070=2, Strix=2).
+  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
@@ -31,7 +33,7 @@ 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-jul2026` | 192.168.68.123 | root@.123 | 6 profiles ✱ |
+| 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 | — |
@@ -129,10 +131,9 @@ mcp_servers:
 # ─── Compression ───
 compression:
   enabled: true
-  model: ornith-1.0-35b           # ⚠️ Must match auxiliary.compression.model
+  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      # For Strix Halo compression (256K ctx).
+  max_context_window: 262144      # MUST match actual GPU capacity. All 3 GPUs are 256K (Jul 15).
-                                  # Set 131072 if using gemma directly.
   threshold: 0.65                 # Fires at ~170K for 262K window, ~85K for 128K
   target_ratio: 0.30
   protect_last_n: 40
@@ -164,10 +165,10 @@ auxiliary:
     timeout: 30
   compression:
     provider: harness
-    model: ornith-1.0-35b
+    model: strix-moe              # MUST match compression.model above. Stable alias for Strix Halo.
-    base_url: http://192.168.68.116/v1
+    base_url: http://192.168.68.116/v1   # Rule 5: /v1 NOT /litellm/v1
     api_key_env: LITELLM_API_KEY
-    timeout: 60
+    timeout: 300                 # gpu-fleet: 300s for large-history summarization (was 60)
 
 # ─── Custom Provider ───
 custom_providers:
@@ -236,23 +237,25 @@ The following MUST be identical across ALL profiles:
 - 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 July 2026)
+### Rule 7: Auxiliary Model Consistency (UPDATED 2026-07-16)
 - Vision and web_extract use `gemma-4-12b` (RTX 5070 — 12GB, vision-optimized)
-- Compression uses `ornith-1.0-35b` (Strix Halo — 64GB, 256K ctx, compression-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`
+  - `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 moved to Strix Halo (July 2026)**: The ornith-1.0-35b model on Strix Halo
+- **Compression on Strix Halo**: The strix-moe alias routes to Strix Halo
-  (64GB UMA, 256K context, 72.4 tok/s) is the designated compression GPU. This frees the
+  (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 (July 2026)
+### 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, 131K ctx, gemma-4-12b)**: Vision, web search, quick tasks, web_extract
+- **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, ornith-1.0-35b)**: Context compression, summarization, long docs
+- **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)
@@ -293,6 +296,48 @@ The following MUST be identical across ALL profiles:
 - 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 $LITELLM_API_KEY" http://192.168.68.116/v1/models` (must be 200)
+4. **custom_providers aligned?** — `model: syslog-auto` (Rule 10), `api_mode: chat_completions`
+   (NOT `responses`). A wrong api_mode causes silent request failures.
+
+One-line agent health check (run on the agent host):
+```bash
+PID=$(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: .env Fallback Enforcement (ADDED 2026-07-16, WAL #1300)
+- The infisical-gateway.sh wrapper MUST source `~/.hermes/.env` BEFORE exporting `LITELLM_API_KEY`,
+  so the local .env overrides a stale Infisical vault value:
+  ```bash
+  -- bash -c "
+    . /root/.hermes/.env  # [FALLBACK Rule 3/13] local .env overrides stale vault value
+    export LITELLM_API_KEY=\"\$MUMUNI_LITELLM_API_KEY\"
+    ...
+  ```
+- `~/.hermes/.env` MUST contain `MUMUNI_LITELLM_API_KEY=sk-<valid>` (or the agent's equivalent).
+- This is sanctioned by Rule 3: "Infisical service tokens can expire/404; the .env fallback prevents
+  agents from running without keys."
+- The systemd unit `hermes-gateway.service` ExecStart MUST be `/root/.hermes/infisical-gateway.sh`
+  (the wrapper), NOT `python -m hermes_cli.main gateway run` directly (direct exec breaks ALL env
+  injection → "No messaging platforms enabled").
+- To sync the Infisical vault (when write access is available): see `litellm-api-keys.prose.md`
+  § Machine Identity for Vault Writes.
+
 ## Execution
 
 1. **Check current config** — Read the target agent's config.yaml

litellm-api-keys.prose.md

@@ -51,8 +51,8 @@ description: >
    - Generate new key with key_alias: "{agent_name}" (e.g., "tanko" — bare name, no date)
    - Set metadata: { "agent": "{agent_name}", "purpose": "agent-inference" }
    - Duration is null (permanent) — inherited from litellm default_key_generate_params
-   - Set models: ["syslog-auto", "qwen3.6-27B-code", "gemma-4-12b", "ornith-1.0-35b"]
+   - Set models: ["syslog-auto", "qwen3.6-27B-code", "gemma-4-12b", "strix-moe", "gpu-dense", "gpu-light", "qwen3.6-35B-udq4"]
-   - Note: qwen3.6-35B-A3B removed from fleet (was never deployed on any GPU)
+   - Note: `ornith-1.0-35b` is NOT a valid LiteLLM model name (use `strix-moe`, the stable alias). qwen3.6-35B-A3B removed from fleet (was never deployed).
    - Return the new key
 5. **If action == "rotate"**:
    - Generate new key with same alias (LiteLLM replaces the old key)
@@ -67,3 +67,47 @@ description: >
    - Test the key against LiteLLM /v1/models
    - Confirm key alias matches agent_name in LiteLLM key list
    - Verify agent gateway uses vault wrapper: `cat /proc/<pid>/cmdline` shows `infisical run`
+
+## Machine Identity for Vault Writes (ADDED 2026-07-16, WAL #1300)
+
+**Problem:** The infisical CLI on agent hosts is logged in as a user session (jerome@sysloggh.com).
+In CLI v0.38.0, `infisical secrets set` / `infisical export` fail with "project id missing" / "workspace
+key 404" — a known bug where user-session auth works for `run` but NOT for `secrets set`. The apt
+repo only ships 0.38.0, so `apt upgrade` does not help.
+
+**Proper fix — Machine Identity (Infisical automation best practice):**
+Create a machine identity with READ+WRITE scope on the `agents` project (project_id=
+`322fceab-39da-4854-a55a-568e76c0f13f`, env `prod`). Store client_id + client_secret securely.
+Then vault writes work from any host:
+```bash
+# Get a machine-identity access token
+TOKEN=$(curl -fsSL -X POST https://vault.sysloggh.net/api/v1/auth/universal-auth/login \
+  -H 'Content-Type: application/json' \
+  -d '{"clientId":"<CLIENT_ID>","clientSecret":"<CLIENT_SECRET>"}' | jq -r .accessToken)
+# Write a secret via REST API v3
+ curl -fsSL -X PATCH https://vault.sysloggh.net/api/v3/secrets/MUMUNI_LITELLM_API_KEY \
+  -H "Authorization: Bearer $TOKEN" -H 'Content-Type: application/json' \
+  -d '{"environment":"prod","secretValue":"sk-<NEW_KEY>","workspaceId":"<WORKSPACE_ID>","type":"shared"}'
+# OR via CLI: infisical secrets set --token=$TOKEN --projectId=322fceab... --env=prod ...
+```
+Creation requires the Infisical web UI (https://vault.sysloggh.net) under Project Settings →
+Machine Identities, or an admin API call. **TODO: create `abiba-automation` machine identity
+and store its credentials in the vault itself (or a root-only file).**
+
+**Interim (working now):** the `.env` fallback (hermes-config-template Rule 3/13). The
+infisical-gateway.sh wrapper sources `~/.hermes/.env`, so its `MUMUNI_LITELLM_API_KEY` overrides
+the stale vault value. This is fully functional and contract-sanctioned — the vault sync above is
+only for consistency so .env and vault never drift.
+
+## Key Rotation Log
+
+| Date | Agent | Action | Notes |
+|------|-------|--------|-------|
+| 2026-07-16 | mumuni | rotate | Old key malformed (sk-_SWAl_Vu_, 47 chars, not LiteLLM format) → 401. Deleted old `mumuni` key (token 15cbca18…), generated fresh (alias `mumuni`, 7 models: syslog-auto, qwen3.6-27B-code, gemma-4-12b, strix-moe, gpu-dense, gpu-light, qwen3.6-35B-udq4). New key sk-OzuWsoX2… written to /root/.hermes/.env (Rule 3/13 fallback). Vault sync PENDING (needs machine identity). WAL #1300. |
+
+## LiteLLM Master Key (use sparingly — agents should NOT use it directly)
+
+- Master key: `sk-litellm-7f96080dd99b15c36bd4b333b58a6796` (in /opt/inference-harness/.env on CT116, Infisical project=infrastructure env=production secret=LITELLM_MASTER_KEY)
+- Used for /key/generate, /key/delete, /key/list (GET), DB queries
+- **Known violation:** Abiba's LITELLM_API_KEY IS the master key (should be a dedicated `abiba` virtual key). TODO: generate `abiba` virtual key and stop using master key directly.
+- LiteLLM key DB: `harness-postgres` container on CT116, table `"LiteLLM_VerificationToken"` (columns: token, key_alias, key_name, created_at, expires). Query: `docker exec harness-postgres psql -U litellm -d litellm -t -c "SELECT key_alias, substr(token,1,16) FROM \"LiteLLM_VerificationToken\" ORDER BY created_at;"`