Germaine Brown
98073dc636
Publish Docs Site / build (push) Failing after 5s
- mkdocs.yml with dark slate theme, nav for 12 ITPP projects - build-docs.sh aggregates docs from all project repos - .gitea/workflows/docs-publish.yml for nightly rebuild+deploy - README and CHANGELOG for the itpp-docs repo itself - docs-source/ populated from all 12 repos - site/ ready for deployment to docs.itpropartner.com
2.0 KiB
2.0 KiB
Cost Control Rollout — 2026-07-24
Trigger: $46 additional unexpected spend on top of $155.76/3-day burn. Root cause: Unlimited LiteLLM key + GPT-5.6 Terra as default gateway model with no enforced budget, session-size, or model-allowlist guardrails.
Changes Deployed
1. LiteLLM — New constrained team + key
- Team
hermes-normal-ops: $3.33 rolling daily cap + $100 rolling 30-day cap, 30 RPM, 250K TPM, max 3 parallel requests. - Key
hermes-normal-ops-daily-capped(...I3gQ): Hard $3.33/day, model-restricted to approved list only. - Allowed models:
claude-sonnet-5,deepseek-v4-pro,deepseek-v4-flash,glm-5.2,MiniMax-M3,qwen3.7-plus. - Terra/GPT-5.6/Claude-Opus-4: explicitly excluded from this key — LiteLLM returns HTTP 403.
- Legacy key
sk-...itzA: blocked (blocked=t in DB).
2. Hermes config — Default routing
- Conductor:
claude-sonnet-5(admin-ai/LiteLLM proxy). - Fallbacks:
deepseek-v4-pro→deepseek-v4-flash(admin-ai only). - Delegation/workers:
deepseek-v4-pro, fallbackdeepseek-v4-flash. - No automatic escalation to premium — failure stops, not silently upgrades.
3. Session controls
- Context length: 128k tokens hard ceiling.
- Compression: enabled at 50% fill, targets 20% ratio.
- Max turns: 50 per session (prevents unbounded tool-call marathons).
4. Rate limits (on LiteLLM key)
- 30 RPM, 250K TPM, max 3 concurrent requests.
- 429 throttle-backoff confirmed working in live logs.
Verification
- Sonnet makes calls through new key: HTTP 200.
- Terra through new key: HTTP 403 (blocked).
- Old key blocked in DB:
blocked = t. - Live gateway confirmed routing through
admin-aiathttps://admin-ai.itpropartner.com/v1/.
What's still behavioral (not enforced)
- Model compliance is enforced at the proxy key layer. Cost caps are enforced at the key+team layer. Session size is a Hermes config setting — stickiness depends on the runtime respecting it.