# hermes/gateway.yaml — the covert-gpt LiteLLM gateway, as a Hermes custom
# provider. Merged into ~/.hermes/config.yaml by hermes/install.sh.
#
# NO SECRETS, EVER: the key is referenced by NAME via `key_env: LITELLM_KEY`,
# never by value. mcp-config/sync.sh exports LITELLM_KEY into every interactive
# shell from ~/.config/mcp-sync/key (0600), and Hermes — launched from such a
# shell — resolves it at runtime. So this file is safe in a PUBLIC repo, and
# `hermes/install.sh` has no key to prompt for. Run mcp-config/install.sh first;
# without it LITELLM_KEY is unset and Hermes falls back to "no-key-required",
# which the gateway rejects with a 401.
#
# WHY a custom provider instead of `model.provider: openrouter` + a base_url:
# that older shape pointed Hermes at the gateway by pretending it WAS OpenRouter
# (OPENROUTER_API_KEY held the LiteLLM key, OPENROUTER_BASE_URL held the gateway
# URL). Requests reached the gateway, but the MODEL PICKER did not: Hermes'
# fetch_openrouter_models hardcodes openrouter.ai/api/v1/models and ignores
# OPENROUTER_BASE_URL, so the picker listed OpenRouter's ~342-model catalog —
# models this gateway cannot serve — while the gateway's own models never
# appeared. A named custom provider probes THIS base_url instead.
#
# NOTE ON COMMENTS: Hermes rewrites ~/.hermes/config.yaml itself (save_config)
# and does not preserve comments, so none of this survives into the deployed
# file. That is exactly why the reasoning lives HERE, in the repo, rather than
# inline in the generated config.
custom_providers:
  - name: covert-gpt
    base_url: https://llm.covert-gpt.com/v1
    key_env: LITELLM_KEY
    api_mode: chat_completions
    # `discover_models` is deliberately left at its default (true): with a key
    # present Hermes probes the gateway's /v1/models and REPLACES the picker's
    # list with the live catalog, so new gateway models show up with no edit
    # here. The `models:` map below is NOT the picker list — it exists purely to
    # carry per-model context_length overrides, which are read from config
    # independently of discovery.
    models:
      # NO LONGER HAND-MAINTAINED. mcp-config/sync.sh renders this map from the
      # gateway's /v1/model/info on every sync (_mcp_sync_hermes_models), so the
      # single source of truth is `model_info.max_input_tokens` in ai-k8s-iac's
      # charts/inference/values.yaml. Fix a wrong window THERE, not here: an
      # edit to these entries is overwritten by the next sync.
      #
      # What follows is only a first-boot seed, so a brand-new box has sane
      # limits before its first sync. Anything you add that the gateway does
      # not serve is left alone — the renderer only touches fields it set.
      #
      # Unlike opencode, Hermes needs NO safety margin here. opencode reserves
      # `limit.output` and targets an input of exactly context - output, landing
      # one token over the window (a hard 400); Hermes omits max_tokens entirely
      # unless model.max_tokens is set, so vLLM just bounds output by whatever
      # context remains. Do NOT add model.max_tokens to work around anything: it
      # is GLOBAL, would apply to every provider (including Anthropic), and only
      # shrinks the effective input budget Hermes compacts against.
      # CORRECTED 2026-09-11. This map had drifted badly and the drift was
      # not visible from inside Hermes: it listed `qwen3-vl-30b-a3b` at
      # 262144, a model the gateway stopped serving when Ornith replaced it,
      # while Ornith — the model actually on cg-1, and a SMALLER window at
      # 196608 — had no entry at all. A model with no entry gets whatever
      # default Hermes carries, so the one model on this gateway that needs a
      # lower ceiling than its neighbours was the one model not declaring one.
      # That is the right shape to produce exactly the reported symptom: fine
      # on short turns, hard 400 once a task grows.
      ornith-1.0-35b: # cg-1 — reasoning + tool calling, multimodal
        # 196608, NOT 262144. Lower than the others on purpose — see
        # vllm.nodes[cg1] --max-model-len.
        context_length: 196608
        supports_vision: true
      qwen3.8-27b: # cg-2 — general, NVFP4
        context_length: 262144
      qwen3-coder-next: # cg-2 — agentic coder
        # Shares cg-2 with qwen3.8-27b; only one is enabled at a time, so at
        # most one of these two is ever live. Both are listed because which
        # one it is changes without touching this file.
        context_length: 262144
      # Models the gateway proxies to third parties (kimi, glm, …) are
      # intentionally absent: discovery still lists them, and inventing a
      # context_length we have not verified is worse than letting Hermes probe.