command-center/agent/models.yml

# Imported from ~/.pi/agent/models.json (pi agent settings)
# - apiKey "EMPTY" -> auth: none (keyless local endpoint)
# - thinkingLevelMap {max: xhigh} -> compat.reasoningEffortMap
providers:
  # The provider NAMES are historical (they were llama.cpp endpoints when the
  # fleet ran llama.cpp): frank-medium is vllm-radiance now, and frank-large is
  # halogen-flash-server again. Renaming is deliberately avoided because every
  # modelRoles entry in config.yml embeds the provider name, and a partial
  # rename fails at call time — the label is cosmetic, the references are not.
  # One provider per HOST:PORT, so Dankclaw's second endpoint (:7771) is a
  # separate block rather than a second model inside the :7770 one.
  "llamacpp (dankserver)":
    baseUrl: http://192.168.0.235:7770/v1
    api: openai-completions
    auth: none
    models:
      - id: frank-medium
        name: "frank-medium (dankserver)"
        # Dankserver: both Radeon AI PRO R9700 (gfx1201) serving one model —
        # mainline llama.cpp, `--split-mode layer`, on
        # ajgazin/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP at UD-Q8_K_XL with
        # the z-lab DFlash2 Q8_0 drafter. Tensor parallelism is impossible on
        # this host (the second card's chipset path has no PCIe atomic routing,
        # so it cannot dispatch an RCCL collective — and vLLM's pipeline
        # parallelism needs the same p2p primitive), which is why one process
        # layer-splits across both cards instead. Since 2026-09-16 this is the
        # box's only LLM runtime; the vllm-radiance replica pair is retired.
        contextWindow: 196608
        # The KV pool is 393216 positions over TWO slots, so one conversation
        # carries 196608 -- the house rule (see frank-large) is to declare the
        # per-conversation window, not the pool. The checkpoint's trained
        # window is 262144 and the GGUF has no rope scaling, so the top 131k
        # of a conversation extrapolates on the base rope. 32768 keeps prompt
        # + budget comfortably inside it; thinking counts against the budget.
        maxTokens: 32768
        reasoning: true
        input: [text, image]
        compat:
          # Qwen3.8's chat template accepts ONLY xhigh, medium and low for
          # reasoning_effort and RAISES on anything else — verified against this
          # endpoint on 2026-09-16: low/medium/xhigh answer 200, `high` returns
          # a 500 from the template. The harness's levels must therefore be
          # folded onto that set, exactly as the sibling frank-small entry does,
          # or any role whose level is unmapped fails on its first request
          # (subagents run at `high`).
          reasoningEffortMap:
            minimal: low
            low: low
            medium: medium
            high: xhigh
            max: xhigh

  "llamacpp (dankclaw)":
    baseUrl: http://192.168.0.143:7770/v1
    api: openai-completions
    auth: none
    models:
      - id: frank-large
        name: "frank-large (dankclaw-gpu)"
        # halogen-flash-server. The model's native window is 262,144, but this
        # deployment caps a conversation at 200,192 — exactly half of its
        # 400,384-position KV pool, so two 200k conversations are resident at
        # once. Declaring the half rather than the native window is what keeps
        # prompt + budget inside one conversation's region of the pool.
        contextWindow: 200192
        # HALOGEN_MAX_TOKENS_CAP: above this a request is a 400 rather than a
        # silent truncation, and thinking counts against the budget.
        maxTokens: 65536
        reasoning: true
        # Text only as of 2026-09-16: the vision tower moved to frank-small and
        # this server refuses image content parts.
        input: [text]
        compat:
          reasoningEffortMap:
            max: xhigh
          # Qwen3.8-Flash-Next recommended sampling. Halogen has no server-side
          # sampler defaults (a request that sends no temperature decodes
          # greedily), so this override is what makes ordinary calls sample.
          # extraBody is merged last (after compat policy) and wins.
          extraBody:
            temperature: 1.0
            top_p: 0.95
            top_k: 20
            min_p: 0.0
            presence_penalty: 0.0
            repetition_penalty: 1.0
            # Keep prior thinking blocks in the rendered prompt across turns;
            # halogen honours this key top-level (verified: 275-token prompt
            # delta with it false).
            preserve_thinking: true

  "llamacpp (dankclaw-3090)":
    baseUrl: http://192.168.0.143:7771/v1
    api: openai-completions
    auth: none
    models:
      - id: frank-small
        name: "frank-small (dankclaw-3090)"
        # Dankclaw's RTX 3090: mainline llama.cpp serving
        # HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced at Q4_K_M.
        # The MTP head ships as a separate assistant sidecar
        # (mtp-gemma-4-12B-it.gguf) loaded via --model-draft and chained
        # behind the draftless ngram-mod matcher; q8_0 KV with the model's
        # sliding-window pattern keeps each full 262144-token window cheap,
        # and the explicit CTX_SIZE=1048576 / PARALLEL=4 gives FOUR full
        # windows (measured 22.3 GiB of the 24 GiB card at load; a 5th slot
        # does not fit). The BF16 projector (with audio encoder) is loaded
        # too, so this stays multimodal (frank-medium gained vision on
        # 2026-09-17 as well; frank-large has no vision tower).
        contextWindow: 262144
        # Each slot IS the full trained window: prompt + budget must fit
        # inside it, and thinking counts against the budget.
        maxTokens: 32768
        reasoning: true
        input: [text, image]
        compat:
          # Gemma4's chat template accepts every reasoning_effort level as of
          # 2026-09-17 (all seven probed: 200), so this map is inert. Kept
          # anyway: it cost nothing, and it is the safety net if the template
          # ever gates again the way Qwen3.8's did (subagents run at `high`).
          reasoningEffortMap:
            minimal: low
            low: low
            medium: medium
            high: xhigh
            max: xhigh
          # Gemma's reference local-recipe sampling (temp 1.0 / top_p 0.95);
          # the server's own default is greedy for clients that stay silent.
          # Thinking is already retained across turns by the server's
          # --reasoning-preserve default, and the key below is accepted
          # top-level (verified 200, not a 400), so it is passed to pin the
          # behaviour at the request rather than rely on a server default.
          extraBody:
            temperature: 1.0
            top_p: 0.95
            preserve_thinking: true