esh-pfi-infrastructure/stacks/litellm/conf/config.yaml

# LiteLLM gateway config — fronts the vLLM services on ana-ml2
# (10.250.50.54) and logs every request + response so they're
# inspectable in the Logs UI at http://10.250.50.70:4000/ui.
#
# Deploys to /opt/docker/conf/litellm/config.yaml (mounted read-only
# into the container at /app/config.yaml).
#
# Model-name → upstream mapping:
#   phi4-mini        → vLLM :8004  (generative chat)
#   qwen3-embedding  → vLLM :8001  (/v1/embeddings)
#   qwen3-reranker   → vLLM :8002  (/rerank)
#   *  (wildcard)    → llama-swap :9292  (the swappable generative zoo)
#
# The wildcard fronts llama-swap so its whole model zoo logs through the
# gateway without per-model registration. The vllm-reward classifier
# (:8003) is a pooling /classify endpoint with no first-class LiteLLM
# route — left direct; see README.

model_list:
  # --- Granite 4.1 8B (generative chat) — production summarizer + dreaming
  #     agent. Replaced phi4-mini 2026-06-05 (beat it on precision in brokkr's
  #     R15 P03 eval). vLLM on ana-ml2 GPU 1, official FP8, 50K ctx. Explicit
  #     entry shadows the "*" wildcard's llama-swap route for this name. Full
  #     prompt + completion captured per call. ---
  # --- granite-4.1-8b RETIRED 2026-08-12 (seat downed, GPU1 reclaimed for RP context) ---
#   - model_name: granite-4.1-8b
#     litellm_params:
#       model: hosted_vllm/granite-4.1-8b
#       api_base: http://10.250.50.54:8004/v1
#       api_key: os.environ/VLLM_API_KEY
#       temperature: 0
#     model_info:
#       mode: chat

  # alias: summarizer -> gen (repointed 2026-08-12, granite retired) (operator 2026-06-19). Duplicate-entry alias
  #   (not router_settings.model_group_alias — that's hidden from /v1/models and can be
  #   silently ignored in config per litellm #15020/#5524). Keep api_base in sync above.
  - model_name: summarizer
    litellm_params:
      model: hosted_vllm/qwen3.8-27b-uncensored
      api_base: http://10.250.50.54:8015/v1
      api_key: os.environ/VLLM_API_KEY
      temperature: 0
      extra_body:
        chat_template_kwargs:
          enable_thinking: false
    model_info:
      mode: chat

  # alias: classifier -> gen (repointed 2026-08-12, granite retired) (operator 2026-06-19). Light/fast classification
  #   + triage endpoint; same backend as summarizer. Keep api_base in sync above.
  - model_name: classifier
    litellm_params:
      model: hosted_vllm/qwen3.8-27b-uncensored
      api_base: http://10.250.50.54:8015/v1
      api_key: os.environ/VLLM_API_KEY
      temperature: 0
      extra_body:
        chat_template_kwargs:
          enable_thinking: false
    model_info:
      mode: chat

  # alias: summarizer-large -> gen / qwen3.8-27b-uncensored (operator 2026-07-05). For heavier
  #   summarization that wants the 35B-A3B heretic `gen` model instead of granite-8b. Thinking OFF
  #   (matches gen). Keep api_base (:8015) + enable_thinking in sync with the gen record below.
  - model_name: summarizer-large
    litellm_params:
      model: hosted_vllm/qwen3.8-27b-uncensored
      api_base: http://10.250.50.54:8015/v1
      api_key: os.environ/VLLM_API_KEY
      presence_penalty: 1.5
      temperature: 0.7
      top_p: 0.8
      extra_body:
        top_k: 20
        chat_template_kwargs:
          enable_thinking: false
    model_info:
      mode: chat

  # --- image-judge / qwen-image-bench — T2I quality JUDGE aliases. The dedicated
  #     Qwen-Image-Bench NVFP4 backend (ana-ml2 GPU 1, :8014) was RETIRED 2026-07-15
  #     (operator: reclaim ~30GB GPU1) after the arbo→gen hero-judge switch. Both
  #     aliases now REPOINT to the gen backend (:8015, qwen3.8-27b-uncensored,
  #     vision-intact), held at deterministic judge sampling (temp 0 / top_k 1) with
  #     enable_thinking:false (a reasoning preamble breaks json_object). Revert =
  #     `docker compose start` stacks/qwen-image-bench on ana-ml2 + repoint api_base
  #     back to :8014 + model hosted_vllm/qwen-image-bench. ---
  - model_name: qwen-image-bench
    litellm_params:
      model: hosted_vllm/qwen3.8-27b-uncensored
      api_base: http://10.250.50.54:8015/v1
      api_key: os.environ/VLLM_API_KEY
      temperature: 0
      top_p: 1.0
      extra_body:
        top_k: 1
        repetition_penalty: 1.05
        chat_template_kwargs:
          enable_thinking: false
    model_info:
      mode: chat
  - model_name: image-judge
    litellm_params:
      model: hosted_vllm/qwen3.8-27b-uncensored
      api_base: http://10.250.50.54:8015/v1
      api_key: os.environ/VLLM_API_KEY
      temperature: 0
      top_p: 1.0
      extra_body:
        top_k: 1
        repetition_penalty: 1.05
        chat_template_kwargs:
          enable_thinking: false
    model_info:
      mode: chat

  # --- Qwen3.6-35B-A3B heretic (llmfan46, uncensored, NVFP4 ModelOpt Experts-Only, VISION-INTACT)
  #     — the general / `gen` model on ana-ml2 GPU 0, at /tank/aimodels/qwen36-35b-a3b-heretic-nvfp4.
  #     Displaced AEON-27B 2026-07-08 (which had displaced qwopus3.5-122b 2026-07-05). MoE 35B-A3B
  #     (256 experts / 8 active), qwen3_5_moe GDN-hybrid, native MTP preserved but served MTP-OFF
  #     (spec-decode hurts concurrent aggregate). Served on :8015 via vLLM,
  #     served-name qwen3.8-27b-uncensored. Thinking split = chat_template_kwargs.enable_thinking +
  #     --reasoning-parser qwen3; tool-calling qwen3_coder. gen / gen-reasoning + summarizer-
  #     large route here; -reasoning enables thinking. Keep api_base (:8015) in sync.
  #     RETIRED with the displacement (→ 404, callers migrate to gen): qwen3.5-122-a10b
  #     [-reasoning] + qwen-large[-reasoning] — they named a 122B that no longer exists;
  #     aliasing a 27B under those is the naming footgun the qwen36-vl stack warns against.
  #     presence_penalty: 1.5 — Qwen3.6 README anti-repetition rec for BOTH non-thinking and
  #     thinking (dvalin-smithy canonical 2026-07-08, validated vs Qwen guidance). gen
  #     non-thinking temp 0.7/top_p 0.8; gen-reasoning thinking temp 1.0/top_p 0.95 (the
  #     GENERAL thinking profile, not the 0.6 coding sub-profile). docs/pfi/model-sampler-defaults.md. ---
  # CANONICAL Qwen3.8 INSTRUCT (non-thinking) sampling set, verified 2026-08-16
  # against BOTH upstreams, which are byte-identical on this:
  #   Qwen/Qwen3.8-27B card "Best Practices" §1  and  unsloth/Qwen3.8-27B §1
  #   temperature=0.7, top_p=0.80, top_k=20, min_p=0.0,
  #   presence_penalty=1.5, repetition_penalty=1.0
  #
  # ⚠️ presence_penalty=1.5 is canonical BUT is the one value upstream itself
  # hedges on, verbatim: "you can adjust the presence_penalty parameter between
  # 0 and 2 to reduce endless repetition. However, using a higher value may
  # occasionally result in LANGUAGE MIXING and a slight decrease in model
  # performance." 1.5 sits high in that 0-2 band. If short/degraded replies
  # reappear on long multi-turn conversations, THIS is the first dial to move
  # (try 0.0-0.5) — operator's own hypothesis 2026-08-16, and upstream's caveat
  # supports it. Left at canonical for now so the baseline is defensible rather
  # than hand-tuned.
  - model_name: gen
    litellm_params:
      model: hosted_vllm/qwen3.8-27b-uncensored
      api_base: http://10.250.50.54:8015/v1
      api_key: os.environ/VLLM_API_KEY
      presence_penalty: 1.5
      temperature: 0.7
      top_p: 0.8
      extra_body:
        top_k: 20
        min_p: 0.0
        repetition_penalty: 1.0
        chat_template_kwargs:
          enable_thinking: false
    model_info:
      mode: chat
  - model_name: gen-reasoning
    litellm_params:
      # Distinct served-name so a thinking-off `gen` request can't mutate this deployment's
      # enable_thinking (shared-config-mutation footgun). Same backend :8015, different model id.
      model: hosted_vllm/qwen3.8-27b-uncensored-thinking
      api_base: http://10.250.50.54:8015/v1
      api_key: os.environ/VLLM_API_KEY
      # CANONICAL Qwen3.8 THINKING sampling set (Qwen + unsloth "Best Practices"
      # §1, identical in both): temperature=1.0, top_p=0.95, top_k=20,
      # min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0.
      #
      # ⚠️ presence_penalty was 1.5 here until 2026-08-16 — the INSTRUCT-mode
      # value applied to a THINKING deployment. Canonical for thinking mode is
      # 0.0, and upstream warns a high presence_penalty can cause language
      # mixing and degrade performance. Corrected to 0.0.
      presence_penalty: 0.0
      temperature: 1.0
      top_p: 0.95
      extra_body:
        top_k: 20
        min_p: 0.0
        repetition_penalty: 1.0
        chat_template_kwargs:
          enable_thinking: true
    model_info:
      mode: chat
  # char-rp -> MeroMero-v2 NON-THINKING prose seat (:8016, vLLM, meromero-charrp stack on
  #   ana-ml2 GPU 0). G4-MeroMero-v2-31B NVFP4A16, **Gemma-4 base** (google/gemma-4-31B-it),
  #   256K ctx, in-house quant. Replaced the GGUF/llama.cpp Magidonia-24B seat 2026-08-12.
  #
  #   THIS SEAT EXISTS BECAUSE THE QWEN BASE THINKS INCESSANTLY. char-rp-reasoning is a
  #   Qwen3.x derivative and emits ~5-6k chars of CoT per turn no matter which Qwen RP tune
  #   is loaded — that is the base family, not the finetune, and no swap within it fixes it
  #   (measured 2026-08-16: Dark-Scarlett 6036 ch vs Fable-Fusion 5323 ch on the same
  #   prompts). Gemma-4 gives a genuinely non-thinking prose seat. Reach for THIS one when
  #   you want prose without a reasoning trace; reach for char-rp-reasoning when you want
  #   the deliberation. Best-of-breed per seat — deliberately NOT the same model.
  #
  #   Serving flags are load-bearing (commit b8f0f4c): `--tool-call-parser gemma4
  #   --enable-auto-tool-choice --reasoning-parser gemma4` AND
  #   `--default-chat-template-kwargs '{"enable_thinking": false}'`. That last flag is
  #   MANDATORY, not decorative — the gemma4 parser defaults enable_thinking to True, which
  #   pre-initialises the engine to REASONING and returns null `content` for all plain RP
  #   prose. Before it was set, every tools-bearing request also 400'd (no parser at all).
  #   Verified 0 chars reasoning / clean prose end-to-end 2026-08-16.
  #
  #   Sampler note: the temp 1.1 / min_p 0.10 / top_k 0 values below were A/B-tuned
  #   2026-07-08 against the retired Mistral-family Magidonia seat, NOT against MeroMero.
  #   They have not been re-tuned for Gemma-4 — treat as inherited, not canonical.
  #   Callers may override. docs/pfi/model-sampler-defaults.md; stacks/meromero-charrp/.
  - model_name: char-rp
    litellm_params:
      model: hosted_vllm/char-rp
      api_base: http://10.250.50.54:8016/v1
      api_key: os.environ/VLLM_API_KEY
      temperature: 1.1
      top_p: 0.95
      extra_body:
        min_p: 0.10
        top_k: 0
    model_info:
      mode: chat
  # char-rp-reasoning -> GGUF managed-REASONING seat (:8018, llama.cpp, char-rp-gguf stack).
  #   Qwen3.5-27B-Deckard-PKD-Heretic-Uncensored-Thinking i1-Q5_K_M — DavidAU creative tune.
  #   Reasoning ON server-side (--reasoning on): CoT surfaces in reasoning_content, content stays
  #   clean prose, budget-capped. DRY server-side (sampler order = dry after temperature) tames looping.
  #   A/B WINNER 2026-07-08: 0/30 loops + 0/30 refusals; beat RpR-v4 (1/30 loop, forbids DRY),
  #   Pantheon-27B (7/30 explicit refusals), Snowdrop + Gembrain (llama.cpp template-incompat).
  #   Deckard decode: temp 1.0, top_p 0.95, top_k 40, min_p 0.05 (dvalin-CONFIRMED canonical 2026-07-08;
  #   NO presence/rep penalty; DRY 0.8 server-side). Tuning ladder: flat prose→min_p 0.08, loops→DRY 0.9,
  #   over-damped→DRY 0.6/off. Do NOT import RpR/QwQ sampler rules (different family). NOT the same model as
  #   char-rp (best-of-breed per seat) — see stacks/char-rp-gguf/README.md.
  # ⚠️ TEMPORARY REPOINT 2026-08-16 (operator-directed evaluation window).
  #   char-rp-reasoning currently resolves to FABLE-FUSION 711 on :8019, NOT to
  #   Dark-Scarlett. DS v1.0 is DOWN — GPU1 is zero-sum and Fable-Fusion occupies
  #   her slot. This is a deliberate, explicit substitution for hands-on testing;
  #   it is NOT a silent alias swap, and it is not the permanent seat decision.
  #   Address the seat unambiguously as `char-rp-fable` below; `char-rp-reasoning`
  #   is kept live only so existing consumers keep working during the window.
  #
  #   WHY: DS v1.0 is a plain finetune of stock Qwen3.6-27B with NO abliteration,
  #   so cold prompts revert to safety-tuned base behaviour. Measured three-arm
  #   A/B (services/refusal-probe/): under a bare instruction with no character
  #   card, DS refuses 92.5% (37/40) and Fable-Fusion 15.8% (6/38); with a
  #   character card both sit at ~0%. Fable-Fusion is Heretic-abliterated.
  #
  #   ROLLBACK (restores Dark-Scarlett):
  #     ssh infra-ops@10.250.50.54 'cd /opt/docker/compose/fablefusion-charrp-probe && sudo docker compose down'
  #     ssh infra-ops@10.250.50.54 'cd /opt/docker/compose/darkscarlett-charrp-reasoning && sudo docker compose up -d'
  #     then revert this block to api_base :8018 / model hosted_vllm/char-rp-reasoning
  #     and restart litellm (~52s).
  #
  #   Samplers below are the model card's thinking-mode recommendation (temp 1.0 /
  #   top_p 0.95 / top_k 20) and are unchanged from the DS entry. Verified the FF
  #   chat template honours `enable_thinking` (chat_template.jinja:44) rather than
  #   ignoring it — the mismatch that returned null content on the MeroMero seat.
  - model_name: char-rp-reasoning
    litellm_params:
      model: hosted_vllm/char-rp-probe
      api_base: http://10.250.50.54:8019/v1
      api_key: os.environ/VLLM_API_KEY
      temperature: 1.0
      top_p: 0.95
      extra_body:
        top_k: 20
        chat_template_kwargs:
          enable_thinking: true
    model_info:
      mode: chat
  # char-rp-fable -> the SAME Fable-Fusion seat under its own honest name, so the
  #   evaluation can address it without relying on the temporary repoint above.
  #   Distinct model_name = distinct litellm_params object, which avoids the
  #   shared-deployment param mutation that bleeds sampler overrides between
  #   variants.
  - model_name: char-rp-fable
    litellm_params:
      model: hosted_vllm/char-rp-probe
      api_base: http://10.250.50.54:8019/v1
      api_key: os.environ/VLLM_API_KEY
      temperature: 1.0
      top_p: 0.95
      extra_body:
        top_k: 20
        chat_template_kwargs:
          enable_thinking: true
    model_info:
      mode: chat

  # --- Selene 1 Mini 8B (AtlaAI judge, FP8) — restored on GPU1 after the
  #     llama-swap teardown (was the Q6_K GGUF in the swap zoo). vLLM dynamic fp8,
  #     :8011. Explicit entry shadows the "*" wildcard (which used to reach it via
  #     llama-swap). Hallucination/RAG-faithfulness judge; callers set temp ~0.01. ---
  - model_name: selene-1-mini-8b
    litellm_params:
      model: hosted_vllm/selene-1-mini-8b
      api_base: http://10.250.50.54:8011/v1
      api_key: os.environ/VLLM_API_KEY
      temperature: 0.6
      top_p: 0.9
    model_info:
      mode: chat

  # --- Qwen3 embeddings ---
  - model_name: qwen3-embedding
    litellm_params:
      model: hosted_vllm/Qwen/Qwen3-Embedding-0.6B
      api_base: http://10.250.50.54:8001/v1
      api_key: os.environ/VLLM_API_KEY
    model_info:
      mode: embedding

  # --- Qwen3 reranker (proxy /rerank route) ---
  - model_name: qwen3-reranker
    litellm_params:
      model: hosted_vllm/Qwen/Qwen3-Reranker-0.6B
      api_base: http://10.250.50.54:8002/v1
      api_key: os.environ/VLLM_API_KEY
    model_info:
      mode: rerank

  # --- Worldtree capability aliases (role→capability gateway swaps, ADR-0012).
  #     Stable role-named aliases so consumers bind the CAPABILITY, not a concrete
  #     model; swap the backing model here and callers are unaffected. NO generic
  #     `embedding` alias ON PURPOSE — embedding vectors are model-specific (not
  #     swap-transparent), so that capability stays `qwen3-embedding` above. ---
  # chat-judge → generative LLM-as-judge (Selene); WT selene-judgment role.
  - model_name: chat-judge
    litellm_params:
      model: hosted_vllm/selene-1-mini-8b
      api_base: http://10.250.50.54:8011/v1
      api_key: os.environ/VLLM_API_KEY
      temperature: 0.6
      top_p: 0.9
    model_info:
      mode: chat
  # reranker → generic capability name for rerank (currently qwen3-reranker).
  - model_name: reranker
    litellm_params:
      model: hosted_vllm/BAAI/bge-reranker-v2-m3
      api_base: http://10.250.50.54:8013/v1
      api_key: os.environ/VLLM_API_KEY
    model_info:
      mode: rerank

  # --- coder-fast → Qwen2.5-Coder-1.5B (BASE), FIM code-completion seat (ana-ml2
  #     GPU1 :8020, vLLM; deep-research pick 2026-07-27). For Zed editor inline
  #     edit-predictions via the LEGACY /v1/completions endpoint with Qwen FIM
  #     markers (<|fim_prefix|>/<|fim_suffix|>/<|fim_middle|>). BASE not -Instruct
  #     (FIM is a pretraining objective; base completions are cleaner). Apache-2.0.
  #     mode: completion — this is text-completion, not chat. Reached KEYLESS from
  #     Vuong's Mac via the zed-fim-proxy (separate port on ana-docker) which injects
  #     a coder-fast-scoped virtual key; the proxy's model-allowlist + the scoped key
  #     bound the blast radius. Runner-up was Qwen2.5-Coder-3B (higher HumanEval-FIM,
  #     non-commercial Qwen-Research license). ---
  - model_name: coder-fast
    litellm_params:
      model: hosted_vllm/qwen2.5-coder-1.5b
      api_base: http://10.250.50.54:8020/v1
      api_key: os.environ/VLLM_API_KEY
    model_info:
      mode: completion

  # --- z.ai GLM (cloud API) — fronted for unified logging across local
  #     + cloud inference. Explicit entries, so they win over the "*"
  #     wildcard below (no collision with llama-swap's glm4.7-flash etc.
  #     — different model IDs). NOTE: paid API; only gateway-keyed callers
  #     can reach these, but they DO spend z.ai credits. Key in .env. ---
  # glm-5.1: thinking DISABLED by default (2026-06-11, operator call). LiteLLM
  #   strips a top-level `thinking` param (drop_params), but forwards `extra_body`
  #   verbatim to z.ai, where the native thinking:{type:disabled} control lands —
  #   verified reasoning_tokens→0. Reasoning is opt-in via glm-5.1-reasoning below.
  - model_name: glm-5.1
    litellm_params:
      model: openai/glm-5.1
      api_base: https://api.z.ai/api/coding/paas/v4
      api_key: os.environ/Z_AI_API_KEY
      temperature: 1.0
      top_p: 0.95
      extra_body:
        thinking:
          type: disabled
  # glm-5.1-reasoning: identical upstream, thinking ENABLED (opt-in reasoning).
  - model_name: glm-5.1-reasoning
    litellm_params:
      model: openai/glm-5.1
      api_base: https://api.z.ai/api/coding/paas/v4
      api_key: os.environ/Z_AI_API_KEY
      temperature: 1.0
      top_p: 0.95
      extra_body:
        thinking:
          type: enabled
  # glm-5.2 (released ~2026-06; canonical z.ai id `glm-5.2`, confirmed via /models +
  #   a live completion with our key). Mirrors the glm-5.1 pattern: thinking DISABLED
  #   by default (consistency with the 2026-06-11 operator call), opt-in reasoning via
  #   glm-5.2-reasoning. extra_body.thinking is forwarded verbatim to z.ai.
  #   CANONICAL LIMITS (probed live vs z.ai 2026-07-05): 1,048,576-token (1M, 2^20)
  #   INPUT context; 131,072 (128K) MAX OUTPUT (z.ai max_tokens range [1,131072]).
  #   NO gateway-side cap — pure z.ai passthrough, so these are the effective limits.
  - model_name: glm-5.2
    litellm_params:
      model: openai/glm-5.2
      api_base: https://api.z.ai/api/coding/paas/v4
      api_key: os.environ/Z_AI_API_KEY
      temperature: 1.0
      top_p: 0.95
      extra_body:
        thinking:
          type: disabled
  - model_name: glm-5.2-reasoning
    litellm_params:
      model: openai/glm-5.2
      api_base: https://api.z.ai/api/coding/paas/v4
      api_key: os.environ/Z_AI_API_KEY
      temperature: 1.0
      top_p: 0.95
      extra_body:
        thinking:
          type: enabled
  # gen-frontier / gen-frontier-reasoning: capability aliases for the PAID
  #   frontier tier (GLM 5.2 @ z.ai), mirroring glm-5.2 / glm-5.2-reasoning
  #   (thinking off / on). Worldtree binds these for frontier-grade generation
  #   / reasoning; swap the backing frontier model here, callers unaffected.
  #   PAID — only all-proxy-models / explicitly-scoped keys reach them; the free
  #   all-agents-local key is fenced off z.ai spend and cannot.
  - model_name: gen-frontier
    litellm_params:
      model: openai/glm-5.2
      api_base: https://api.z.ai/api/coding/paas/v4
      api_key: os.environ/Z_AI_API_KEY
      temperature: 1.0
      top_p: 0.95
      extra_body:
        thinking:
          type: disabled
  - model_name: gen-frontier-reasoning
    litellm_params:
      model: openai/glm-5.2
      api_base: https://api.z.ai/api/coding/paas/v4
      api_key: os.environ/Z_AI_API_KEY
      temperature: 1.0
      top_p: 0.95
      extra_body:
        thinking:
          type: enabled
  - model_name: glm-5-turbo
    litellm_params:
      model: openai/glm-5-turbo
      api_base: https://api.z.ai/api/coding/paas/v4
      api_key: os.environ/Z_AI_API_KEY
      temperature: 1.0
      top_p: 0.95
  - model_name: glm-4.7
    litellm_params:
      model: openai/glm-4.7
      api_base: https://api.z.ai/api/coding/paas/v4
      api_key: os.environ/Z_AI_API_KEY
      temperature: 1.0
      top_p: 0.95
  - model_name: glm-4.5-air
    litellm_params:
      model: openai/glm-4.5-air
      api_base: https://api.z.ai/api/coding/paas/v4
      api_key: os.environ/Z_AI_API_KEY
      temperature: 0.6
      top_p: 0.95

  # --- Kimi K3 — CODING endpoint (Kimi Code / Vivace membership). THE PRIMARY
  #     Kimi arm the Heid cross-frontier panel plan uses. OpenAI-compatible base
  #     https://api.kimi.com/coding/v1 → openai/ provider, upstream model id `k3`
  #     (1M-context; the coding lineup also carries k3-256k, kimi-for-coding,
  #     kimi-for-coding-highspeed — ids confirmed live via /models 2026-07-25).
  #     PAID (Vivace subscription); key KIMI_CODE_API_KEY in .env. CONSTRAINT
  #     (verified live 2026-07-25): k3 accepts ONLY temperature=1 — any other value
  #     400s ("only 1 is allowed for this model") — so it is pinned here; callers
  #     must NOT override it. k3 is also a REASONING model (thinking-effort tiers
  #     low/high/max per Kimi Code docs): CoT returns in `reasoning_content`, the
  #     answer in `content` — give it adequate max_tokens or content returns EMPTY
  #     (reasoning eats a tiny budget). ---
  - model_name: kimi-k3
    litellm_params:
      model: openai/k3
      api_base: https://api.kimi.com/coding/v1
      api_key: os.environ/KIMI_CODE_API_KEY
      temperature: 1
    model_info:
      mode: chat

  # --- Kimi K3 — GENERAL Moonshot API endpoint (https://api.moonshot.ai/v1),
  #     kept as the `-gen-api` variant. The plan uses the CODING endpoint above;
  #     this is the general-platform route (originally wired then demoted when the
  #     coding endpoint became canonical). OpenAI-compatible, upstream `kimi-k3`,
  #     key MOONSHOT_API_KEY. Same temperature=1 + reasoning-model constraints as
  #     the coding k3 (verified live through the gateway 2026-07-25, 17+25→"42"). ---
  - model_name: kimi-k3-gen-api
    litellm_params:
      model: openai/kimi-k3
      api_base: https://api.moonshot.ai/v1
      api_key: os.environ/MOONSHOT_API_KEY
      temperature: 1
    model_info:
      mode: chat

  # --- (removed 2026-06-20, operator call) the `*` wildcard → llama-swap
  #     (ana-ml2:9292). llama-swap is decommissioned (:9292 confirmed down), so
  #     the wildcard routed every unmatched / typo'd / stale model name to a DEAD
  #     backend → a misleading "Connection error" instead of a clean "model not
  #     found". This is the footgun that silently swallowed Worldtree's defunct
  #     model names. Removed so unknown models now fail loudly (404). Re-add an
  #     explicit per-model entry if a swappable zoo ever returns. ---

  # --- lfm2.5-2.6b -> RETIRED PERMANENTLY 2026-08-20 (operator directive). The
  #     LiquidAI LFM2.5-2.6B seat (ana-ml2 GPU1 :8021) was an EVAL-ONLY bake-off
  #     against granite-4.1-8b that never got its operator ruling; its comparator
  #     was retired 2026-08-15 and spend logs showed 0 calls in the 4 days to
  #     2026-08-21. Container removed, service deleted from stacks/vllm. The alias
  #     is deleted rather than repointed so the name 404s cleanly. ---

general_settings:
  master_key: os.environ/LITELLM_MASTER_KEY
  database_url: os.environ/DATABASE_URL
  store_model_in_db: true
  # THE log switch: persists full request messages + response bodies into
  # SpendLogs so they render in the Logs UI. Without this you get metadata
  # (tokens, latency, model) but not the prompt/completion text.
  #
  # ⚠️ TURNED OFF 2026-08-16 (operator: "I don't need any of that information").
  # With this TRUE the SpendLogs table stored every prompt+completion body and
  # grew to 6.0 GB (of a 6.08 GB DB). Off = lightweight cost/usage rows only
  # (tokens, latency, model, cost) — the cross-project spend tracking survives,
  # the bulky bodies do not. Re-enable ONLY for a bounded debugging window, not
  # standing.
  store_prompts_in_spend_logs: false
  # HARD CAP on SpendLogs growth (operator: "if there's a way to cap it, CAP
  # it"). The retention job deletes rows older than the period on the interval
  # cadence, so the table is bounded by ~7 days of lightweight rows rather than
  # unbounded. Names verified against LiteLLM docs (proxy/spend_logs_deletion).
  maximum_spend_logs_retention_period: "7d"
  maximum_spend_logs_retention_interval: "1d"
  # scalar-judge → Skywork-Reward-V2 (scalar reward model; vLLM pooling on
  #   ana-ml2:8003). LiteLLM has no reward/pooling MODE, so this is a passthrough,
  #   not a model_list alias. Gateway-key-gated. Consumers POST the reward body to
  #   /scalar-judge/<route> (e.g. /pooling or /classify), forwarded to :8003.
  #   SWAP-SENSITIVE: a different reward model shifts the score scale, so consumers
  #   must recalibrate thresholds after a backing swap.
  pass_through_endpoints:
    - path: "/scalar-judge"
      target: "http://10.250.50.54:8003"
      forward_headers: true
      include_subpath: true

litellm_settings:
  # vLLM rejects some OpenAI params other backends accept; drop silently
  # rather than 400 the caller.
  drop_params: true
  # Custom pre-call hook: strip an empty `tools: []` (+ orphaned tool_choice)
  # before forwarding upstream. vLLM 400s on empty tools arrays ("tools must
  # not be an empty array"); drop_params doesn't catch empty VALUES, only
  # unsupported params. Runs on every request → fixes it for all vLLM models.
  # File mounted at /app/strip_empty_tools.py; reference is module.instance,
  # resolved relative to this config's directory.
  callbacks: ["strip_empty_tools.strip_empty_tools_instance"]
  # Langfuse trace export RETIRED 2026-06-20 (operator). Its ClickHouse member spewed
  # ~94 GB of unrotated logs and filled ana-docker's disk; the trace UI was redundant
  # with LiteLLM's native spend_logs (store_prompts_in_spend_logs: true → full
  # prompts/responses/tokens/cost at :4000/ui). Gateway observability stays fully
  # native. Re-add success_callback/failure_callback here if Langfuse ever returns.