yj8)UdZddlmZddlZddlmZdZded<deed DZ d ed <ddZ ddZ dS)u Per-reasoning-model stale-timeout floor for known reasoning models. Reasoning models (those that emit extended thinking blocks before their first content token) routinely exceed Hermes's default chat-model stale detectors: * Stream stale detector: ``HERMES_STREAM_STALE_TIMEOUT`` default 180s ``agent/chat_completion_helpers.py:2544`` * Non-stream stale detector: ``HERMES_API_CALL_STALE_TIMEOUT`` default 90s ``run_agent.py:1140`` For NVIDIA Nemotron 3 Ultra on the hosted NIM gateway the empirical upstream idle kill is ~120s (first-party reproduction at NVIDIA/NemoClaw#4846 — TTFB ~31s, stream dies at 120s). The same failure mode exists on OpenAI o1/o3, Anthropic Opus 4.x thinking, DeepSeek R1, Qwen QwQ, xAI Grok reasoning — every cloud reasoning model hits upstream-proxies / load-balancers with idle timeouts shorter than the model's thinking phase. Result: the stale detector kills the connection mid-think, surfacing as ``BrokenPipeError``/``RemoteProtocolError`` on the next read. This module provides a floor that the existing stale-detector scaling blocks consult via :func:`get_reasoning_stale_timeout_floor` and apply as ``max(default, floor)``. It is a FLOOR: * Never overrides explicit user config (``providers..models..stale_timeout_seconds`` or ``request_timeout_seconds`` already wins — this code never runs in that branch). * Never lowers an existing threshold. * Has zero effect on non-reasoning models — they are not in the allowlist and the resolver returns ``None``. Matching uses start-anchored regex on the slug-only component of the model name (after stripping any aggregator prefix like ``openai/``, ``x-ai/``, ``anthropic/``). The right-anchor matches end-of-string or a ``-``/``.``/``_`` slug separator, so ``qwen3-235b`` matches the ``qwen3`` family entry (a future model slug would be ``qwen3-235b-instruct`` and would also match) but ``some-other-qwen3`` does NOT match ``qwen3`` (the ``-qwen3`` is not at start of slug). The ``o1`` case is the most delicate: a model named ``llama-4-70b-o1-preview`` is a hypothetical community derivative that should NOT trigger the reasoning-model floor for the user (the user chose a non-OpenAI model, not a reasoning model). The start-of-slug anchor naturally excludes this — the matched ``o1-preview`` is at position 11 of the slug, not at position 0. The previous substring- with-trailing-hyphen design would have over-matched here, which is why start-of-slug anchoring is the right shape. Fixes #52217. ) annotationsN)Optional))znemotron-3-ultraX)znemotron-3-superr)znemotron-3-nano,)z deepseek-r1r)zdeepseek-reasonerr)zdeepseek-v4-flashr)zdeepseek-v4-pror)zqwq-32br)qwen3)o1r)zo1-minir)zo1-pror)z o1-previewr)o3r)zo3-pror)zo3-minir)zo4-minir)z claude-opus-4)z claude-opus-5r )zclaude-sonnet-5r)zclaude-sonnet-4.5r)zclaude-sonnet-4.6r)z claude-fabler)zgrok-4-fast-reasoningr)zgrok-4.20-reasoningr)zgrok-4.5r)zgrok-4-fast-non-reasoningrztuple[tuple[str, int], ...]_REASONING_STALE_TIMEOUT_FLOORSc rg|]4\}}||tjdtj|zdzf5S)^z (?:$|[\-._]))recompileescape).0slugfloors >/home/ragecks/.hermes/hermes-agent/agent/reasoning_timeouts.py rsUFFFe 5"*TBIdOO3oEFFGFFFc.t|d S)Nr)len)kvs rrsRU r)keyz(list[tuple[str, float, re.Pattern[str]]]_SORTED_REASONING_FLOORS model_lowerstrreturnOptional[float]cntD],\}}}||rt|cS-dS)a5Return the floor for the first matching slug, else None. Each table entry is matched as a start-of-slug prefix with the slug-separator-or-end-of-string right-anchor. Table iteration order is irrelevant: longest slug wins (so ``o3-mini`` beats ``o3`` on a model like ``openai/o3-mini``). N)rsearchfloat)r_slugrpatterns r _match_anyr'sJ":  ug >>+ & & <<    4rmodelobjectc|rt|tsdS|}|sdSd|vr|ddd}t |S)uReturn the stale-timeout floor (seconds) for a known reasoning model. Returns ``None`` when the model is not in the allowlist or the argument is empty / not a string. Matching uses word-boundary-anchored regex on the lowercased model name, so ``openai/o3-mini`` matches the ``o3-mini`` slug but ``olmo-1`` does NOT match ``o1`` (the ``o1`` substring is not at a word boundary inside ``olmo-1``). Aggregator prefixes (``openai/``, ``x-ai/``, ``anthropic/`` etc.) are preserved through matching — the ``/`` is itself a word boundary, so ``openai/o3-mini`` matches ``o3-mini`` because the ``/`` before ``o3-mini`` satisfies the left-anchor alternation. This is a FLOOR — callers must apply it as ``max(default, floor)`` and only when no explicit user-configured per-model ``stale_timeout_seconds`` exists. >>> get_reasoning_stale_timeout_floor("nvidia/nemotron-3-ultra-550b-a55b") 600.0 >>> get_reasoning_stale_timeout_floor("openai/o3-mini") 300.0 >>> get_reasoning_stale_timeout_floor("deepseek/deepseek-r1") 600.0 >>> get_reasoning_stale_timeout_floor("deepseek/deepseek-v4-flash") 600.0 >>> get_reasoning_stale_timeout_floor("deepseek/deepseek-v4-pro") 600.0 >>> get_reasoning_stale_timeout_floor("qwen/qwen3-235b-a22b-thinking") 180.0 >>> get_reasoning_stale_timeout_floor("x-ai/grok-4-fast-reasoning") 300.0 >>> get_reasoning_stale_timeout_floor("anthropic/claude-opus-4-6") 240.0 >>> get_reasoning_stale_timeout_floor("anthropic/claude-fable-5") 600.0 >>> get_reasoning_stale_timeout_floor("gpt-4o") is None True >>> get_reasoning_stale_timeout_floor("olmo-1") is None True >>> get_reasoning_stale_timeout_floor(None) is None True N/) isinstancerstriplowerrsplitr')r(names r!get_reasoning_stale_timeout_floorr2szX  5#..t ;;==   D t d{{{{3""1% d  r)rrr r!)r(r)r r!) __doc__ __future__rrtypingrr __annotations__sortedrr'r2rrr9s222h#"""""  @@@@@@zFFv'-C-CFFF    666666r