- refresh the Anthropic lineup to the current GA set (Fable 5, Opus 4.8,
Sonnet 5, Opus 4.7, Haiku 4.5)
- extend the effort gate to single-number Claude 5 IDs (claude-sonnet-5,
claude-fable-5) so their effort setting is honored
Trim each provider to current-generation models and drop the special-casing
they required:
- OpenAI: remove gpt-4.1 (deprecated; the only non-reasoning model).
- Anthropic: remove Claude Sonnet 4.5 (legacy; the only Sonnet that 400s on effort).
- Google: remove the Gemini 2.5 line (superseded by 3.x).
- Gemini client: drop the integer thinking_budget mapping; 3.x takes the string
thinking_level directly.
Effort/reasoning gates stay as defense in depth for custom model IDs. All kept
IDs verified against live APIs.
Verified each provider's hard-coded list against current official docs:
- MiniMax: add MiniMax-M3 (1M ctx, multimodal) as the default; keep M2.7 line.
- Qwen: use the live qwen{3.7,3.6}-{plus,max} IDs.
- GLM: add glm-5.2 as the latest flagship.
- xAI: drop deprecated grok-4-fast-* / grok-4-0709 builds.
- DeepSeek: migrate to deepseek-v4-pro / deepseek-v4-flash (the chat/reasoner
aliases are deprecated 2026-07-24 and now map to V4 Flash).
OpenAI, Anthropic, and Gemini were already current and are unchanged.
Clear the deferred full-repo lint backlog so the whole tree passes the strict
ruff select (E,W,F,I,B,UP,C4,SIM). Mechanical fixes dominate: import sorting,
pep585/604 annotations, dropped dead imports, and whitespace. The few semantic
changes are behavior-preserving: declare __all__ on the agent_utils and
alpha_vantage re-export hubs; expand 'from x import *' to explicit names; use
immutable tuple defaults instead of mutable list defaults; contextlib.suppress
for try/except/pass; and narrow an over-broad assertRaises.
Bedrock uses the Converse API (langchain-aws) and the AWS credential chain, so
it has its own client like Anthropic/Google rather than the OpenAI-compatible
registry. langchain-aws is an optional dependency (pip install ".[bedrock]"),
lazy-imported with a clear install hint; importing the package never requires
it. The model name is a Bedrock model ID / inference profile ID.
Each is a one-row entry in the OpenAI-compatible provider registry (base_url,
key env, CLI option); the model is user-specified since they serve many models.
The OpenAI-compatible family (openai, xAI, DeepSeek, Qwen, GLM, MiniMax,
OpenRouter, Ollama) all speak the same Chat Completions API and differ only by
base_url, key, and two narrow wire-format quirks already isolated in subclasses.
Replace the scattered base-URL dict, key handling, and client-class branches with
one ProviderSpec registry that get_llm and the factory drive off; provider quirks
stay in their subclasses. Add a generic "openai_compatible" provider for any
OpenAI-compatible server (vLLM, LM Studio, llama.cpp, relays) via backend_url +
optional key — adding a provider is now one registry row. Native Anthropic/Google
keep their own clients (genuinely different APIs). Also fixes the env backend URL
being ignored when the provider was chosen interactively (#978).
Users with other models pulled via `ollama pull` (beyond the three
suggested defaults) can now select "Custom model ID" and type any
model name. Matches the same pattern used for DeepSeek, GLM, Qwen,
and MiniMax — the existing _prompt_custom_model_id flow handles the
"custom" value generically, so this is a one-row catalog addition
plus regression coverage.
OLLAMA_BASE_URL now flows through both the CLI dropdown and the
programmatic client (call-time evaluation so tests behave). After
provider selection, the CLI prints the resolved endpoint and marks
when it came from the env var, plus a soft warning when the URL is
missing a scheme or non-default port. Drops the stale "(local)"
suffix from Ollama model labels since the endpoint is now dynamic.
Zhipu serves GLM under two brands with separate accounts (Z.AI
international vs BigModel China); the CLI URL pointed at one while
the openai_client default pointed at the other. Split into glm +
glm-cn with secondary region prompt (same UX as Qwen + MiniMax).
Catalog adds glm-5-turbo and glm-4.5-air per docs.z.ai.
Qwen and MiniMax each had two main-dropdown entries (intl + CN);
consolidate to one entry per provider and prompt for region as a
secondary step. Internal provider keys (qwen-cn, minimax-cn) and
endpoint routing unchanged. Add qwen3.6-flash to the Qwen catalog
and drop the version-less aliases (qwen-flash, qwen-plus) that
auto-shift their backing model per Alibaba's docs.
#758
xAI's official docs lead with grok-4.20-reasoning and
grok-4.20-non-reasoning across all SDK examples. Replace the prior
grok-4-1-fast-* entries (hyphens where docs use dots, no literal
code example) with the verified grok-4.20 family. Keep grok-4-0709
and grok-4-fast variants that are still referenced.
gemini-3.1-flash-lite is now GA per ai.google.dev. Use the stable
version (fewer rate limits, stronger compat guarantees) instead of
the -preview suffix. Labels mark preview vs GA explicitly.
Opus 4.7 is the current frontier per platform.claude.com (frontier
category, listed first). Demote Opus 4.6 to second deep-tier slot.
Polish quick-tier labels to match official wording; effort docstring
includes 4.7.
GPT-5.5 (Apr 2026, 1M ctx, $5/$30 per 1M) replaces GPT-5.4 as the
catalog flagship. GPT-5.5 Pro replaces 5.4 Pro in the most-capable
slot. GPT-5.4 demotes to previous-gen cost-effective option.
M2.x tool_choice is enum-only (none/auto), so route through the
no-tool_choice dispatch. MinimaxChatOpenAI injects reasoning_split
so <think> blocks stay out of content. Catalog rounded out to the
full official M2.x lineup plus forward-compat regex.
Two regional endpoints (global api.minimax.io, China api.minimaxi.com)
with separate API keys. Models M2.7 / M2.5 plus -highspeed variants,
204K context. Follows the existing provider-preset pattern.
#789#609#577#546#395#378
Resolves#599: thinking-mode models require reasoning_content to be
echoed back across turns; multi-turn agent runs failed with HTTP 400.
The fix isolates DeepSeek's quirks (reasoning_content round-trip and
the deepseek-reasoner no-tool_choice limitation) into a subclass so
the general OpenAI-compatible client stays untouched. Adds DeepSeek
V4 Pro/Flash to the catalog. 9 new tests; rationale documented in
the class docstrings.
Design adapted from #600; #611 closed in favour of this approach.
Yijia-Xiao