DEEPSEEK_V4_FLASH_THINKING_LEVEL_MAP (which enables the low effort level)
was only applied to deepseek/deepseek-v4-flash, so the same model served
through opencode and opencode-go only offered off/high/max. models.dev
reports reasoning_options effort values of low/high/max for these
providers, and the live opencode-go API accepts reasoning_effort=low
(verified against https://opencode.ai/zen/go/v1).
Apply the flash map to every deepseek-v4-flash variant on the deepseek,
opencode, and opencode-go providers. qwen-token-plan is left unchanged
since its gateway support for the low effort level is not verified.
* feat(ai): route xAI models through Responses and default to Grok 4.6
Send built-in xAI catalog models through the Responses API with
store: false and include reasoning.encrypted_content so encrypted
reasoning is requested and replayed, including future models.dev
additions. Thinking levels come from models.dev reasoning_options
(grok-4.6 exposes xhigh); models without verified options
(grok-build-0.1) keep reasoning always on and never send unsupported
"none"/"minimal" efforts. Narrow the xAI provider to the Responses API,
send pi's runtime User-Agent on xAI requests for provider-side
attribution, and make Grok 4.6 the default xAI model.
* fix(ai): drop duplicate xAI encrypted-reasoning tests
Azure already covers the shared replay path; keep the xAI-specific include-without-effort case next to the existing request tests.
---------
Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com>
GA qwen3.8-max is on models.dev for alibaba-token-plan[-cn]. Point the
Qwen3.8 effort map at the GA id and exclude the retired preview so
regenerate does not revive it.
* fix(ai): send max_tokens for Z.AI providers
Z.AI (zai, zai-coding-cn, api.z.ai, open.bigmodel.cn) ignores
max_completion_tokens and only honors max_tokens, so the configured
output cap never applied and Z.AI fell back to its 65536 default.
Add isZai to detectCompat's useMaxTokens condition.
* fix(ai): set zai max_tokens compat in model generator
Per review feedback: the model generator now maps Z.AI to max_tokens, so
regenerated Z.AI model entries carry compat.maxTokensField="max_tokens"
(Z.AI ignores max_completion_tokens). The runtime detectCompat change is
kept as a fallback for custom/self-hosted Z.AI base URLs not in the catalog,
matching how moonshot/together/nvidia are handled in both places.
Route claude-opus-5 through the Anthropic Messages API with adaptive
thinking, the Copilot minimal thinking-level override, and pin the
extended 1M context window alongside the other Copilot Opus models.
Add the constrained sampling API and provider plumbing for OpenAI and Anthropic tool calls, including grammar sampling variants and model capability metadata.
Fresh package installs could give bundled model catalog
files newer filesystem mtimes than the remote catalog’s Last-Modified timestamp,
causing Pi to ignore newer remote models.
Use the catalog’s recorded generation time instead of installation-dependent file metadata.
Treat the models.dev k2p7 entry as an alias for kimi-for-coding and regenerate provider catalogs. This restores consistency between generated model types and values and unblocks repository type checks.
Add Alibaba Cloud Model Studio Token Plan subscription service as two
built-in API-key providers: qwen-token-plan (international, Singapore)
and qwen-token-plan-cn (China, Beijing).
Each provider exposes 15 text-generation models (Qwen, DeepSeek, GLM,
Kimi, MiniMax) via the OpenAI-compatible endpoint with DashScope
enable_thinking support. Model metadata is sourced from models.dev;
qwen3.8-max-preview is hardcoded until models.dev includes it.
Also fixes kimi-coding test references (k2p7 -> kimi-for-coding) after
models.dev catalog update picked up by generate-models.
Closes#6850
