CLIProxyAPI

feat(cliproxy): introduce global model name mappings for improved aliasing and routing

Luis Pater · 2025-12-30 08:13:06 +08:00

50e6d845f4

fix(thinking): align budget effort mapping across translators

Unify thinking budget-to-effort conversion in a shared helper, handle disabled/default thinking cases in translators, adjust zero-budget mapping, and drop the old OpenAI-specific helper with updated tests.

hkfires · 2025-12-16 18:34:43 +08:00

28a428ae2f

fix(thinking): map budgets to effort levels

Ensure thinking settings translate correctly across providers:
- Only apply reasoning_effort to level-based models and derive it from numeric
  budget suffixes when present
- Strip effort string fields for budget-based models and skip Claude/Gemini
  budget resolution for level-based or unsupported models
- Default Gemini include_thoughts when a nonzero budget override is set
- Add cross-protocol conversion and budget range tests

hkfires · 2025-12-12 21:33:20 +08:00

374faa2640

refactor(thinking): use parentheses for metadata suffix

hkfires · 2025-12-11 18:39:07 +08:00

e79f65fd8e

refactor(thinking): use bracket tags for thinking meta

Align thinking suffix handling on a single bracket-style marker.

NormalizeThinkingModel strips a terminal `[value]` segment from
model identifiers and turns it into either a thinking budget (for
numeric values) or a reasoning effort hint (for strings). Emission
of `ThinkingIncludeThoughtsMetadataKey` is removed.

Executor helpers and the example config are updated so their
comments reference the new `[value]` suffix format instead of the
legacy dash variants.

BREAKING CHANGE: dash-based thinking suffixes (`-thinking`,
`-thinking-N`, `-reasoning`, `-nothinking`) are no longer parsed
for thinking metadata; only `[value]` annotations are recognized.

hkfires · 2025-12-11 18:17:28 +08:00

facfe7c518

fix(util): do not strip thinking suffix on registered models

NormalizeThinkingModel now checks ModelSupportsThinking before removing
"-thinking" or "-thinking-<ver>", avoiding accidental parsing of model
names where the suffix is part of the official id (e.g., kimi-k2-thinking,
qwen3-235b-a22b-thinking-2507).

The registry adds ThinkingSupport metadata for several models and
propagates it via ModelInfo (e.g., kimi-k2-thinking, deepseek-r1,
qwen3-235b-a22b-thinking-2507, minimax-m2), enabling accurate detection
of thinking-capable models and correcting base model inference.

hkfires · 2025-12-11 15:52:14 +08:00

007572b58e

fix(runtime): unify reasoning effort metadata overrides

hkfires · 2025-12-11 14:35:05 +08:00

3a81ab22fd

fix(util): align reasoning effort handling with registry

hkfires · 2025-12-11 12:20:12 +08:00

169f4295d0

fix(util): centralize reasoning effort normalization

hkfires · 2025-12-11 12:14:51 +08:00

d06d0eab2f

feat(util): implement dynamic thinking suffix normalization and refactor budget resolution logic

- Added support for parsing and normalizing dynamic thinking model suffixes.
- Centralized budget resolution across executors and payload helpers.
- Retired legacy Gemini-specific thinking handlers in favor of unified logic.
- Updated executors to use metadata-based thinking configuration.
- Added `ResolveOriginalModel` utility for resolving normalized upstream models using request metadata.
- Updated executors (Gemini, Codex, iFlow, OpenAI, Qwen) to incorporate upstream model resolution and substitute model values in payloads and request URLs.
- Ensured fallbacks handle cases with missing or malformed metadata to derive models robustly.
- Refactored upstream model resolution to dynamically incorporate metadata for selecting and normalizing models.
- Improved handling of thinking configurations and model overrides in executors.
- Removed hardcoded thinking model entries and migrated logic to metadata-based resolution.
- Updated payload mutations to always include the resolved model.

Luis Pater · 2025-12-11 03:10:50 +08:00

423ce97665

10 Commits