nestharus e73cdf5cff fix(claude): ensure max_tokens exceeds thinking budget for thinking models ...

Fixes an issue where Claude thinking models would return 400 errors when
the thinking.budget_tokens was greater than or equal to max_tokens.

Changes:
- Add MaxCompletionTokens: 128000 to all Claude thinking model definitions
- Add ensureMaxTokensForThinking() function in claude_executor.go that:
  - Checks if thinking is enabled with a budget_tokens value
  - Looks up the model's MaxCompletionTokens from the registry
  - Ensures max_tokens is set to at least the model's MaxCompletionTokens
  - Falls back to budget_tokens + 4000 buffer if registry lookup fails

This ensures Anthropic API constraint (max_tokens > thinking.budget_tokens)
is always satisfied when using extended thinking features.

Fixes: #339

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

2025-11-26 22:31:05 -08:00

..

access

feat(ws): add WebSocket auth

2025-10-26 07:46:04 +08:00

api

style(amp): tidy whitespace in proxy module and tests

2025-11-26 18:57:26 +08:00

auth

feat(iflow): add cookie-based authentication endpoint

2025-11-20 18:23:43 +08:00

browser

feat(logging): introduce centralized logging with custom format and Gin integration

2025-09-26 00:54:52 +08:00

buildinfo

feat(buildinfo): add build metadata and expose via HTTP headers

2025-11-13 08:38:03 +08:00

cmd

**feat(auth, executor, cmd): add Antigravity provider integration**

2025-11-21 12:43:16 +08:00

config

**feat(config): add TLS support for HTTPS server configuration**

2025-11-24 10:41:29 +08:00

constant

**feat(translator): add Antigravity translation logic**

2025-11-21 23:40:59 +08:00

interfaces

**feat(translator): add ThoughtSignature handling in Gemini request transformations**

2025-11-19 11:34:13 +08:00

logging

**feat(logging, middleware): add error-based logging support and error log management**

2025-11-23 22:41:57 +08:00

managementasset

feat: implement management asset configuration and auto-updater

2025-10-21 09:01:58 +08:00

misc

**feat(registry): add GPT-5.1 Codex Max model definitions and support**

2025-11-20 03:12:22 +08:00

registry

fix(claude): ensure max_tokens exceeds thinking budget for thinking models

2025-11-26 22:31:05 -08:00

runtime

fix(claude): ensure max_tokens exceeds thinking budget for thinking models

2025-11-26 22:31:05 -08:00

store

Add Object Storage

2025-10-15 11:47:35 +08:00

translator

**fix(translator): normalize function calls and outputs for consistent input processing**

2025-11-27 10:25:45 +08:00

usage

**feat(auth): add AuthIndex for diagnostics and ensure usage recording**

2025-11-19 22:02:40 +08:00

util

Fixed: #291

2025-11-21 00:48:12 +08:00

watcher

#293

2025-11-24 09:55:15 +08:00

wsrelay

refactor(wsrelay): rename RoundTrip to NonStream

2025-10-26 20:01:46 +08:00