- formatBriefTimestamp (5): force LC_ALL=en-US + TZ=UTC for CI
- EFFORT_LEVELS (1): update to 5 levels (added xhigh)
- effort description (1): remove stale 'no model names' test
- prompt caching (1): fix input_tokens expectation to match
Anthropic convention (non-cached only)
- ExecuteTool: rename runner to .runner.test.ts so bun finds it
- localVault/store.ts: synced from upstream
Remaining 4 failures are test isolation issues (compound command)
and feature flag mismatch (CtxInspectTool) — all pass in isolation.
DeepSeek v4 requires reasoning_content to be echoed back even when
empty, otherwise the API returns HTTP 400. The implementation already
handles this correctly (see convertMessages.ts L253-257 comment),
but the test expected undefined instead of empty string.
CC_Pure: was the last un-gated outbound
connection — it unconditionally sent a TCP+TLS handshake to
api.anthropic.com on every startup. Now checked against the central
privacy gate (CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1) and
skipped when enabled.
Verified via strace: zero remote connections after fix.
- Add Vite as alternative build (vite.config.ts, scripts/vite-plugin-*)
- Add dab04af7 RSS fix (distRoot, ripgrep path, post-build)
- Pull in packages/builtin-tools/ (+354 files)
- Pull in packages/agent-tools/, mcp-client/, acp-link/, weixin/
- Copy defines.ts from upstream for Vite compatibility
- Update package.json with Vite scripts and deps
- model.ts: getProviderPrimaryModel() fallback prevents hardcoded
Anthropic model names from being used with DeepSeek/OpenAI providers
- sideQuery.ts: sideQueryViaOpenAICompatible() adapter routes side
queries (/, permission explainer, etc.) to OpenAI/Grok API instead
of Anthropic when a third-party provider is configured
The buildDiffableContent and buildPrevDiffableContent fields were closures
capturing full system prompt and tool schema arrays (~300KB each). With 10
map entries × 2 closures, this held ~6MB of GC-unreachable memory.
Since recordPromptState already serializes the same data for hashing,
pre-computing the diffable content string has negligible marginal cost.
OpenAI's prompt_tokens includes cached tokens, but Anthropic's
input_tokens semantic excludes them. The adapter was mapping
prompt_tokens → input_tokens verbatim, causing downstream code
(cache hit rate, cost, autocompact) to double-count.
When ANTHROPIC_BASE_URL points to a non-Anthropic endpoint (e.g.
DeepSeek), the JSON-formatted user_id containing {, ", : characters
fails validation against ^[a-zA-Z0-9_-]+$. Send only the hex device_id
for third-party providers.
* fix: reorder tool and user messages for OpenAI API compatibility (#168)
Fixes#168
OpenAI requires that an assistant message with tool_calls be immediately
followed by tool messages. Previously, convertInternalUserMessage
output user content before tool results, causing 400 errors.
Now tool messages are pushed first.
* fix: 修复OpenAI兼容层中deferred tools处理问题
提交描述:
修复了在使用OpenAI兼容API时TaskCreate工具调用失败的问题。
问题:
- 当使用OpenAI兼容API模型时，调用TaskCreate工具出现"InputValidationError: The required
parameter `subject` is missing"错误
- OpenAI兼容层没有正确处理deferred tools的过滤逻辑，导致工具schema没有被正确发送给模型
修复:
1. 在OpenAI兼容层中添加了与Anthropic API路径一致的deferred tools处理逻辑
2. 导入必要的工具搜索相关函数: isToolSearchEnabled, extractDiscoveredToolNames,
isDeferredTool等
3. 实现工具过滤逻辑:
- 检查工具搜索是否启用
- 构建deferred tools集合
- 过滤工具列表: 只包含非deferred工具或已发现的deferred工具
- 为deferred tools设置deferLoading标志
4. 修正了extractDiscoveredToolNames函数的导入路径错误
影响:
- 解决了TaskCreate工具调用时的参数验证错误
- 确保OpenAI兼容层与Anthropic API路径在处理deferred tools时行为一致
- 支持工具搜索功能在OpenAI兼容模式下正常工作
修改的文件:
- src/services/api/openai/index.ts - 主要修复文件
测试建议:
1. 使用OpenAI兼容API模型时，TaskCreate工具应该可以正常调用
2. 如果工具搜索功能启用，可能需要先使用ToolSearchTool来发现TaskCreate工具
3. 验证工具调用时不再出现"InputValidationError"错误
这个修复确保了当使用OpenAI兼容API（如Ollama、DeepSeek、vLLM等）时，deferred
tools（如TaskCreate）能够被正确处理，解决了工具调用失败的问题。
* fix: 更新未发送工具架构提示，提供OpenAI兼容模型的使用步骤
* fix: Handle undefined command names in getCommandName function
- Modified getCommandName in src/types/command.ts to return empty string instead of undefined when cmd.name is undefined
- Added null checks in src/hooks/useTypeahead.tsx to safely handle command names
- Prevents "undefined is not an object" error when FEATURE_BUDDY=1 and FEATURE_FORK_SUBAGENT=1 are enabled
The error occurred because getCommandName(cmd) could return undefined when cmd.name was undefined, causing .length access to fail.
* feat: 支持自托管的 remote-control-server (#214)
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* feat: Add DeepSeek thinking mode support for OpenAI compatibility layer
- Add DeepSeek reasoning models support (deepseek-reasoner and DeepSeek-V3.2)
- Automatic thinking mode detection based on model name
- Inject thinking parameters in request body (both official API and vLLM formats)
- Preserve reasoning_content in message conversion for tool call iterations
- Extract buildOpenAIRequestBody() for testability
- Treat multimodal inputs (e.g. images) as new turn boundaries
- Fix env var cleanup in tests to prevent state leak
Signed-off-by: guunergooner <tongchao0923@gmail.com>
* docs: update contributors
---------
Signed-off-by: guunergooner <tongchao0923@gmail.com>
Co-authored-by: guunergooner <18660867+guunergooner@users.noreply.github.com>
