- Deleted `QwenAuthenticator`, internal `qwen_auth`, and `qwen_executor` implementations.
- Removed all Qwen-related OAuth flows, token handling, and execution logic.
- Cleaned up dependencies and references to Qwen across the codebase.

…-signature-thinking-blocks

fix(antigravity): use E-prefixed fake signature in strict bypass test

…ax-output-tokens-cap

fix(antigravity): cap maxOutputTokens using registry max_completion_tokens

…egistry JSON

feat(server): add HOME_ADDR and HOME_PASSWORD env var fallback

…ode-attribution

fix: strip Claude Code attribution from non-Anthropic translations

…name-loss-and-duplicates

fix(openai→claude): suppress empty/duplicate tool_use content_block_start

…proxy-dialer

fix(proxy): support HTTP CONNECT dialer

…call-id-length

Fix Claude-Codex long tool call IDs

…ions

- Introduced `-home-jwt` flag and `HOME_JWT` environment variable to provide JWT for mTLS certificate generation.
- Added new APIs to handle certificate requests, validate JWT claims, and manage local certificate files.
- Updated Home TLS configuration to support client certificates, keys, and dynamic server name resolution.

…eporting

- Added APIs to store, retrieve, and clone upstream response headers in context for detailed logging.
- Updated `RecordAPIResponseMetadata`, `RecordAPIWebsocketHandshake`, and related methods to capture response headers.
- Extended `UsageReporter` to include response headers in published usage records.
- Enhanced payload tests to validate response headers' integrity and persistence.
- Refactored `usage.Record` to support optional `ResponseHeaders` field.

…entation

- Implemented `xAI` provider for thinking configurations with support for reasoning.effort levels.
- Registered `xAI` in available providers and updated relevant APIs for compatibility.
- Added unit tests for `xAI` provider functionality, including fallback logic for unsupported levels.
- Integrated `xAI` with executor handling and ensured conformance with OpenAI-compatible standards.

…tput-token-cap

Cap Gemini max output tokens

…emini-thought-signatures

Fix Antigravity Gemini thought signatures

- Introduced OpenAI-compatible image model support in the API, enabling integration through image generation and editing endpoints.
- Added registry type for OpenAIImageModelType to classify and validate compatibility.
- Implemented request handling for OpenAI-compatible image models, including JSON and multipart formats.
- Enhanced executor methods to support OpenAI-compatible image streaming and non-streaming requests.
- Included tests to validate model registration, streaming behavior, and multipart payload formatting.

…erification

- Added support for `ClusterID`, `CAFingerprint`, and `EnrollmentSecret` in Home JWT claims.
- Implemented CA fingerprint normalization and verification for PEM and file-based certificates.
- Improved certificate request validation and error handling.
- Updated server-side logic to include `EnrollmentSecret` in certificate requests.

- Updated text formatting with bold emphasis for consistent branding.
- Refined wording for VisionCoder's promotion details in Chinese, Japanese, and English README.

…ion failover

- Introduced `homeRedisOperationTimeout` and `homeSubscriptionReceiveTimeout` constants for configurable timeouts.
- Enhanced Redis connection options with operation timeout settings and failover mechanisms.
- Implemented subscription failover logic on heartbeat timeouts to improve resilience.
- Updated message handling to support additional Redis event types, including Pong and Subscription.

Added a new section for Codex Switch tool with details.

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

Add Codex Switch tool to README

- Removed obsolete Redis protocol test cases and helper functions that were no longer relevant due to recent architecture changes.
- Streamlined remaining test files to align with updated Redis handling and connection management logic.

- Remove the early return in GetRequestErrorLogs that returned empty
  when RequestLog was enabled. Error log files are now always listed
  regardless of the RequestLog setting.

- Refactor logRequest to always write error-*.log files for failed
  requests (status >= 400), even when full request logging is enabled.
  Previously error logs were only written when RequestLog was disabled.

- Fix Claude usage reporting: when input_tokens < cache_read_input_tokens,
  add cached tokens to input tokens so the displayed total is accurate
  (e.g. "I 167.5K" instead of misleading "I 3").

- Add 4 tests covering Claude usage cache inclusion scenarios.

- Add publish.yml for GHCR Docker image builds
- Add workflow_dispatch to docker-image.yml and release.yaml
- Use secrets-based DOCKERHUB_REPO for docker-image.yml
- Remove upstream-only agents-md-guard and auto-retarget workflows

GetRequestErrorLogs previously only listed error-*.log files and
returned empty when request-log was enabled. Now it lists ALL request
log files (v1-messages-*.log, error-*.log, etc.) when request-log is
on, and only error-*.log when it's off.

Also fix writeErrorLog condition to trigger on any status >= 400
regardless of the force flag.

parseClaudeUsageNode previously dropped cache_creation_input_tokens
whenever cache_read_input_tokens > 0, causing CachedTokens, InputTokens
and TotalTokens to be under-reported when both cache fields were
present. Sum both cache fields into the cached total and use that sum
for both the CachedTokens field and the heuristic that decides whether
input_tokens already aggregates the cached portion.

- env.md: local/remote environment record
- journal.md: progress journal
- plan.md: immutable plan reference
- .gitignore: ignore .omc/.omx/scripts local tooling directories