router-for-me/CLIProxyAPIPlus v6.5.29-0 on GitHub

Changelog

6f9c23a #167
7063a17 #293
34855bc Fix model switch logic when quota is exceeded
56c8297 Handle data: without trailing space in streaming responses
cbf9a57 build(goreleaser): set CGO_ENABLED=0 for cli-proxy-api binaries
52e5551 chore(build): rename artifacts and adjust workflows for 'plus' variant
257621c chore(executor): update default agent version and simplify const formatting
93fa1d1 docs: add Amp CLI integration guide to Chinese documentation
8203bf6 docs: update README for CLIProxyAPI Plus and rename artifacts
cc3cf09 feat(auth): add AuthIndex for diagnostics and ensure usage recording
7757210 feat(auth): implement Antigravity OAuth authentication flow
2d84d2f feat(auth, executor, cmd): add Antigravity provider integration
d114d8d feat(config): add TLS support for HTTPS server configuration
8d23ffc feat(executor): add model alias mapping and improve Antigravity payload handling
ac06438 feat(executor, translator): enhance token handling and payload processing
aa57f32 feat(instructions): add detailed agent behavior guidelines for Codex CLI
e308288 feat(logging, middleware): add error-based logging support and error log management
bf116b6 feat(registry): add GPT-5.1 Codex Max model definitions and support
ee6429c feat(registry): add Gemini 3 Pro Image Preview model and remove Claude Sonnet 4.5 Thinking
17016ae feat(registry): add Gemini 3 Pro Preview model definition
01b7b60 feat(registry): add Gemini 3 Pro Preview model definition
d2e4639 feat(registry): add context length and update max tokens for Claude model configurations
371324c feat(registry): expand Gemini model definitions and support Vertex AI
fcd98f4 feat(runtime): add payload configuration support for executors
cf9b9be feat(runtime): extend executor support for GPT-5.1 Codex and variants
c1031e2 feat(translator): add Antigravity translation logic
8977121 feat(translator): add ThoughtSignature handling in Gemini request transformations
4eab141 feat(translator): add support for reasoning/thinking content blocks in OpenAI-Claude and Gemini responses
9d50a68 feat(translator): improve content processing and Antigravity request conversion
4307f08 feat(watcher): optimize auth file handling with hash-based change detection
f0711be fix(auth): prevent access to removed credentials lingering in memory
bb9955e fix(auth): resolve index reassignment issue during auth management
0087eec fix(build): append '-plus' suffix to version metadata in workflows and Goreleaser
9875565 fix(claude translator): ensure default token counts when usage data is missing
52c17f0 fix(executor): comment out redundant code for setting Claude system instructions
113db3c fix(executor): update antigravity executor to enhance model metadata handling
a748e93 fix(executor, auth): ensure index assignment consistency for auth objects
506f111 fix(handlers): refactor API response capture to append data safely
23a7633 fix(registry): update Thinking parameters and replace Gemini-3 Preview with Gemini-2.5 Flash Lite
db2d22c fix(runtime): simplify scanner buffer allocation in executor implementations
0a47b45 fix(translator): add conditional check for key renaming in Gemini tools
261f08a fix(translator): adjust key renaming logic in Gemini request processing
c8cee54 fix(translator): ensure partial content is retained while skipping encrypted thoughtSignature
7a8e00f fix(translator): handle missing parameters in Gemini tool schema gracefully
346b663 fix(translator): handle non-JSON output gracefully in function call outputs
72c7ef7 fix(translator): handle non-JSON output parsing for OpenAI function responses
39621a0 fix(translator): normalize function calls and outputs for consistent input processing
0bcae68 fix(translator): preserve raw JSON encoding in function call outputs
ddb0c0e fix(translator): reintroduce thoughtSignature bypass logic for model parts
1c815c5 fix(translator): simplify string handling in Gemini responses
1d0f030 refactor(api/config): centralize legacy OpenAI compatibility key migration
327cc70 refactor(auth): use customizable HTTP client for Antigravity requests
d50b0f7 refactor(executor): simplify Gemini CLI execution and remove internal retry logic
db81331 refactor(middleware): extract request logging logic and optimize condition checks
0586da9 refactor(registry): move Gemini 3 Pro Preview model definition to base set
1ccb016 refactor(runtime): centralize reasoning effort logic for GPT models
98596c0 refactor(translator): remove service_tier from Codex OpenAI request payload
8193392 Add AMP fallback proxy and shared Gemini normalization
c86545d Add Chinese README and update project files
3c0c61a Add Claude compatibility and enhance API handling
c62e45e Add Codex API key support and Gemini 2.5 Flash-Lite model documentation updates
67e0b71 Add Codex load balancing documentation and refine JSON handling logic
9b627a9 Add Docker Compose
3687963 Add Docker support with CI/CD workflow and usage instructions
2406cc7 Add GPT-5 Codex model support and configuration options in documentation
3e09bc9 Add Gemini 2.5 Flash-Lite Model
b3607d3 Add Gemini-compatible API and improve error handling
c0eaa41 Add Gemini-to-Gemini request normalization and passthrough support
6164f5c Add JSON annotations to configuration structs and new /config management endpoint
7e0fd1e Add Keep-Alive header
545dff8 Add OAuth support for Gemini CLI, Claude, Codex, and Qwen authentication
9ef76dc Add Object Storage
3acdec5 Add OpenAI Responses support
ce5d2ba Add OpenAI Responses support
ed8873f Add OpenAI compatibility support and improve resource cleanup
aa2f37d Add Qwen support
d292456 Add SOCKS5 and HTTP/HTTPS proxy support
040d66f Add SSH tunnel guidance for login fallback
c263398 Add Telegram group link to Chinese README for user support
5812229 Add .gitignore and ignore config.yaml
bea5f97 Add /v1/completions endpoint with OpenAI compatibility
c601542 Add ClaudeMessages handler for SSE-compatible chat completions
aa9fd05 Add FixCLIToolResponse for enhanced function call-response mapping
54ffb52 Add FunctionCallIndex to ConvertCliToOpenAIParams and enhance tool call handling
31a9e2d Add GeminiGetHandler, enhance Gemini functionality, and enable token counting
423faae Add GeminiModels handler and enhance API key validation
bf08646 Add archive configuration to .goreleaser.yml
d58cc55 Add claude code support
5ed79e5 Add debounce logic for file events to prevent duplicate reloads
c875088 Add dynamic log level adjustment and "type" field to auth files response
3c4dc07 Add file watcher for dynamic configuration and client reloading
db43930 Add management API handlers for config and auth file management
3704dae Add nil-check for GetRequestMutex across handlers to prevent potential panics
de7b850 Add openai codex support
f1d6f01 Add reasoning/thinking configuration handling for Claude and OpenAI translators
fcadf08 Add request logging capabilities to API handlers and update .gitignore
ad943b2 Add reverse mappings for original tool names and improve error logging
c4a42eb Add support for Codex API key authentication
4155805 Add support for Codex model in provider logic and update documentation for claude code
589ae6d Add support for Generative Language API Key and improve client initialization
e5ed2cb Add support for dynamic model providers
b84cbee Add support for forcing GPT-5 Codex model configuration
1c4183d Add support for localhost unauthenticated requests
9c9ea99 Add support for new GPT-5 model variants
273e1d9 Add system instruction support and enhance internal API handlers
512c8b6 Add token refresh handling for 401 responses across clients
0331660 Add token refresh handling for 401 responses across clients
b05d00e Add versioning support to build artifacts and log outputs
8d05489 Add versioning support to build artifacts and log outputs
ebf2a26 Avoid unnecessary config.yaml reloads via hash check
b3c534b Build instructions reformatting
aacfcae Codex CLI - setting 'store = false'
9be56fe Correct config in README.md
ef8820e Default tokenType to an empty string instead of "gemini" in watcher.go and run.go.
00f33f5 Enhance Gemini request handling for contents support and improve error logging
e64fa48 Enhance Gemini request handling with fallback support for contents
58b7afd Enhance HTTP server with custom multiplexer in Auth flow
0449fef Enhance OAuth handling for Anthropic, Codex, Gemini, and Qwen tokens
551bc1a Enhance README formatting and update .dockerignore
6d2f7e3 Enhance parseArgsToMap with tolerant JSON parsing
b125410 Enhance client reload process with new OpenAI compatibility support
3dd0844 Enhance logging for API requests and responses across executors
7cb76ae Enhance quota management and refactor configuration handling
fa8d949 Enhance response and request handling in translators
35daffd Ensure auth directory existence before processing tokens in run.go
ae06f13 Extract argument parsing logic into parseArgsToMap helper function
ade279d Feature: #103
74bae32 Filter OpenAI models response to include only essential fields (id, object, created, owned_by).
3b2ab0d Fix SSE headers initialization for geminiStreamGenerateContent and internalStreamGenerateContent
beff928 Fix alt parameter handling in URL construction
ebcd4db Fix activation URL extraction logic and improve warning message formatting
3d8d02b Fix amp v1beta1 routing and gemini retry config
7353bc0 Fix bug: #38 about lobechat cors policy
8c2063a Fix log key name from gpt-5-codex to force-gpt-5-codex for consistency
f9f2333 Fix model name update during quota check to avoid incorrect logging
e9e0016 Fix some bugs.
11f090c Fixed #102
b641d90 Fixed #91
99c9f30 Fixed bug #38
4576f99 Fixed: #121
4477c72 Fixed: #129 #123 #102 #97
735b213 Fixed: #137
a552a45 Fixed: #140 #133 #80
eadccb2 Fixed: #148
847c250 Fixed: #172
fd2b235 Fixed: #193
a7d105b Fixed: #223
8ae8a5c Fixed: #233
75b57bc Fixed: #246
772fa69 Fixed: #254
5937b8e Fixed: #260
e5e9859 Fixed: #263
cbcfeb9 Fixed: #291
d291eb9 Fixed: #302
ed9f6e8 Fixed: #337
a4a26d9 Fixed: #339
7e30157 Fixed: #354
b727e4e Fixed: #86
d6f6712 Fixed: #97
f4977e5 Ignore GEMINI.md file
1c92034 Implement IP-based rate limiting and ban mechanism for management API
3b4634e Improve getClient logic with optional content generation flag
ead71fb Improve error logging and add user guidance for issue reporting
dff31a7 Improved the /v1/models endpoint
1dccdb7 Merge branch 'cookie_snapshot' into dev
c52255e Merge branch 'dev'
d42384c Merge branch 'dev'
1cd275f Merge branch 'dev'
67a4fe7 Merge branch 'dev'
9ff38dd Merge branch 'dev' into feat-amp-cli-module
2e5681e Merge branch 'dev' into feat/claude-thinking-and-beta-headers
fa762e6 Merge branch 'dev' of github.com:luispater/CLIProxyAPI into dev
e0d1314 Merge branch 'main' into dev
2a274d4 Merge branch 'main' into gemini-web
edf9d9b Merge branch 'main' of github.com:luispater/CLIProxyAPI
1a9f939 Merge branch 'plus-dev' into feature/github-copilot-auth
8c947ca Merge branch 'vertex' into dev
65f47c1 Merge pull request #1 from chaudhryfaisal/main
1ada33a Merge pull request #104 from router-for-me/cloud
1834c65 Merge pull request #107 from router-for-me/gemini-web
f6e713a Merge pull request #110 from router-for-me/cloud
2513d90 Merge pull request #111 from router-for-me/cloud
0508c9f Merge pull request #113 from sususu98/main
71faa19 Merge pull request #114 from router-for-me/management
f2710c0 Merge pull request #116 from router-for-me/log
4fdbdf7 Merge pull request #117 from router-for-me/pg
9072acc Merge pull request #118 from router-for-me/config
32d01a6 Merge pull request #125 from router-for-me/object
ac4f52c Merge pull request #127 from router-for-me/usage
f58d0fa Merge pull request #130 from router-for-me/log
8e95c5e Merge pull request #134 from router-for-me/hg
674393e Merge pull request #139 from router-for-me/log
0e91e95 Merge pull request #145 from router-for-me/path
c5dcbc1 Merge pull request #146 from router-for-me/iflow
fed6f3e Merge pull request #147 from router-for-me/config
5b3fc09 Merge pull request #151 from VjayC/add-subtitle-translator
ba4c114 Merge pull request #16 from hkfires/main
5da5674 Merge pull request #161 from router-for-me/aistudio
3e20b00 Merge pull request #163 from router-for-me/nb
ac3d47e Merge pull request #173 from tobwen/feature/dynamic-model-routing
d6272d3 Merge pull request #177 from router-for-me/aistudio
8dba32a Merge pull request #185 from router-for-me/thinking
3e7b645 Merge pull request #186 from router-for-me/doc
96c7271 Merge pull request #191 from router-for-me/gemini
4d08046 Merge pull request #194 from router-for-me/gemini-key
32c964d Merge pull request #221 from router-for-me/gemini
b9eef45 Merge pull request #222 from router-for-me/api
d4064e3 Merge pull request #225 from jeffnash/feat/codex-mini-variants
3264605 Merge pull request #226 from router-for-me/headers
87291c0 Merge pull request #227 from router-for-me/api
7b9cfbc Merge pull request #23 from luispater/dev
6ae1dd7 Merge pull request #230 from router-for-me/api
09ecba6 Merge pull request #237 from TUGOhost/feature/support_auto_model
1ede134 Merge pull request #249 from ben-vargas/fix-gpt5-1-reasoning
faa483b Merge pull request #257 from lollipopkit/main
56a05d2 Merge pull request #26 from luispater/flash-lite
567227f Merge pull request #268 from router-for-me/tools
14ddfd4 Merge pull request #270 from router-for-me/iflow
c40e005 Merge pull request #274 from router-for-me/log
9acfbcc Merge pull request #275 from router-for-me/iflow
798f65b Merge pull request #28 from luispater/bugfix
618511f Merge pull request #280 from ben-vargas/feat-enable-gemini-3-cli
670ce2e Merge pull request #285 from router-for-me/iflow
b70bfd8 Merge pull request #287 from ben-vargas/feat-amp-cli-module
4f18809 Merge pull request #29 from luispater/bugfix
b4d15ac Merge pull request #296 from router-for-me/antigravity
d1cdedc Merge pull request #303 from router-for-me/image
7c3c24a Merge pull request #306 from router-for-me/usage
d10ef7b Merge pull request #31 from luispater/docker-build-sh
d1736cb Merge pull request #315 from router-for-me/aistudio
0ceee56 Merge pull request #318 from router-for-me/log
1aa0b6c Merge pull request #322 from ben-vargas/feat-claude-opus-4-5
1305f2f Merge pull request #33 from luispater/docker
9c1e3c0 Merge pull request #334 from nestharus/feat/claude-thinking-and-beta-headers
0832122 Merge pull request #340 from nestharus/fix/339-thinking-openai-gemini-compat
3675542 Merge pull request #343 from router-for-me/misc
179b8aa Merge pull request #36 from luispater/ssh-tunnel
fa087ee Merge pull request #362 from em4go/feature/github-copilot-auth
18b5c35 Merge pull request #366 from router-for-me/blacklist
54a9c4c Merge pull request #371 from ben-vargas/test-amp-tools
d4dc7b0 Merge pull request #39 from luispater/config_hash
bd68472 Merge pull request #41 from kaixxx/main
7f0c9b1 Merge pull request #43 from kyle-the-dev/fix/gemini-schema-sanitization
9ec8478 Merge pull request #44 from luispater/gemini-web
6ad5e07 Merge pull request #46 from router-for-me/cookie_snapshot
b449d17 Merge pull request #47 from router-for-me/dev
bc376ad Merge pull request #49 from router-for-me/gemini-web
c16a989 Merge pull request #50 from router-for-me/auth-dev
b07ed71 Merge pull request #51 from router-for-me/gemini-web
83a1fa6 Merge pull request #52 from router-for-me/gemini-web
c28a5d2 Merge pull request #54 from router-for-me/v6-test
c9ce3a5 Merge pull request #55 from router-for-me/v6-test
45d382f Merge pull request #57 from router-for-me/v6-test
c159180 Merge pull request #58 from router-for-me/v6-test
361a69f Merge pull request #59 from router-for-me/gemini-web-v6
68be2f0 Merge pull request #60 from router-for-me/v6-test
e9d2905 Merge pull request #61 from router-for-me/gemini-web
cc8c46d Merge pull request #62 from router-for-me/dev
830b51c Merge pull request #63 from router-for-me/gemini-web
fc103f6 Merge pull request #64 from router-for-me/bugfix
80b6a95 Merge pull request #65 from router-for-me/gemini-web
7e54156 Merge pull request #66 from router-for-me/log
9bbe644 Merge pull request #67 from router-for-me/rr
4fd95ea Merge pull request #68 from router-for-me/log
c678ca2 Merge pull request #69 from router-for-me/reload
250628d Merge pull request #70 from router-for-me/log
8cfa228 Merge pull request #71 from ben-vargas/fix-max_output_tokens-codex-oauth
8e88a61 Merge pull request #72 from router-for-me/log
beba2a7 Merge pull request #78 from router-for-me/gemini
cf5476e Merge pull request #82 from router-for-me/mgmt
6b413a2 Merge pull request #83 from router-for-me/oaifix
389c8ec Merge pull request #85 from router-for-me/iflow
4bc8a52 Merge pull request #90 from router-for-me/dethink
a68e0dd Merge pull request #94 from router-for-me/gemini-web
d6721e4 Merge pull request #95 from router-for-me/gemini-web
8056af4 Merge pull request #99 from router-for-me/banana
3c5390a Merge remote-tracking branch 'origin/v6' into v6
47b5ebf Modify docker compose for remote image and local build
0371062 Normalize select to STRING type in Gemini OpenAI request outputs
5ec6450 Numerous Comments Added and Extensive Optimization Performed using Roo-Code with CLIProxyAPI itself.
4ecc798 Reduce the size of gemini-web's package files
ef68a97 Refactor API handlers and proxy logic
1483c31 Refactor API handlers organization and simplify error response handling
9102ff0 Refactor API handlers to implement retry mechanism with configurable limits and improved error handling
e73f165 Refactor API handlers to streamline response handling
512f2d5 Refactor API request flow and streamline response handling
6bbdf67 Refactor Gemini API handlers to standardize response field names and improve model descriptions
70e9169 Refactor cliCancel calls to remove unused resp argument across handlers.
79acea5 Refactor authentication and service initialization code
f49a530 Refactor client handling and improve error responses
7209fa2 Refactor client map construction to include all client types and enhance callback updates
8c555c4 Refactor codebase
5aba4ca Refactor docker-compose config for simplicity and consistency
c5cc238 Refactor error handling and variable declarations in browser and logging modules
20985d1 Refactor executor error handling and usage reporting
582280f Refactor token management, client initialization, and project handling
e0bff9f Refactor translator packages for OpenAI Chat Completions
305916f Refactor translator packages for OpenAI Chat Completions
e3994ac Refactor translator packages for OpenAI Chat Completions
e11637d Refactor translator packages for OpenAI Chat Completions
1f46dc2 Refactor translator packages for OpenAI Chat Completions
bff6f66 Refactor translator packages for OpenAI Chat Completions
57ead9a Refactor user onboarding and token management
d6037e5 Refine .gitignore and .dockerignore files
d00604d Refine Codex instructions for GPT-5 use case
0983119 Remove API key truncation in Gemini client ID generation
b6f8677 Remove commented debug logging in ConvertOpenAIResponsesRequestToGeminiCLI
b0f7273 Remove redundant dataUglyTag parsing logic in streaming responses
d4f5ec2 Removed the cookie snapshot feature.
8a2285e Reorganize and reintroduce Management API section in README files
d4709ff Replace path with filepath for cross-platform compatibility
4375822 Resolve logsDir path relative to configuration directory in FileRequestLogger
4e67cd4 Resolve relative logsDir to executable directory in FileRequestLogger
edeadfc Restrict CLI access to localhost and update README for Gemini compatibility
156e3b0 Restrict management key validation to non-localhost requests only
d193307 Revert "feat(translator): Pass through imageConfig"
3f78401 Set the default Docker timezone to Asia/Shanghai
d880d1a Set the http request header and update client metadata handling
7a6adfa Suppress debug logs for model routing and ignore empty tools arrays
9319602 UPDATE README
09b9d3b Unlock mutex before returning error in handlers.go to prevent deadlocks
ee0a91f Update GitHub funding model with username
9c6832c Update LICENSE to reflect extended copyright ownership
caf386c Update MANAGEMENT_API.md with expanded documentation for endpoints
6d30faf Update Management API CN docs for authentication requirements
bdac24b Update PassthroughGeminiResponseStream to handle [DONE] marker
e074e95 Update README
2a2a276 Update README
1bb0d11 Update README
f1d9364 Update README documentation to clarify auth-dir configuration for Windows users
c2b2c9e Update README documentation to clarify auth-dir configuration for Windows users
36ee21e Update README to include Codex support and multi-account load balancing details
30d5d87 Update README to include Codex support and multi-account load balancing details
2b1762b Update README to reflect usage of Qwen models instead of Claude models
0652241 Update README to rename gpt-5-nano to gpt-5-minimal in usage examples
00bd6a3 Update .goreleaser.yml to include config.example.yaml instead of config.yaml in release assets
d2394b0 Update .goreleaser.yml to specify archive formats for different OS targets
ed6e775 Update config key gpt-5-codex to force-gpt-5-codex for clarity in example configuration file
4883349 Update doc
0b02693 Update example configuration file (config.example.yaml)
9fce13f Update internal module imports to use v5 package path
1aad033 Update issue templates
46fa32f Update log level in OpenURL function from Debug to Info
8dd7f8e Update model name to include release date in API handlers
f38b78d Update the README to include Docker Compose usage instructions
ef922b2 Update workflows and build process for enhanced metadata injection
d410421 Updated README.md
b7d6ae1 Windows build instructions
240e782 add default medium reasoning case for gpt-5-codex-mini
ec354f7 add default medium reasoning case for gpt-5-codex-mini
7b546ea build(goreleaser): inject build metadata into binary during release
3be6175 chore(auth): add debug log for iflow token response body
19c32f5 chore(config): comment out API keys and update default settings for logging and usage statistics
0db0b03 chore(docs): add and refine package-level comments across modules
72325f7 chore(docs): remove outdated allow-localhost-unauthenticated section from API docs
4832297 chore(docs): update README with GUI client, WebUI links, and detailed SDK documentation
c6b3913 chore(executor): add debug logging for API request errors
c5df806 chore(executor): add debug logging for API request errors
5010b09 chore(gitignore): add cli-proxy-api to ignored files
aa25820 chore(log): Refine debug messages for config reloads
837ae1b chore(logging): add debug logs for executor Refresh methods
1bbbd16 chore(logging): clarify 429 rate-limit retries in Gemini executor
cb83985 chore(server): remove debug println statement from server.go
f9a170a chore(watcher): Clarify API key client reload log message
80f6d6f chore(watcher): add YAML serialization for config change tracking and improve quota-exceeded debug logs
06a3e97 chore: Ignore .serena directory
70ee4e0 chore: remove unused httpx sdk package
03334f8 chore: revert gitignore change
af82855 chore: update .gitignore include .env
fb76071 ci(homebrew): add workflow to auto-bump Homebrew formula on release
9ff21b6 ci(homebrew): remove workflow for Homebrew formula bump
5546c9d ci(homebrew): trigger workflow on tag push instead of release event
848a620 ci: add GitHub Action to block changes under internal/translator directory in PRs
c4e3646 docs(config): expand model exclusion examples
695eaa5 docs(instructions): add Codex operational and review guidelines
41975c9 docs(management): document remote-management.disable-control-panel option
97af785 docs(readme): add CLIProxyAPI Linux installer instructions
6ec0288 docs(readme): add MANAGEMENT_PASSWORD environment variable documentation
5891785 docs(readme): clarify model definition and add usage example for undefined models
92bb642 docs(readme): document Git-backed configuration and token store setup
3ffd87d docs(sdk-access): add SDK usage guides in English and Chinese
8aaed4c feat(aistudio): support non-streaming responses
c32e013 feat(aistudio): track Gemini usage and improve stream errors
7b7871e feat(api): add oauth excluded model management
28218ec feat(api): implement granular client type metrics in server updates
20f3e62 feat(auth): Add stable label to Gemini Web tokens for logging
f228a4d feat(auth): Enhance Gemini web auth with flexible input and UI
a45d210 feat(auth): Improve Gemini web auth with email label detection
8ca041c feat(auth): Use user info for iFlow auth identifier
2724630 feat(auth): add Gemini Web token saving endpoint
3a9ac7e feat(auth): add GitHub Copilot authentication and API integration
4fd70d5 feat(auth): add callback forwarder support for Web UI in OAuth flows
b52a5cc feat(auth): add iFlow cookie-based authentication support
f1f24f5 feat(auth): add iFlow provider support with multi-account load balancing
96cebd2 feat(auth): add interactive prompts to Gemini web auth flow
5983e3e feat(auth): add oauth provider model blacklist
f6de2a7 feat(auth): add per-key proxy support and enhance API key configuration handling
8fc7387 feat(auth): centralize token store management and enhance persistence
e68a603 feat(auth): enable model suspension and resumption logic in AuthManager
ac3ecd5 feat(auth): enhance Gemini CLI onboarding and project verification
8fa52e9 feat(auth): enhance Gemini web auth with macOS support and input fallback
1c91823 feat(auth): enhance DoLogin to include Gemini CLI user onboarding flow
6046a8c feat(auth): enhance watcher with asynchronous dispatch and buffering
792ec49 feat(auth): implement incremental auth updates with queue integration
2eef687 feat(auth): improve OpenAI compatibility normalization and API key handling
3933762 feat(auth): include email attribute in auth files response
4008be1 feat(auth): introduce auth.providers for flexible authentication configuration
ab55373 feat(auth): introduce per-model state tracking and enhanced error handling
7c642be feat(auth): normalize OpenAI compatibility entries and enhance proxy configuration
2e836ce feat(auth): standardize last_refresh metadata handling across executors
a4767fd feat(auth, docs): add SDK guides and local password support for management
9761ac5 feat(auth, docs): add label support for Gemini web token management
ce569ab feat(buildinfo): add build metadata and expose via HTTP headers
6b23e2d feat(claude): add Claude 4.5 Haiku model definition
c7196ba feat(claude): add model alias mapping and improve key normalization
d0e694d feat(claude): add thinking model variants and beta headers support
41577bc feat(claude): map Anthropic 'thinking' to Gemini thinkingBudget
11b0efc feat(claude-executor): add ZSTD decoding support for Claude executor responses
514f5a8 feat(cliproxy): Rebind auth executors on config change
49c52a0 feat(cliproxy): enhance OpenAI compatibility detection and executor registration
24446a4 feat(cliproxy): skip persisting runtime-only websocket auths
022aa81 feat(cliproxy): support wildcard exclusions for models
829dd06 feat(cliproxy/auth): restructure auth candidate selection and ensure synchronization
fc6aa8e feat(config): Gracefully handle empty or invalid optional config
5fd4a8b feat(config): Remove OpenAI providers with empty BaseURL
0aa8706 feat(config): Treat empty BaseURL for Codex keys as deletion
f8cebb9 feat(config): add per-key model blacklist for providers
4c033b3 feat(config): disable logging and usage stats by default
cfb9cb8 feat(config): support HTTP headers across providers
4bc1ed6 feat(config): use block style for YAML maps/lists; keep [] for empty
0d8134a feat(config): use block style for YAML maps/lists; keep [] for empty
25ba042 feat(config, usage): add usage-statistics-enabled option and dynamic toggling
ac59023 feat(executor): add CountTokens support across all executors
e783923 feat(executor): add debug logs for rate-limiting retries in Gemini CLI executor
6a3de3a feat(executor): add intelligent retry logic for 429 rate limits
4ba5b43 feat(executor): share SSE usage filtering across streams
1b2e3dc feat(gemini): Implement pseudo-streaming and improve context reuse
7c1c4ee feat(gemini): add Gemini API key endpoints
a53c84d feat(gemini): apply default safety settings across request translators
3ac5f05 feat(gemini): prefer official reasoning fields, add extra_body(cherry studio) fallback
d0aa741 feat(gemini-cli): add multi-project support and enhance credential handling
e313d39 feat(gemini-executor): implement CountTokens method with request translation and API integration
5cb3782 feat(gemini-translators): set include_thoughts when mapping thinking
82187bf feat(gemini-web): Add conversation affinity selector
8858e07 feat(gemini-web): Add support for custom auth labels
41effa5 feat(gemini-web): Add support for image generation with Gemini models through the OpenAI chat completions translator.
deaa64b feat(gemini-web): Add support for real Nano Banana model
9bb7df7 feat(gemini-web): Enable config hot-reload and fix Gem selection
22a6933 feat(gemini-web): Implement proactive PSIDTS cookie rotation
f2201da feat(gemini-web): Index and look up conversations by suffix
50c8f7f feat(gemini-web): Inject fallback text for image-only flash model responses
2175a10 feat(gemini-web): Introduce stable account label for identification
6080527 feat(gemini-web): Namespace conversation index by account label
43665cb feat(gemini-web): Replace code-mode with flexible gem-mode
e4dd22b feat(gemini-web): squash all features and fixes for gemini-web
c8029b7 feat(iflow): Add User-Agent header to API requests
3f4f8b3 feat(iflow): add cookie-based authentication endpoint
4504ba5 feat(iflow): add masked token logs; increase refresh lead to 24h
395164e feat(log): Add separator when saving client credentials
9f45806 feat(logging): centralize sensitive header masking
f1c4caf feat(logging): integrate logrus with custom Gin middleware for enhanced request logging and recovery
cf734f7 feat(logging): introduce centralized logging with custom format and Gin integration
6d98a71 feat(login): add interactive project selection and improve onboarding flow
943a8c7 feat(logs): add limit query param to cap returned logs
2e328dd feat(management): Improve logging for management route status
ab76cb3 feat(management): add Vertex service account import and WebSocket auth management
72cb268 feat(management): add log retrieval and cleanup endpoints
4a31f76 feat(management): add proxy support for management asset synchronization
c589c0d feat(management): add support for control panel asset synchronization
c9fc033 feat(management): support in-memory auth listing with disk fallback
b5ad978 feat(managementasset): Authenticate GitHub API requests
c75e524 feat(managementasset): add MANAGEMENT_STATIC_PATH override
57195fa feat(managementasset): enforce 3-hour rate limit on management asset update checks
f8dcd70 feat(mgmt): support YAML config retrieval and updates via /config.yaml
d03a75d feat(middleware): add path exclusion for request logging in management routes
b2ca493 feat(models): add support for Claude 4.5 Sonnet model in registry
e41d127 feat(openai-compat): enhance provider key handling and model resolution
9253bdb feat(provider): Introduce dedicated provider type for Gemini-Web
562a49a feat(provider/gemini-web): Prioritize explicit label for account identification
6b5aefc feat(proxy): add SOCKS5 support and improve proxy handling
9abcaf1 feat(registry): Add display names and descriptions for iFlow models
43f007c feat(registry): add Claude Opus 4.5 model definition
fcb0293 feat(registry): add GPT-5 Codex Mini model variants
2d5d06c feat(registry): add Qwen3 Vision Model definition #164
07da781 feat(registry): add client model support check for executor filtering
3d7aca2 feat(registry): add thinking budget support; populate Gemini models
782bba0 feat(registry): enable gemini-3-pro-preview for gemini-cli provider
5dced4c feat(registry): unify Gemini models and add AI Studio set
d45ebff feat(registry, executor): add support for gemini-2.5-flash-image model
b2cdbbd feat(registry, executor): add support for glm-4.6 model and enhance Gemini CLI token handling
20787cd feat(registry, executor, util): add support for gemini-2.5-flash-image-preview and improve aspect ratio handling
bbdd68a feat(registry/runtime): add Gemini 2.5 model and increase buffer sizes
9d42e4b feat(runtime): add User-Agent headers to codex and claude executors
de796ac feat(runtime): introduce newProxyAwareHTTPClient for enhanced proxy handling
12c09f1 feat(runtime): remove previous_response_id from Codex executor request body
19a0488 feat(runtime): track antigravity usage and token counts
19b10cb feat(sdk/auth): extend Gemini Web refresh lead to 1 hour
ac01c74 feat(server): Add cloud deploy mode
5a50856 feat(server): add keep-alive endpoint with timeout handling
506e2e1 feat(server): inject build metadata into application logs and container image
b1fee5d feat(server): introduce DefaultConfigPath for streamlined configuration
50c8448 feat(store)!: Lock AuthDir when use gitstore/pgstore
78989d6 feat(store)!: Lock AuthDir when use gitstore/pgstore
42087d5 feat(store): add PostgreSQL-backed config store with env selection
5123cfd feat(store): add PostgreSQL-backed config store with env selection
a83978f feat(store): introduce GitTokenStore for token persistence via Git backend
a602ae8 feat(translator): Add support for openrouter image_config
01be94a feat(translator): Map OpenAI modalities to Gemini responseModalities
c5d7137 feat(translator): Pass through imageConfig
2f477df feat(translator): add built-in translator registry and helpers
ede4471 feat(translator): add default thinkingConfig for gemini-3-pro-preview
40255b1 feat(translator): add usage metadata aggregation for Claude and OpenAI responses
6524d3a feat(translator): add usage metadata mapping for Gemini responses
6d4b43d feat(translator): add user metadata generation for Claude transformation requests
644a3ad feat(translator): emit response.output_item.done event for reasoning summary completion
5999864 feat(translator): enhance OpenAI Gemini request handling for mixed content
c945e35 feat(translator): improve Claude request handling with enhanced content processing
dc8d320 feat(translator): support image size and googleSearch tools
31659c7 feat(translator/gemini-cli): support inline image data in responses
3dd5095 feat(translators): add token counting support for Claude and Gemini responses
5090d98 feat(translators): improve system instruction extraction and input handling for OpenAI and Claude responses
d41ff20 feat(translators): improve system instruction extraction and input handling for OpenAI and Claude responses
9df04d7 feat(translators/claude): implement non-streaming response parsing for various translator types
19609db feat(usage): add in-memory usage statistics tracking and API endpoint
32a8102 feat(usage): add support for tracking request source in usage records
3ade03f feat(usage): implement usage tracking infrastructure across executors
717eadf feat(vertex): add support for Vertex AI Gemini authentication and execution
592f6fc feat(vertex): add usage source resolution for Vertex projects
d6bd6f3 feat(vertex, management): enhance token handling and OAuth2 integration
88f06fc feat(watcher): Log detailed diff for openai-compatibility on reload
02e28bb feat(watcher): add support for proxy_url in auth metadata
40f7061 feat(watcher): debounce config reloads to prevent redundant operations
39e398a feat(watcher): ensure reload callback triggers before auth refresh
a7d2f66 feat(watcher): expand event handling for config and auth JSON updates
f60ef0b feat(watcher): implement incremental client hot-reloading
3297f75 feat(watcher, auth): add stable hash for OpenAI compatibility models
359b8de feat(ws): add WebSocket auth
9ad0f3f feat: Add Amp CLI integration with comprehensive documentation
4657c98 feat: Add option to disable management control panel
580ec73 feat: Add support for Gemini Web via cookie authentication
b839e35 feat: Add support for iFlow provider
ad4d045 feat: Restore API key config in config file
9678be7 feat: add DisableCooling configuration to manage quota cooldown behavior
92f4278 feat: add auto model resolution and model creation timestamp tracking
df66046 feat: add client availability tracking and error handling improvements
172f282 feat: add graceful shutdown for streaming response handling
0d89a22 feat: add handling for function call finish reasons in OpenAI response conversion
24f243a feat: add support for Gemini 2.5 Flash image preview alias
3839d93 feat: add websocket routing and executor unregister API
3569e57 feat: enhance quota management with backoff levels and cooldown logic
d5ad5fa feat: enhance request logging and account handling in CLI proxy
243bf5c feat: enhance tool call handling in OpenAI response conversion
67f5538 feat: implement management asset configuration and auto-updater
869a3df feat: implement model-specific Codex instructions for GPT-5
0607e52 feat: implement token refresh support for executors
d225558 feat: improve error handling with added status codes and headers
f81898c feat: introduce custom provider example and remove redundant debug logs
d16599f feat: prefer util.WritablePath() for logs and local storage
827bd6e first commit
08856a9 fix(access): Exclude inline provider from reconciliation changes
b6d5ce2 fix(access): Force rebuild of aliased provider configurations
6d822cf fix(access): rebuild providers for specific AccessProviderTypeConfigAPIKey changes
7f266aa fix(aistudio): ensure colon-spaced JSON in responses
7459c2c fix(aistudio): remove generationConfig and tools when action is countTokens
c99d0df fix(aistudio): remove no-op executor unregister on WS disconnect
62bfd62 fix(aistudio): strip Gemini generation config overrides
ea6065f fix(aistudio): strip usage metadata from non-final stream chunks
db1119d fix(amp): add /threads.rss root-level route for AMP CLI
7ae0032 fix(amp): enable OAuth fallback for Gemini v1beta1 routes
72d8226 fix(amp): filter context-1m beta header for local OAuth providers
608d745 fix(api): Enable management routes based on secret key presence
1f6a384 fix(api): omit auth file entries lacking path unless runtime-only
eac8b1a fix(auth): Correct iFlow OAuth callback port to 11451
759bb88 fix(auth): Improve file-based auth handling and consistency
e836b4a fix(auth): Make round-robin auth selection deterministic
64f4c18 fix(auth): Return error if iFlow API key fetch fails
c63dc7f fix(auth): Scope unavailability checks to specific models
5bf7a95 fix(auth): address index logic bug and remove redundant conditions
6a19135 fix(auth): fix runtime auth reload on oauth blacklist change
ec08500 fix(auth): resolve drain label for correct loop termination in cliproxy service
27faf71 fix(auth): use fixed antigravity callback port 51121
c73b3fa fix(claude translator): guard tool schema properties
e73cdf5 fix(claude): ensure max_tokens exceeds thinking budget for thinking models
5ab0854 fix(claude): track message_start event in streaming response
d9f8129 fix(client): Add reason to unregistration to skip persistence
f17ec7f fix(client): Prevent overwriting auth file on update
6bd37b2 fix(client): Prevent overwriting auth file on update
b0f2ad7 fix(cliproxy): Clear stale compatibility model registrations
dd1e0da fix(cliproxy): Use model name as fallback for ID if alias is empty
b86ed46 fix(codex): Remove reasoning.effort for default gpt-5-codex model
da72ac1 fix(config): Inline SDKConfig for proper YAML parsing
16be3f0 fix(config): dedupe and normalize Gemini keys and headers
2021ae3 fix(config): skip persisting empty API key and compat entries
5c65938 fix(config): stabilize YAML sequence merges by reordering items
78738ca fix(config): treat directory as absent for optional config in cloud deploy mode
c8f20a6 fix(executor): add logging and prompt cache key handling for OpenAI responses
38cfbac fix(executor): adjust Anthropic-Beta header handling for consistent API requests
5be4d22 fix(executor): ensure consistent header application in Claude API requests
ef7e820 fix(executor): ensure usage reporting for upstream responses lacking usage data
8356b35 fix(executor): expire stop chunks without usage metadata
7dd93a4 fix(executor): only apply thinking config to supported models
663b9b3 fix(executor): pass authID to relay instead of provider
ed23472 fix(executor): prevent streaming from 429 response when fallback available
0ff094b fix(executor): prevent streaming on failed response when no fallback
89b0d53 fix(executor): remove safetySettings from payload for Gemini requests
64774a5 fix(executor): remove safetySettings from payload in token counting request
67ad26c fix(executor): remove default reasoning effort for gpt-5-codex-mini
3ce1b41 fix(executor): remove outdated Gemini model previews from CLI fallback order
30d448e fix(executor): update model name from codex-mini-latest to gpt-5-codex-mini
c62ecc2 fix(gemini): Disable thinking config for incompatible models
88e5662 fix(gemini): filter SSE usage metadata in streams
48bbd9e fix(gemini): handle "[DONE]" chunk, trim "data:" prefix, and remove session_id from requests
7061cd6 fix(gemini): map responseModalities to uppercase IMAGE/TEXT
166fa9e fix(gemini): parse stream usage from JSON, skip thoughtSignature
b018072 fix(gemini): trim "data:" prefix in raw JSON and resolve variable shadowing in stream translation
eb2549a fix(gemini): update response template to omit finishReason until known
58d3036 fix(gemini-cli): correctly strip/normalize thinking config by model
abc2465 fix(gemini-cli): ignore thoughtSignature and empty parts
e370f86 fix(gemini-executor): uppercase responseModalities
1d70336 fix(gemini-web): Correct ambiguity check in conversation lookup
108dcb7 fix(gemini-web): Correct history on conversation reuse
bb6ec7c fix(gemini-web): Correct inaccurate cookie refresh log message
73cf491 fix(gemini-web): Correct stream translation and reduce auth refresh lead
d33a89b fix(gemini-web): Ignore tool messages to fix sticky selection
1d7abc9 fix(gemini-web): ensure colon spacing in JSON output for compatibility
b285b07 fix(iflow): adjust auth filename email sanitization
7980f05 fix(iflow): streamline authentication callback handling and improve error reporting
cd0b1be fix(log): Reduce noise on metadata updates and provider sync
4923237 fix(log): Trim trailing newlines to prevent blank log lines
314125e fix(logging): Prevent race conditions in FileStreamingLogWriter
df3b006 fix(logs): ignore ENOENT when truncating default log file
43095de fix(management): exclude disabled runtime-only auths from file entries
dc804e9 fix(management): improve error handling and normalize YAML comment indentation
51d2766 fix(management): sanitize keys and normalize headers
f335aee fix(postgresstore): normalize config line endings for DB/disk writes
d6aa1e5 fix(postgresstore): normalize config line endings for DB/disk writes
2717ba3 fix(registry): Avoid provider update when new provider is empty
63af4c5 fix(registry): Fix provider change logic for new models
a887a33 fix(registry): Handle duplicate model IDs in client registration
e18e288 fix(registry): Remove gemini-2.5-flash-image Gemini models from gemini cli and add gemini-2.5-flash-image preview to AIStudio
e1de042 fix(registry): Reset client status on model re-registration
7516ac4 fix(registry): add gemini-3-pro-preview-11-2025 model to Gemini CLI model definitions
0895533 fix(registry): correct Claude Opus 4.5 created timestamp
d745f07 fix(registry): replace Gemini model list with updated stable and preview versions
9c5ac29 fix(request_logging): update logging conditions to include only /v1 paths
c419264 fix(responses): handle empty and invalid rawJSON in ConvertOpenAIChatCompletionsResponseToOpenAIResponses
cfbaed0 fix(runtime): remove gpt-5.1 minimal effort variant
d32bb9d fix(runtime): treat non-empty finishReason as terminal
843a81f fix(server): Handle empty/invalid config in cloud deploy mode
9e10573 fix(server): add PATCH method to CORS allowed methods
cd4706f fix(server): resolve incorrect variable usage in management asset paths
84fa497 fix(server): snapshot config with YAML to handle in-place mutations
bb00436 fix(service): skip disabled auth entries during executor binding
8ce22b8 fix(sse): preserve usage metadata for stop chunks
d60040b fix(translator): accept camelCase thinking config in OpenAI→Gemini
680b3f5 fix(translator): avoid default thinkingConfig in Gemini requests
682c459 fix(translator): handle gjson strings in OpenAI response formatting
c29931e fix(translator): ignore empty JSON chunks in OpenAI responses
0defb68 fix(translator): improve error handling for function parameters schema transformation
b05cfd9 fix(translator): include empty text chunks in responses
734b040 fix(translator): remove strict field from Gemini Claude tool initialization
10be026 fix(translator): remove strict field from Gemini Claude tool initialization
af3fbd1 fix(translator): remove strict key from function declaration to prevent errors during schema transformation
2965bda fix(translator): remove debug print statement from OpenAI Gemini request processing
9e3b849 fix(translator): remove unsupported token limit fields for Codex Responses API
1afbc4d fix(translator): separate tool calls from content in OpenAI Claude requests
2a73d8c fix(translator): simplify tool response handling and adjust JSON schema updates in Gemini modules
5d806fc fix(translator): support system instructions with parts and inline data in OpenAI Gemini requests
2a3ee8d fix(translators): normalize thinking budgets
cf9a748 fix(watcher): Prevent infinite reload loop on rapid config changes
f97954c fix(watcher): enhance API key client counting and logging
57484b9 fix(watcher): improve client reload logic and prevent redundant updates
e9037fc fix(windows): Improve path handling and file read reliability
15981aa fix: add Claude→Claude passthrough to prevent SSE event fragmentation
a0c389a fix: comprehensive JSON Schema sanitization for Claude to Gemini
8a33f3e fix: detect HTML error bodies without text/html content type
1061354 fix: handle empty and non-JSON SSE chunks safely
9cdef93 fix: initialize contentBlocks with an empty slice and improve content handling in ConvertOpenAIResponseToClaudeNonStream
46b4110 fix: preserve SSE usage metadata-only trailing chunks
5a2bebc fix: remove duplicate CountTokens stub
1ba0571 fix: use underscore suffix in short name mapping
84248b6 merge
afff921 perf(watcher): Avoid unnecessary auth dir scan on config reload
f5dc380 rebuild branch
b56edd4 refactor(access): Introduce ApplyAccessProviders helper function
1dbb930 refactor(access): centralize configaccess.Register and remove redundant calls
6557d9b refactor(access): migrate config-api-key provider to internal package
d512f20 refactor(access): migrate to SDKConfig for authentication and provider management
edd4b4d refactor(api): Lazily register management routes
fd795ca refactor(api): Use middleware to control management route availability
aba719f refactor(auth): Centralize auth file reading with snapshot preference
2274d74 refactor(auth): Centralize logging for saving credentials
56b2dab refactor(auth): Introduce generic cookie snapshot manager
9b80820 refactor(auth): Move candidate sorting to RoundRobinSelector
053134f refactor(auth): remove unused Refresh methods from authenticators
bb8f931 refactor(auth): replace FileStore with FileTokenStore for unified token persistence
72ffeb7 refactor(auth): replace NextRefreshAfter with NextRetryAfter for clarity and consistency
d01c490 refactor(auth): replace TokenRecord with coreauth.Auth and migrate TokenStore to coreauth.Store
e3be548 refactor(auth): replace log calls with fmt for improved consistency and standard output usage
7c157d6 refactor(auth): simplify inline API key provider logic and improve configuration consistency
39518ec refactor(client): Improve auth file handling and client lifecycle
ed87dda refactor(client): remove deprecated and unused methods for cleaner session handling and core auth management
5888e04 refactor(cliproxy): remove unused access provider refresh logic
c675cf5 refactor(config): Implement reconciliation for providers and clients
57c9ba4 refactor(config): migrate to SDKConfig and streamline proxy handling
58f74eb refactor(config): remove force-gpt-5-codex option and related handlers
a00ba77 refactor(config): rename SyncGeminiKeys; use Sanitize* methods
c43f0ea refactor(config): rename model blacklist fields to excluded models
688547b refactor(config, auth): remove allow-localhost-unauthenticated support and related handlers
7632204 refactor(cookie): Extract cookie snapshot logic to util package
efd28bf refactor(copilot): address PR review feedback
2c296e9 refactor(copilot): improve code quality in authentication module
7ea8835 refactor(executor): centralize header application logic for executors
7515090 refactor(executor): improve concurrency and code quality in GitHub Copilot executor
a2c5fda refactor(executor): remove ClientAdapter and legacy fallback logic
514add4 refactor(executor): remove redundant handling of "reasoning.effort" in gpt-5 and gpt-5-codex models
a517290 refactor(executor): summarize API error bodies of html in debug logs
9810834 refactor(gemini-web): Centralize HTTP client creation for media
7f2e2fe refactor(gemini-web): Consolidate conversation data into single BoltDB file
0d4cb9e refactor(gemini-web): Improve client robustness and code reuse
e9707c2 refactor(gemini-web): Move provider logic to its own package
8e485e5 refactor(gemini-web): Remove auto-refresh, auto-close, and caching
7a30e65 refactor(gemini-web): Remove file-based PSIDTS cookie caching
75d7763 refactor(gemini-web): Rename flash image preview model ID
c76b878 refactor(gemini-web): Standardize logging with logrus
d32fc04 refactor(headers): centralize header logic using EnsureHeader utility
3ca01b6 refactor(logging): Improve client loading and registration logs
ac93641 refactor(logging, mgmt): update timestamp format in logs and remove force-gpt-5-codex handlers
ae646fb refactor(login): disable geminicloudassist API check in required services list
9e2d76f refactor(login): enhance project ID normalization and onboarding logic
b895018 refactor(provider): remove Gemini Web cookie-based provider
c3f8812 refactor(provider): remove Gemini Web cookie-based support
832268c refactor(proxy): improve SOCKS5 proxy authentication handling
0f55e55 refactor(registry): Preserve duplicate models in client registration
352a678 refactor(runtime): move Anthropic-Beta header setting to applyClaudeHeaders for better header management
6629cad refactor(server): remove unused context and managementasset references
d6bb143 refactor(translator): Remove unused logrus imports
92c8cd7 refactor(translator): remove unnecessary debug log in ConvertOpenAIRequestToGeminiCLI function
f6cf784 refactor(translator): remove unused log dependency and comment out debug logging
582677d refactor(usage): replace channel-based queue with mutex-protected slice
6136a77 refactor(util): Centralize auth directory path resolution
06e6f0a refactor(watcher): Extract config change logging to new function
8f0a345 refactor(watcher): Filter irrelevant file system events early
4bfafbe refactor(watcher): Move API key client creation to watcher package
e8e00d4 refactor(watcher): Remove unnecessary log separator
39abde2 refactor(watcher): remove redundant quota-exceeded change logs
0e0602c refactor(watcher): restructure client management and API key handling
f3f3127 refactor(wsrelay): rename RoundTrip to NonStream
c0fbc19 refactor: remove redundant Codex instruction validation logic
e5a6fd2 refactor: standardize dataTag processing across response translators
d9ad656 refactor: standardize constant naming and improve file-based auth handling
307ae76 refactor: streamline ConvertCodexResponseToGeminiNonStream by removing unnecessary buffer and improving response handling
3f69254 remove all
a6cb16b security: fix localhost middleware header spoofing vulnerability
6c17dbc style(amp): tidy whitespace in proxy module and tests
4999fce v6 version first commit