Replace permissive JSON Schema Draft-07 whitelist with strict
Gemini-compatible field set (22 fields). The "examples" field
in Claude Code tool schemas caused 400 errors from Gemini API.
Also strips other unsupported fields: $ref, $defs, oneOf, allOf,
additionalProperties, const, if/then/else, etc.
Safe change — sanitizer only runs for CLIProxy profiles (Gemini,
Codex, Antigravity), never for direct Anthropic API requests.
Closes#155
Track hasReceivedMessageDelta and hasReceivedMessageStop in both
streaming paths (pipe-through and SSE-processing). Conditionally
omit these events from buildSyntheticErrorResponse() when upstream
already sent them, preventing protocol violations.
Closes#491
* fix(cliproxy): disable 1M extended context for gemini-claude-opus-4-6-thinking
Antigravity backend only supports 256k context window for this model,
not 1M as previously declared. Set extendedContext: false with TODO
comment for easy re-enable when backend adds support.
Closes#490
* fix(cliproxy): strip [1m] suffix at runtime for models without extended context
Users with existing [1m] in saved agy.settings.json will now have it
automatically stripped at runtime when the model no longer supports
extended context. Prevents misleading context window claims.
* fix(cliproxy): guard against empty upstream SSE responses in agy profile
When CLIProxyAPIPlus drops unsigned thinking blocks during sub-agent
execution, the response stream can contain no content_block_start or
message_delta events. This causes Claude Code CLI to crash with
"No assistant message found".
Add empty response detection in the tool sanitization proxy's streaming
handler. Both the pipe-through and SSE-processing paths now track
whether meaningful content was received. If upstream sent data but no
content blocks on a 200 OK, a synthetic minimal valid SSE response is
injected to prevent the client crash and surface a clear error message.
Closes#350
* fix(cliproxy): improve empty response detection and add tests
Address code review findings:
- Remove message_delta from content detection (lifecycle event, not
content); only content_block_start indicates actual content
- Add try-catch in end handlers to handle client disconnects gracefully
- Add 3 integration tests: empty stream injection, normal stream
passthrough, 4xx/5xx non-injection
* fix(cliproxy): avoid duplicate message_start in synthetic response
Track whether upstream already sent a message_start event. When
injecting the synthetic error response, omit message_start if upstream
already sent one, preventing duplicate events in the SSE stream.
Addresses PR review feedback from ccs-reviewer[bot].
* test(cliproxy): add SSE processing path and real failure mode tests
Address code review observations:
- Add test exercising SSE processing path (sanitized tool names) for
empty response detection, ensuring both code paths are covered
- Add test mirroring real failure mode where upstream sends only
message_start then ends abruptly (no message_delta/message_stop)
- Document duplicate message_start assumption with inline comment
* fix(version): show active config path instead of deprecated config.json
The version command was using deprecated getConfigPath() which always
returned config.json path. Now uses getActiveConfigPath() which shows
config.yaml in unified mode or config.json in legacy mode.
* chore(release): 7.37.1-dev.1 [skip ci]
* fix(ui): use native dynamic import to fix Node 24 ESM/CJS interop
TypeScript compiles import() to require() when targeting CommonJS,
which breaks ESM packages like ora on Node 24. Use new Function()
to create native dynamic import at runtime, bypassing TS transform.
Closes#472
* chore(release): 7.37.1-dev.2 [skip ci]
* fix(env): strip ANTHROPIC_* from account/default profiles
Account and default profiles inherit process.env which may contain
stale ANTHROPIC_BASE_URL from prior CLIProxy sessions. This causes
ConnectionRefused errors when Claude tries to hit an unavailable proxy.
Settings-based profiles already handle this by explicitly injecting
their own ANTHROPIC_* values. This fix applies the same protection
to account/default profiles by stripping ANTHROPIC_* before spawn.
Closes#474
* test(env): add unit tests for stripAnthropicEnv
Address code review feedback from PR #475. Tests cover:
- Removing all ANTHROPIC_* keys
- Preserving non-ANTHROPIC keys
- Empty object handling
- Undefined value preservation
- Case sensitivity (only uppercase ANTHROPIC_)
- All ANTHROPIC_ prefixed variants stripped
* chore(release): 7.37.1-dev.3 [skip ci]
* feat(cliproxy): add extended context support for 1M token window
Add --1m and --no-1m flags to enable/disable 1M token context window.
Uses Claude Code's [1m] suffix mechanism.
Behavior:
- Gemini models: auto-enabled by default
- Claude models: opt-in with --1m flag
- New extendedContext field in model catalog
Also adds Claude Opus 4.6 to model catalog with extended context support.
Closes#103
* feat(ui): add extended context toggle in dashboard model config
- Add ExtendedContextToggle component for 1M token context window
- Add Claude Opus 4.6 (claude-opus-4-6-20260203) to model catalogs
- Mark Gemini and Claude models with extendedContext: true
- Toggle only appears when selected model supports extended context
- Auto-enabled info for native Gemini, opt-in info for Claude
Part of extended context feature implementation for issue #103.
* fix: address code review findings and CI failure
- Fix CI error: add missing 'provider' prop to ModelConfigSection
- Fix case sensitivity in applyExtendedContextSuffix
- Fix whitespace handling in stripModelSuffixes
- Handle --1m=value and --no-1m=value CLI patterns
- Add warning when --1m used on unsupported model
- Sync agy catalog: add extendedContext to gemini-3-pro-preview
- Extract isNativeGeminiModel to shared utility (DRY)
- Add 21 unit tests for extended-context-config
* fix(catalog): rename claude-opus-4-6-20260203 to claude-opus-4-6
* fix(ui): wire extended context toggle through component tree
- Add extendedContextEnabled and toggleExtendedContext to useProviderEditor hook
- Store setting as CCS_EXTENDED_CONTEXT env var in provider settings
- Pass props through provider-editor → model-config-tab → model-config-section
- Update UseProviderEditorReturn type with new properties
* fix(ui): apply [1m] suffix directly to model strings in settings
- Toggle now applies/strips [1m] suffix to all ANTHROPIC_*MODEL env vars
- Extended context detected by checking if any model has [1m] suffix
- Remove legacy CCS_EXTENDED_CONTEXT flag approach
- Add suffix utilities: applyExtendedContextSuffix, stripExtendedContextSuffix
- Raw Configuration now shows actual model values with [1m] suffix
* fix(qwen): update model catalog with correct context windows and tier mappings
- Update context window specs from official Alibaba docs:
- Qwen3 Coder Plus: 1M context (was 32K)
- Qwen3 Max: 256K context (flagship)
- Qwen3 Coder Flash: fast code generation
- Fix preset mappings for Claude tier equivalence:
- Opus → qwen3-max (flagship 256K)
- Sonnet → qwen3-coder-plus (balanced 1M)
- Haiku → qwen3-coder-flash (fast)
- Update provider descriptions to reflect 256K-1M context range
- Add all 7 Qwen models from CLIProxyAPI: qwen3-coder-plus, qwen3-max,
qwen3-max-preview, qwen3-235b, qwen3-vl-plus, qwen3-coder-flash, qwen3-32b
Closes#478
* fix(ui): only apply [1m] suffix to ANTHROPIC_MODEL, fix toggle refresh
- Only ANTHROPIC_MODEL gets [1m] suffix, not tier mappings
- Strip [1m] when looking up model in catalog to prevent toggle disappearing
- Fix odd page refresh when toggling extended context
* chore(release): 7.37.1-dev.4 [skip ci]
* fix(ui): remove duplicate import in use-provider-editor
* chore: address PR review feedback - sync comment and unused import
* chore(release): 7.37.1-dev.5 [skip ci]
* feat(cliproxy): add Opus 4.6 to Antigravity model catalog (#482)
* feat(cliproxy): add Opus 4.6 to Antigravity model catalog
- Add gemini-claude-opus-4-6-thinking as new default agy model
- Update preset mappings to route opus tier to Opus 4.6
- Bump CLIProxy fallback versions to v6.8.2
- Keep Opus 4.5 as previous flagship option
* fix(cliproxy): include oauth-model-alias in config generation
Root cause: CLIProxy config.yaml was missing Opus 4.6 alias because:
1. CLIProxyPlus startup migration is disabled (intentional)
2. CCS config generator never wrote oauth-model-alias section
3. Existing users with outdated aliases got 502 on Opus 4.6
Fix:
- Add DEFAULT_ANTIGRAVITY_ALIASES to config generator
- Generate oauth-model-alias section in config.yaml template
- Preserve claude-api-key and custom aliases during regeneration
- Bump config version to v6 to trigger auto-regeneration
- Update model catalog tests for new model count
* fix(cliproxy): preserve YAML indentation in extractYamlSection
- Replace .trim() with regex to strip only leading/trailing newlines,
preserving 2-space indent on claude-api-key children
- Skip standalone comments at col 0 in section boundary detection
- Update stale test description (4 → 5 models)
* chore(release): 7.37.1-dev.6 [skip ci]
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
- Skip saving registry when no new accounts discovered (prevents empty
accounts.json creation for invalid files)
- Skip merging empty provider sections to prevent empty provider entries
- Update test module cache clearing to include new modular submodules
(accounts/registry, accounts/index) for proper test isolation
The GLMT retry logic tests use dynamic imports and GlmtProxy
instantiation which are slower on CI runners than locally.
Increase default timeout from 5s to 30s to prevent flaky failures.
- Refactor: Remove duplicate expandWindowsPath(), use expandPath() from helpers
- Simplify: Update WINDOWS_NATIVE_PATHS to actual install location
(%USERPROFILE%\.local\bin\claude.exe from Claude's install.ps1)
- Tests: Add comprehensive test suite for Windows detection (9 tests)
- Address code review feedback from PR #449
Refs: #447
- Read ANTHROPIC_MODEL from profile settings instead of hardcoding
- Display model name in full uppercase (GLM-4.7, not Glm-4.7)
- Add null/undefined guard to getModelDisplayName
- Remove hardcoded GLM-4.6/GLM-4.6 (Thinking) display names
Closes#431
Address review feedback:
- Add line-buffering to handle chunk splitting edge case
- Add 14 unit tests for stderr filter logic
- Test chunk boundary handling, mixed output, edge cases
Handles case where "npm warn cleanup" could be split across chunks.
- Test proxy lifecycle (start/stop)
- Test request sanitization (duplicates, truncation, passthrough)
- Test response restoration (buffered and SSE streaming)
- Test error handling (invalid JSON, upstream errors)
- Test multiple tools with mapping tracking
- Mock upstream server for isolated testing
- change AccountTier from binary (free/paid) to granular (ultra/pro/free/unknown)
- update mapTierString() to parse API tier strings correctly
- remove faulty inferTierFromModels() fallback - tier comes only from API
- update default tier_priority config to ['ultra', 'pro', 'free']
- update model catalog tier types and display logic
Closes#387
- Add 31 unit tests for fetchLocalSyncStatus, fetchProfiles, and performLocalSync
- Cover success, error, timeout, and network failure scenarios
- Remove unused --force flag from sync handler (YAGNI)
- Fix "Remote" → "Local" in sync-dialog.tsx and CLI help text
- Add resetWatcherState() export for test cleanup
- Add unit tests for profile-mapper, local-config-sync, auto-sync-watcher
- Remove unused ModelAlias and AliasesResponse types from hooks
- Validate authToken with trim() to reject whitespace-only values
- Show broken model warning for both remote and local modes
- Add context-aware messaging for remote proxy users
- Add comprehensive test coverage for authToken edge cases:
- Whitespace-only strings
- Null values
- Tabs/newlines
- Tokens with leading/trailing whitespace
Co-authored-by: Shun Kakinoki <shunkakinoki@gmail.com>
When --proxy-host and --proxy-auth-token are provided, the remote proxy
handles authentication via its own OAuth sessions. This change skips:
- Local OAuth check/trigger
- Preflight quota check (managed by remote server)
- Model configuration prompts (configured on remote server)
- Broken model warnings (model selection is remote)
This enables headless CI/CD usage without requiring pre-cached
CCS_SESSIONS when a remote proxy with auth token is available.
- Add 3 test cases for setup_completed flag:
- Detect flag when present and true
- Treat missing flag as first-time eligible
- Treat false flag as first-time eligible
- Update JSDoc to document detection priority order
Addresses code review feedback on PR #372.
- Add centralized mock infrastructure in tests/mocks/:
- mock-fetch.ts: Bun native fetch interception
- mock-http-server.ts: Fake server responses (no ports)
- fixtures/responses.ts: Preset response constants
- types.ts: Mock type definitions
- Refactor https-tunnel-proxy.test.ts:
- Remove TEST_CERT constant (~50 lines)
- Remove real HTTPS server creation
- Use invalid hosts for error path testing
- 26/26 tests pass in ~430ms
- Refactor remote-token-uploader.test.ts:
- Replace 7 real HTTP servers with mockFetch
- Reduce from 422 to 289 lines
- 18/18 tests pass in ~120ms
- Add global test timeout (10s) in bunfig.toml
Test suite: 10+ min → 14 seconds
- Fix config-generator test assertion for parseUserApiKeys
- Update model-catalog tests to expect codex provider
- Remove outdated codex unsupported test from model-config
Add cliproxy.backend config field to choose between CLIProxyAPI (original)
and CLIProxyAPIPlus backends. Includes CLI --backend flag, Dashboard toggle,
and provider validation to block Kiro/ghcp on original backend.
The previous test relied on client socket receiving close event from
server-side destroy, which is timing-dependent and flaky in CI.
New approach:
- Verify stop() behavior directly via getPort() returning null
- Test what we control (server state) not what we observe (client state)
- Remove timing-dependent assertions
- Faster and more reliable (83ms vs 1000ms+ timeout)
- Fix connection tracking test: wait for 'close' event instead of only
checking socket.destroyed (more reliable in CI environments)
- Increase timeout from 500ms to 1000ms for CI latency
- Add proper socket cleanup after test
- Merge dev changes: add projectId parameter to registerAccount()
- Add express-rate-limit to restore endpoint (5 req/min)
- Add JSDoc documentation to RestoreMutex class
- Extract magic numbers to named constants in BackupsSection
- Add unit tests for persist-routes.ts (23 tests)
- Add unit tests for BackupsSection component (28 tests)
Addresses PR #339 code review feedback.
- Fix timeout test to use HTTPS server (tunnel uses https.request)
- Fix timeout event handling - call reject directly instead of relying on destroy error event
- Fix misleading comment in remote-token-uploader (Authorization header, not X-Management-Key)
- Remove unused imports in test files
Built [OnSteroids](https://onsteroids.ai)
Co-Authored-By: OnSteroids <built@onsteroids.ai>
* feat(cliproxy): add HTTPS tunnel for remote proxy mode
Claude Code doesn't support HTTPS in ANTHROPIC_BASE_URL directly (undici
limitation). This adds an HTTP→HTTPS tunnel proxy for remote CLIProxyAPI
connections.
Changes:
- Add HttpsTunnelProxy: local HTTP server tunneling to remote HTTPS
- Add CodexReasoningProxy HTTPS support and path prefix stripping
- Remote mode now uses root paths (/v1/messages) not provider-prefixed
- Add remote token uploader for syncing OAuth tokens to remote server
- Auto-upload tokens after OAuth auth when remote mode is enabled
Flow for remote HTTPS:
Claude CLI → CodexReasoningProxy → HttpsTunnel → Remote HTTPS
Built with [OnSteroids](https://onsteroids.ai)
Co-Authored-By: OnSteroids <built@onsteroids.ai>
* fix: address PR review issues for HTTPS tunnel proxy
- Add connection tracking with activeConnections Set for proper cleanup
- Add port validation after start() to reject port 0
- Add Authorization header fallback injection in buildForwardHeaders()
- Handle client disconnect (premature close) and request errors
- Improve error handling in uploadTokenToRemoteAsync (log instead of silent catch)
- Add comprehensive tests for HttpsTunnelProxy (97% coverage)
- Add integration tests for remote-token-uploader
- Add stripPathPrefix unit tests for remote mode
Built with [OnSteroids](https://onsteroids.ai)
Co-Authored-By: OnSteroids <built@onsteroids.ai>
* fix: bump Node.js engine requirement to >=18.0.0
FormData and Blob APIs used in remote-token-uploader require Node.js 18+.
Addresses coderabbit review comment about Node.js engine compatibility.
Built [OnSteroids](https://onsteroids.ai)
Co-Authored-By: OnSteroids <built@onsteroids.ai>
* fix: address remaining PR suggestions
- Add verbose parameter to registerAccountFromToken for proper propagation
- Improve stripPathPrefix with path normalization (double slashes, leading slash)
- Add edge case tests for path normalization
Built [OnSteroids](https://onsteroids.ai)
Co-Authored-By: OnSteroids <built@onsteroids.ai>
* fix: add timeout to flaky npm CLI tests
Tests 'handles empty arguments gracefully' and 'handles very long argument'
were missing timeout option in execSync, causing occasional timeouts when
bun test's 5000ms limit was reached before CLI completed.
Built [OnSteroids](https://onsteroids.ai)
Co-Authored-By: OnSteroids <built@onsteroids.ai>
* fix: address new PR review feedback
- Add path segment boundary check to prevent partial matches (/codex vs /codextra)
- Add hostname validation in HttpsTunnelProxy constructor
- Add race condition protection with 'starting' flag in start()
- Sanitize error messages (detailed only in verbose mode)
- Update comments for clarity (regex behavior)
- Add comprehensive tests for all edge cases
Built [OnSteroids](https://onsteroids.ai)
Co-Authored-By: OnSteroids <built@onsteroids.ai>
---------
Co-authored-by: OnSteroids <built@onsteroids.ai>
Add backup management functionality to the persist command:
- List available backups with timestamps and dates
- Restore from most recent or specific backup
- Improved error handling for corrupted settings.json
- Updated CLAUDE.md to document the persist command and the exception to the non-invasive constraint
- test budget bounds and constants
- test off/auto/level values handling
- test budget-type and level-type models
- test edge cases and unknown models
Refs #307
kaitranntt