- Remove outdated preview models (gemini-2.5-pro-preview-03-25, gemini-2.5-pro-preview-05-06, gemini-2.5-pro-preview-06-05) from gemini.ts and vertex.ts
- Add backward compatibility logic in Gemini and Vertex providers to automatically map legacy preview models to gemini-2.5-pro GA version
- Update OpenRouter provider to handle legacy preview model mapping
- Update OpenRouter tests to reflect removal of preview model references
Fixes#5444
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
- Update parseOpenRouterModel to always use actual max_completion_tokens from OpenRouter API
- Remove artificial restriction that only reasoning budget and Anthropic models get their actual max tokens
- Fall back to 20% of context window when max_completion_tokens is null
- Update getModelMaxOutputTokens to use same fallback logic for consistency
- Update tests to reflect new behavior
- Fixes issue where reserved tokens showed ~209k instead of actual model limits (e.g. GPT-4o: 16,384)
* chore: adding x-title header and testing for litellm
* chore: indentation fi and headers order fix
* chore: spacing fix
* chore: removed white space
* fix: allow user headers to override default headers and clean up formatting
- Reorder header spread in router-provider.ts so user-provided openAiHeaders can override DEFAULT_HEADERS
- Remove unnecessary blank lines after imports for consistency
- This matches the pattern used in openai.ts where DEFAULT_HEADERS come first
---------
Co-authored-by: Brendan-Z <brendanzhou.99@gmail.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
* fix: resolve Claude Code token counting inefficiency and enable caching (#5104)
- Remove 1.5x fudge factor from Claude Code token counting
- Enable prompt caching support for all Claude Code models
- Add comprehensive tests for token counting and caching
- Update existing tests to reflect accurate token counting
This fixes the extreme token inefficiency where simple messages would
jump from ~40k to over 60k tokens, causing API hangs when approaching
the artificial 120k limit. Claude Code now properly utilizes its full
200k context window with accurate token counting.
* fix: address PR review comments
- Extract IMAGE_TOKEN_ESTIMATE as a named constant for clarity
- Update token counting tests to use exact counts instead of ranges for deterministic testing
- Fix test expectations to match actual tokenizer output
* Remove token counting changes, keep only cache support
- Removed custom countTokens override from claude-code.ts
- Deleted claude-code-token-counting.spec.ts test file
- Kept cache token collection and reporting functionality
- Kept supportsPromptCache: true for all Claude Code models
- Kept claude-code-caching.spec.ts tests
This focuses the PR on enabling cache support without modifying token counting behavior.
* fix: update webview test to expect supportsPromptCache=true for Claude Code models
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* Fix temperature parameter error for Azure OpenAI reasoning models
* Fix tests: Update O3 family model tests to expect temperature: undefined
- Updated failing tests in openai.spec.ts to expect temperature: undefined for O3 models
- This aligns with the PR changes that remove temperature parameter for Azure OpenAI o1, o3, and o4 models
- All 4 previously failing tests now pass
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
fix: handle null families field in Ollama model details schema
- Updated OllamaModelDetailsSchema to make families field nullable and optional
- Made all unused properties optional in Ollama schemas to prevent validation errors
- Added test cases to verify handling of null families field
- Only required properties that are actually used in the code are now mandatory
- Fixes Zod validation error when Ollama returns null for families array
* Add reasoning budget support to Bedrock models and update related components
- Introduced `supportsReasoningBudget` property in Bedrock models.
- Enhanced `AwsBedrockHandler` to handle reasoning budget in payloads.
- Updated `ThinkingBudget` component to dynamically set max tokens based on reasoning support.
- Modified `ApiOptions` and `Bedrock` components to conditionally render `ThinkingBudget`.
- Added tests for extended thinking functionality in `bedrock-reasoning.test.ts`.
* Add BedrockThinkingConfig interface and update payload structure
* fix: address PR review feedback (#4481)
- Simplify ThinkingBudget ternary logic since component only renders when reasoning budget supported
- Break down complex thinking enabled condition with clear documentation
- Replace 'as any' usage with proper TypeScript interfaces for AWS SDK events
- Add comprehensive documentation for multiple stream structures explaining AWS SDK compatibility
* feat: show ThinkingBudget component unconditionally
Remove selectedProviderModels.length check to display ThinkingBudget
for all providers, not just those with available models
---------
Co-authored-by: hannesrudolph <hrudolph@gmail.com>
* Add reasoning budget support to Bedrock models and update related components
- Introduced `supportsReasoningBudget` property in Bedrock models.
- Enhanced `AwsBedrockHandler` to handle reasoning budget in payloads.
- Updated `ThinkingBudget` component to dynamically set max tokens based on reasoning support.
- Modified `ApiOptions` and `Bedrock` components to conditionally render `ThinkingBudget`.
- Added tests for extended thinking functionality in `bedrock-reasoning.test.ts`.
* Add BedrockThinkingConfig interface and update payload structure
* fix: address PR review feedback (#4481)
- Simplify ThinkingBudget ternary logic since component only renders when reasoning budget supported
- Break down complex thinking enabled condition with clear documentation
- Replace 'as any' usage with proper TypeScript interfaces for AWS SDK events
- Add comprehensive documentation for multiple stream structures explaining AWS SDK compatibility
* feat: Add DeepSeek R1 support to Chutes provider (#4523)
- Modified BaseOpenAiCompatibleProvider to expose client as protected
- Enhanced ChutesHandler to detect DeepSeek R1 models and parse reasoning chunks
- Applied R1 format conversion for message formatting
- Set appropriate temperature (0.6) for DeepSeek models
- Migrated tests from Jest to Vitest format
- Added comprehensive tests for DeepSeek R1 functionality
This ensures reasoning chunks are properly separated from regular content
when using DeepSeek R1 models via Chutes provider.
* feat: Enhance DeepSeek R1 support with <think> tag handling in Chutes provider
* fix: Correct temperature retrieval in ChutesHandler to use model's info
* fix: Update condition for DeepSeek-R1 model identification in createMessage method
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Currently, when you use OpenRouter with your own key for the underlying service, the costs shown by Roo Code are way off what it actually costs.
With bring your own key, OpenRouter charges 5% of what it normally would (see https://openrouter.ai/docs/use-cases/byok)
so we have to multiply the reported cost by 20 to get an estimate of what it actually costs.
Co-authored-by: Johan Otten <drakonen@drakonen.com>
Co-authored-by: Eamon Nerbonne <eamon@nerbonne.org>
* fix: remove explicit cache_control for Google models in OpenRouter (#4487)
- Remove all Google models from OPEN_ROUTER_PROMPT_CACHING_MODELS set
- This resolves 3+ minute lag when using google/gemini-2.5-pro-preview
- OpenRouter still provides automatic implicit ephemeral caching for these models
- Updated tests to handle intentional exclusion of Google models from explicit caching
Fixes#4487
* refactor: simplify OpenRouter caching test logic
- Replace hardcoded exclusion list with simple Google model filter
- Keep original validation logic but make it more maintainable
- Still ensures all our caching models are supported by OpenRouter
- Still verifies we exclude all Google models from explicit caching
* cleanup: remove unused excludedModels variable
- Variable was defined but never used
- Keeps the test logic clean and focused
* refactor: only exclude google/gemini-2.5-pro-preview from caching
- More surgical approach - only exclude the specific problematic model
- Keep other Google models in caching (they work fine)
- Add comment explaining the exclusion with issue reference
- Update test to only exclude the specific model
This targets just the model causing 3+ minute lag while preserving
caching benefits for other Google models that work properly.
* feat: Add safeWriteJson utility for atomic file operations
Implements a robust JSON file writing utility that:
- Prevents concurrent writes to the same file using in-memory locks
- Ensures atomic operations with temporary file and backup strategies
- Handles error cases with proper rollback mechanisms
- Cleans up temporary files even when operations fail
- Provides comprehensive test coverage for success and failure scenarios
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* fix: use safeWriteJson for all JSON file writes
This change refactors all direct JSON file writes to use the safeWriteJson
utility, which implements atomic file writes to prevent data corruption
during write operations.
- Modified safeWriteJson to accept optional replacer and space arguments
- Updated tests to verify correct behavior with the new implementation
Fixes: #722
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* feat: Implement inter-process file locking for safeWriteJson
Replaces the previous in-memory lock in `safeWriteJson` with
`proper-lockfile` to provide robust, cross-process advisory file
locking. This enhances safety when multiple processes might attempt
concurrent writes to the same JSON file.
Key changes:
- Added `proper-lockfile` and `@types/proper-lockfile` dependencies.
- `safeWriteJson` now uses `proper-lockfile.lock()` with configured
retries, staleness checks (31s), and lock update intervals (10s).
- An `onCompromised` handler is included to manage scenarios where
the lock state is unexpectedly altered.
- Logging and comments within `safeWriteJson` have been refined for
clarity, ensuring error logs include backtraces.
- The test suite `safeWriteJson.test.ts` has been significantly
updated to:
- Use real timers (`jest.useRealTimers()`).
- Employ a more comprehensive mock for `fs/promises`.
- Correctly manage file pre-existence for various scenarios.
- Simulate lock contention by mocking `proper-lockfile.lock()`
using `jest.doMock` and a dynamic require for the SUT.
- Verify lock release by checking for the absence of the `.lock`
file.
All tests are passing with these changes.
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* feat: implement streaming JSON write in safeWriteJson
Refactor safeWriteJson to use stream-json for memory-efficient JSON serialization:
- Replace in-memory string creation with streaming pipeline
- Add Disassembler and Stringer from stream-json library
- Extract streaming logic to a dedicated helper function
- Add proper-lockfile and stream-json dependencies
This implementation reduces memory usage when writing large JSON objects.
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* fix: improve safeWriteJson locking mechanism
- Use file path itself for locking instead of separate lock file
- Improve error handling and clarity of code
- Enhance cleanup of temporary files
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* test: fix safeWriteJson test failures
- Ensure test file exists before locking
- Add proper mocking for fs.createWriteStream
- Fix test assertions to match expected behavior
- Improve test comments to follow project guidelines
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* test: update tests to work with safeWriteJson
Updated tests to work with safeWriteJson instead of direct fs.writeFile calls:
- Updated importExport.test.ts to expect safeWriteJson calls instead of fs.writeFile
- Fixed McpHub.test.ts by properly mocking fs/promises module:
- Moved jest.mock() to the top of the file before any imports
- Added mock implementations for all fs functions used by safeWriteJson
- Updated the test setup to work with the mocked fs module
All tests now pass successfully.
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* refactor: replace JSON.stringify with safeWriteJson for file operations
Replace all non-test instances of JSON.stringify used for writing to JSON files with safeWriteJson to ensure safer file operations with proper locking, error handling, and atomic writes.
- Updated src/services/mcp/McpHub.ts
- Updated src/services/code-index/cache-manager.ts
- Updated src/api/providers/fetchers/modelEndpointCache.ts
- Updated src/api/providers/fetchers/modelCache.ts
- Updated tests to match the new implementation
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* docs: add rules for using safeWriteJson
Add concise rules for using safeWriteJson instead of JSON.stringify with file operations to ensure atomic writes and prevent data corruption.
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
---------
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
Co-authored-by: Eric Wheeler <roo-code@z.ewheeler.org>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
* Added changeset for my code changes
* Use URL constructor for joining baseUrl and path in litellm.ts
* Restoring Roo dotfiles
* Moved Roo dotfiles to root directory
* Revert this
* Add tests for litellm URL constructor fix
---------
Co-authored-by: Kevin White <kcwhite@ancestry.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* Improves model info detection for custom Bedrock ARNs
Adds heuristics to better estimate model capabilities when using unknown or custom model ARNs, including context window and max tokens. Allows user overrides for key model parameters via provider settings, improving flexibility and reliability for non-standard model integrations.
Fixes#3712
* Improves JSON syntax error handling in import flow
Provides more informative error messages for JSON syntax
errors by extracting the error position and formatting it
for clarity during import. Enhances user feedback when
invalid JSON is encountered.
* Fixed failing tests
* Delete pnpm-lock.yaml
* Added Rory's cache fix from PR #3099
PR #3009 has an important fix, alerted to me by @JBBrown
It was a one liner so I pulled it in.
This brings up a question can we merge PR's in the GH UI?
* Add Claude 4 and Opus 4 to modelID's
Kept previous parameters, did not see any changes in those.
* Fixed types being moved and me breaking the merge.
* Fix merge
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
* feat: Add custom VPC endpoint support for AWS Bedrock
* fix: Fix TypeScript error in Bedrock.tsx
* fix: Update VPC endpoint UI to match Cline's implementation
* Fix AWS Bedrock VPC endpoint UI implementation
- Changed checkbox label to 'Use custom VPC endpoint' to match Cline
- Fixed conditional rendering to show text field when checkbox is checked
- Ensured placeholder text appears correctly
- Maintained proper styling for consistency
* Fix AWS Bedrock VPC endpoint UI implementation to match Cline exactly
- Added state variable to track checkbox selection
- Fixed conditional rendering to show/hide text field based on checkbox state
- Maintained proper styling and placeholder text
* Fix AWS Bedrock VPC endpoint UI implementation with proper event handling
- Fixed checkbox onChange handler to accept boolean directly instead of event object
- Added unit tests to verify the behavior
- Maintained proper styling and placeholder text
* Update Bedrock VPC endpoint tests with proper test IDs
* Improve AWS Bedrock VPC endpoint text field alignment
- Removed left margin from text field to align with checkbox
- Maintained proper styling and placeholder text
* Preserve AWS Bedrock VPC endpoint URL when toggling checkbox
- Added awsBedrockEndpointEnabled field to schema
- Modified Bedrock provider to check both endpoint URL and enabled flag
- Updated UI to preserve endpoint URL when checkbox is toggled
- Maintained proper alignment with checkbox
* Implement AWS Bedrock Custom VPC Endpoint functionality
* fix: update ApiConfiguration to ProviderSettings in Bedrock tests and regenerate types
* fix: update all instances of ApiConfiguration to ProviderSettings in Bedrock tests
* Fixed broken unit test
* Add changeset for Bedrock VPC endpoint support
* informative placeholder
* Bug fixes
* Fixed failing tests
* Add example URLs to Bedrock VPC endpoint section and update tests
* Fix truncated test assertion in Bedrock.test.tsx that was breaking the UI
* Refactor mock components in Bedrock.test.tsx for improved data-testid handling
* feat(i18n): add VPC endpoint translations for AWS Bedrock settings
* test: update Bedrock component tests for internationalized strings
---------
Co-authored-by: Kevin White <kcwhite@ancestry.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* Add structured task metadata to Unbound API requests
* Moves origin app to a constant
---------
Co-authored-by: Pugazhendhi <pugazhendhi@unboundsecurity.ai>
