Tool IDs from providers like Gemini/OpenRouter contain special characters
(e.g., 'functions.read_file:0') that are sanitized when saving tool_use
blocks to API history. However, tool_result blocks were using the original
unsanitized IDs, causing ToolResultIdMismatchError.
This fix ensures tool_result blocks use sanitizeToolUseId() to match the
sanitized tool_use IDs in conversation history.
Fixes EXT-711
- Import vscodeLlmModels from @roo-code/types to check static definitions first
- Use pattern matching only for unknown models not in static definitions
- Add IMAGE_INCAPABLE_MODEL_PATTERNS for explicit non-vision models
- Update IMAGE_CAPABLE_MODEL_PATTERNS to use RegExp for precise matching
- Fix inconsistency where older models incorrectly reported supportsImages: true
- Update tests to verify static definitions take precedence over pattern matching
Re-applies the image support feature from PR #11065 that was reverted,
with a fix for the @types/vscode version issue.
The fix keeps @types/vscode at ^1.84.0 in package.json (matching
engines.vscode) while the pnpm-lock.yaml resolves to version 1.108.1
which provides the LanguageModelDataPart API.
This approach:
- Maintains compatibility with VS Code 1.84.0+
- Provides TypeScript types for the new LanguageModelDataPart API
- Resolves the vsix build failure from the original PR
Changes:
- Add convertImageToDataPart() for image-to-LanguageModelDataPart conversion
- Add checkModelSupportsImages() for model image capability detection
- Update useSelectedModel to use models actual supportsImages capability
- Add comprehensive tests for image support
Relates to #11064, #11065
* feat(condense): add smart code folding with tree-sitter signatures
At context condensation time, use tree-sitter to generate folded code
signatures (function definitions, class declarations) for files read
during the conversation. Each file is included as its own <system-reminder>
block in the condensed summary, preserving structural awareness without
consuming excessive tokens.
- Add getFilesReadByRoo() method to FileContextTracker
- Create generateFoldedFileContext() using tree-sitter parsing
- Update summarizeConversation() to accept array of file sections
- Each file gets its own content block in the summary message
- Add comprehensive test coverage (12 tests)
* fix: skip tree-sitter error strings in folded file context
- Add isTreeSitterErrorString helper to detect error messages
- Skip files that return error strings instead of embedding them
- Add test for error string handling
* refactor: move generateFoldedFileContext() inside summarizeConversation()
- Update summarizeConversation() to accept filesReadByRoo, cwd, rooIgnoreController instead of pre-generated sections
- Move folded file context generation inside summarizeConversation() (lines 319-339)
- Update ContextManagementOptions type and manageContext() to pass new parameters
- Remove generateFoldedFileContext from Task.ts imports - folding now handled internally
- Update all tests to use new parameter signature
- Reduces Task.ts complexity by moving folding logic to summarization module
* fix: prioritize most recently read files in folded context
Files are now sorted by roo_read_date descending before folded context
generation, so if the character budget runs out, the most relevant
(recently read) files are included and older files are skipped.
* refactor: improve code quality in condense module
- Convert summarizeConversation to use options object instead of 11 positional params
- Extract duplicated getFilesReadByRoo error handling into helper method
- Remove unnecessary re-export of generateFoldedFileContext
- Update all test files to use new options object pattern
* fix: address roomote feedback - batch error logging and early budget exit
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
