Commit graph

15 commits

Author SHA1 Message Date
Daniel
6cfa82f571
Revert to pre-AI-SDK state (January 29, 2026) (#11462)
Revert to pre-AI-SDK state (commit 67e568f6b)

This commit reverts the codebase to the state before AI SDK migration work began.

Target commit: 67e568f6b - refactor: replace fetch_instructions with skill tool and built-in skills (#10913)
Date: January 29, 2026

This removes approximately 152 commits of AI SDK migration work.
A follow-up PR will add back bug fixes and features that are unrelated to AI SDK.

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-02-13 16:45:18 -05:00
Daniel
e6f0e79c38
feat: implement ModelMessage storage layer with AI SDK response messages (#11409)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-02-11 13:58:39 -05:00
Matt Rubens
dcb33c47ad
Revert "feat: wire RooMessage storage into Task.ts and all providers" (#11394) 2026-02-10 23:57:42 -05:00
Daniel
a7ba3b5af5
feat: wire RooMessage storage into Task.ts and all providers (#11386) 2026-02-10 21:25:48 -07:00
Hannes Rudolph
d748de6fae
feat(condense v2.1): add smart code folding (#10942)
* 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>
2026-01-27 18:47:24 -05:00
Hannes Rudolph
2f92cb7a8d
fix: prevent nested condensing from including previously-condensed content (#10985) 2026-01-26 22:34:04 -05:00
Hannes Rudolph
0ff826d21d
feat(condense): improve condensation with environment details, accurate token counts, and lazy evaluation (#10920) 2026-01-23 13:52:47 -07:00
Hannes Rudolph
cf5d42e1e1
Intelligent Context Condensation v2 (#10873) 2026-01-23 12:33:35 -07:00
Hannes Rudolph
9d65772d24
fix(condense): remove custom condensing model option (#10901)
* fix(condense): remove custom condensing model option

Remove the ability to specify a different model/API configuration for
condensing conversations. Modern conversations include provider-specific
data (tool calls, reasoning blocks, thought signatures) that only the
originating model can properly understand and summarize.

Changes:
- Remove condensingApiHandler parameter from summarizeConversation()
- Remove condensingApiConfigId from context management and Task
- Remove API config dropdown for CONDENSE in settings UI
- Update telemetry to remove usedCustomApiHandler parameter
- Update related tests

Users can still customize the CONDENSE prompt text; only model selection
is removed.

* fix: remove condensingApiConfigId from types and test fixtures

---------

Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-22 20:06:04 -05:00
Hannes Rudolph
f414ba41a6
fix: correct token counting for context truncation display (#9961) 2025-12-16 16:12:02 -07:00
Hannes Rudolph
8aa13467d3
Refactor: Unified context-management architecture with improved UX (#9795)
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-12-07 17:43:48 -05:00
Hannes Rudolph
a1d392f5cc
fix: prevent cascading truncation loop by only truncating visible messages (#9844) 2025-12-04 20:41:49 -05:00
Hannes Rudolph
23605bed93
fix: restore context when rewinding after condense (#8295) (#9665) 2025-12-03 11:40:39 -05:00
Daniel
311940b085
fix: preserve tool_use blocks in summary message during condensing with native tools (#9582) 2025-11-25 13:17:26 -05:00
Hannes Rudolph
bb6cac4980
rename: sliding-window -> context-management; truncateConversationIfNeeded -> manageContext (#9206) 2025-11-12 22:16:25 -05:00