bc7a0b753c
Update README.md
2026-03-10 17:43:52 +01:00
30dde5cf83
Update README.md
2026-03-10 17:43:16 +01:00
9c56c73838
Update README.md
2026-03-10 17:42:20 +01:00
ae1da96fb6
Update README.md
2026-03-10 17:39:52 +01:00
b54acbde41
Update README.md
2026-03-10 11:51:19 +01:00
4a06afd0f1
Update README.md
2026-03-10 10:24:39 +01:00
f41a9a6114
Update README.md
2026-03-10 10:23:33 +01:00
d3e7e22bb8
Update README.md
2026-03-10 08:57:52 +01:00
311fb08676
feat(summarization): implement summarization feature with dedicated widget and event handling
2026-03-10 01:13:30 +00:00
903ef4d158
feat(thread-picker): add ThreadPickerWidget for inline thread selection in TUI
2026-03-10 00:45:21 +00:00
aad431785c
feat(diff): implement unified diff formatting for edit_file tool results
2026-03-09 22:18:54 +00:00
4c53bb0480
fix(cli): update welcome slogans for clarity and engagement
2026-03-09 17:30:20 +00:00
6817128a03
fix(models): remove deprecated gemini-3-pro model entry from registry
2026-03-09 16:46:09 +00:00
18b1d38aa5
fix(onboard): update wechat dependencies and improve package display formatting
...
fix(cli): unify directory handling in print_banner and _build_welcome_banner functions
2026-03-09 15:01:26 +00:00
c4de31c772
fix(ui): map legacy UI backend values to current equivalents in normalization
2026-03-09 10:38:42 +00:00
68f432b39d
Fix/onboard channel auto install ( #22 )
...
* small fix
* small fix
* small fix
2026-03-09 10:33:10 +00:00
ce33de79af
fix(onboard): map legacy 'textual' value to 'tui' for UI backend default ( #21 )
...
Add mapping for legacy 'textual' value to current 'tui' value when
selecting UI backend, preventing invalid default selection.
2026-03-09 10:19:47 +00:00
3885197559
docs: update CONTRIBUTING.md with test count and headless mode instructions
2026-03-08 17:18:19 +00:00
f3bb70c74e
feat(serve): implement headless serve mode with message processing and interrupt handling
2026-03-08 17:06:40 +00:00
260ee95697
feat(ui): update UI backend references from 'rich' to 'tui' in onboarding and interactive components
2026-03-08 16:44:28 +00:00
a118d3ed23
refactor(onboard): simplify workspace step to return only selected mode
...
test(onboard): update tests for workspace step to reflect mode-only return
2026-03-08 16:16:40 +00:00
07e57e110b
feat(ui): update UI backend options to use 'cli' and 'tui'
2026-03-08 15:34:22 +00:00
659fbc7f84
feat(interactive): implement history-based auto-suggest for TUI input
2026-03-08 15:07:17 +00:00
a91d6def40
fix(interactive): remove unused os import from interactive.py
2026-03-08 14:40:57 +00:00
ed376d1b5b
fix(interactive): update history file path to use config directory
2026-03-08 14:38:11 +00:00
085cef4463
Update README.md
2026-03-08 14:25:46 +01:00
5ea9f3e938
feat(serve): add auto-approve option for tool executions
...
docs: update README to include HITL action approval details
tests: adjust mock for get_effective_config in CLI serve tests
2026-03-07 21:13:40 +00:00
833fa0abfb
Implement HITL (Human-in-the-Loop) approval mechanism
...
- Added HITL approval lifecycle to ToolCallWidget, including a new "rejected" status.
- Introduced configuration options for auto-approval and shell command allow list in EvoScientistConfig.
- Developed approval handling functions in display module to manage HITL interrupts and user decisions.
- Created ApprovalWidget for user interaction during approval prompts.
- Enhanced StreamEventEmitter to support interrupt events.
- Updated StreamState to track pending interrupts.
- Implemented tests for HITL functionality, including event structure, state handling, and approval logic.
2026-03-07 21:02:35 +00:00
bdd3e30284
feat(ollama): enable reasoning by default for Ollama models and update tests
2026-03-07 18:44:11 +00:00
250c41c561
feat(token-usage): implement token usage tracking and display widget
2026-03-07 15:16:29 +00:00
cdb5507896
fix(dependencies): update deepagents version to 0.4.7 for compatibility
2026-03-07 12:49:07 +00:00
6992e37ce5
feat(tui-interactive): update color scheme for improved visibility and aesthetics
2026-03-07 12:09:02 +00:00
0c5d0049a4
feat(tui-interactive): implement throttled scrolling for long content and improve Markdown rendering efficiency
2026-03-07 01:28:44 +00:00
d2555ac10f
feat(tui-interactive): implement message queueing and editing functionality
2026-03-07 01:09:52 +00:00
0a823c6e0d
feat(thinking-widget): enhance collapsible behavior and improve display logic
2026-03-07 00:10:53 +00:00
e7c06f8ddb
feat(display): enhance streaming display with final frame rendering and improved thinking text handling
2026-03-06 23:50:04 +00:00
d69ba4ec8b
feat(skill-creator): enhance HTML documentation and improve benchmark packaging validation
2026-03-06 23:29:37 +00:00
5e1235627d
feat(skill-creator): enhance documentation and validation scripts
...
- Updated SKILL.md for clarity on headless environments
- Adjusted runs_per_configuration logic in aggregate_benchmark.py
- Improved description placeholder in init_skill.py
- Added strict validation checks in quick_validate.py
- Ensured skill-creator root is included in sys.path for script imports
2026-03-06 23:12:37 +00:00
0897f3a2e1
Update
2026-03-06 22:31:12 +00:00
8c77ece5e5
docs(CONTRIBUTING): update test count and add details for skill-creator licensing
2026-03-06 21:35:49 +00:00
eeb0a21275
feat(license): add Apache License 2.0 to skill-creator directory
...
style(eval_review): update button colors and instructions for clarity
style(viewer): modify accent colors and update instructions for agent
docs(output-patterns): replace "Claude" with "agent" for consistency
docs(workflows): replace "Claude" with "agent" for consistency
fix(improve_description): update skill description context to refer to EvoScientist
fix(init_skill): update references to "Claude" to "agent" for consistency
2026-03-06 15:03:36 +00:00
13858b860a
feat(models): add zhipu and zhipu-code providers to models registry tests
2026-03-06 14:19:00 +00:00
b14dceb143
feat(models): add glm-5, glm-4.7 from zhipu API (with code plan supoort) ( #19 )
...
* feat(models): add glm-5, glm-4.7 from zhipu API (with code plan supoort)
* fix: add zhipu and zhipu-code to valid providers in test
2026-03-06 08:57:33 +00:00
5f2d963a97
Update README.md
2026-03-06 06:00:02 +01:00
c62c7d24e2
fix(run_eval): remove reasoning kwarg for OpenAI provider to allow default model behavior
2026-03-06 02:36:16 +00:00
67a60b9ca1
feat(models): add gpt-5.4 model entry to the OpenAI provider
2026-03-06 02:08:55 +00:00
b05576cdbc
feat: Add skill description improvement and evaluation scripts
...
- Implemented `improve_description.py` to enhance skill descriptions based on evaluation results using LLMs.
- Created `run_eval.py` to evaluate skill descriptions against a set of queries, determining trigger effectiveness.
- Developed `run_loop.py` to automate the evaluation and improvement process, tracking history and optimizing descriptions iteratively.
- Added utility functions in `utils.py` for parsing skill metadata from SKILL.md files.
- Enhanced `package_skill.py` to exclude unnecessary files and directories during skill packaging.
- Updated `quick_validate.py` to include compatibility checks in skill validation.
2026-03-06 00:38:07 +00:00
313e48eb62
fix: update default model to claude-sonnet-4-6 and increase recursion limit to 1000
2026-03-04 20:23:02 +00:00
3be3f5adf0
feat(subagent): implement visibility management for completed and running tools in SubAgentWidget
2026-03-04 19:26:08 +00:00
bf4e297cbb
fix(tui): Disable auto refresh during generation when using Rich
...
In some terminals there is heavy flicker when auto refresh was being used. No cause could be found
2026-03-04 16:21:28 +01:00
Yougang Lyu