Commit Graph
884 Commits
Author SHA1 Message Date
Ahmed KamalandGitHub c7b8f8a7db Add X-Initiator header for GitHub Copilot (#200) 2025-12-16 14:05:22 +01:00
Markus YlisiurunenandGitHub 17b4cfe6aa Fix double new line issues in markdown rendering (#199)
* prevent double blank lines after markdown elements

* prevent double blank lines after markdown elements
2025-12-16 00:25:06 +01:00
Mario Zechner 5994e1eed1 Fix ANSI styles not preserved across newlines in text wrapping
wrapTextWithAnsi() was processing each line independently after splitting
on newlines, losing ANSI state. When styled text contained embedded newlines
(e.g. from markdown paragraphs), subsequent lines would lose their styling.

Fixed by tracking ANSI state across lines and prepending active codes to
lines after the first.

Fixes #197
2025-12-15 23:00:25 +01:00
Mario Zechner 263864cc0b Fix reasoning disabled by default for all providers
Previously, when reasoning was not specified, some providers like Gemini
with 'dynamic thinking' enabled by default would still use thinking.
Now explicitly sets thinkingEnabled: false (Anthropic) and
thinking: { enabled: false } (Google) when reasoning is undefined.

Closes #180
2025-12-15 22:42:08 +01:00
Mario Zechner de55b4a824 Fix RGB to 256-color mapping for non-truecolor terminals 2025-12-15 22:32:23 +01:00
Mario Zechner d5ebe1dc48 Release v0.22.2 2025-12-15 22:09:14 +01:00
Mario Zechner 964565c69a Release v0.22.1 2025-12-15 21:53:27 +01:00
Mario Zechner b5a2482e3c Release v0.22.0 2025-12-15 20:14:25 +01:00
Mario Zechner 696a142a91 Minor README cleanup 2025-12-15 20:10:05 +01:00
Mario Zechner 540b831716 Update docs and changelogs for GitHub Copilot changes 2025-12-15 20:08:06 +01:00
Mario Zechner f3a2dee86b GitHub Copilot: auto-enable models, fix gpt-5 API, normalize tool call IDs
- Auto-enable all models after /login via POST /models/{model}/policy
- Use openai-responses API for gpt-5/o3/o4 models (not accessible via completions)
- Normalize tool call IDs when switching between github-copilot models with different APIs
  (fixes #198: openai-responses generates 450+ char IDs with special chars that break other models)
- Update README with streamlined GitHub Copilot docs
2025-12-15 20:06:11 +01:00
Mario Zechner 6a2e3b1d88 Fix GitHub Copilot model enablement instructions (VS Code, not web) 2025-12-15 19:18:07 +01:00
Mario Zechner fb8938972d Add GitHub Copilot documentation to packages/ai README 2025-12-15 19:16:56 +01:00
Mario Zechner 69200399c5 Read GitHub Copilot token from oauth.json in test 2025-12-15 19:16:08 +01:00
Mario Zechner fb4f0ac33e Add GitHub Copilot test to packages/ai 2025-12-15 19:12:43 +01:00
Mario Zechnerandcau1k 555a736051 Add GitHub Copilot support (#191)
- OAuth login for GitHub Copilot via /login command
- Support for github.com and GitHub Enterprise
- Models sourced from models.dev (Claude, GPT, Gemini, Grok, etc.)
- Dynamic base URL from token's proxy-ep field
- Use vscode-chat integration ID for API compatibility
- Documentation for model enablement at github.com/settings/copilot/features

Co-authored-by: cau1k <cau1k@users.noreply.github.com>
2025-12-15 19:05:17 +01:00
Mario Zechner 8a47cb4e3b Merge branch 'main' into pr-191-github-copilot-auth 2025-12-15 18:10:15 +01:00
Mario Zechner 5cb6bbf421 Fix model selector fuzzy search to match provider and support multi-token queries 2025-12-15 18:05:32 +01:00
cau1k df16cfec47 clean up 2025-12-15 00:34:38 -05:00
cau1k 28e5a8d698 fix: model context windows 2025-12-15 00:17:59 -05:00
cau1k 277afec0bb feat: added filter for generate-models and regenerated
- blacklisted gpt-4o-2024-08-06, gpt-4o-2024-11-20, gpt-3.5-turbo-0613,
gpt-4, gpt-4-0613
2025-12-14 22:26:43 -05:00
cau1k 94eb326663 feat: generate models base on copilot /models endpoint, requires GH token 2025-12-14 18:42:57 -05:00
Mario Zechner bcbfac9aa0 Add artifacts server documentation 2025-12-14 23:36:26 +00:00
cau1k 22ceacfbd7 feat: models.dev in generate models - too many deprecated models
could have opted for a whitelist but we'll just fetch from the copilot
/models endpoint
2025-12-14 17:47:42 -05:00
cau1k fd2e433d30 feat: initial impl
- add GitHub Copilot model discovery (env token fallback, headers,
compat) plus fallback list and quoted provider keys in generated map
- surface Copilot provider end-to-end (KnownProvider/default, env+OAuth
token refresh/save, enterprise base URL swap, available only when
creds/env exist)
- tweak interactive OAuth UI to render instruction text and prompt
placeholders

gpt-5.2-high took about 35 minutes. It had a lot of trouble with `npm
check`  and went off on a "let's adjust every tsconfig" side quest.
Device code flow works, but the ai/scripts/generate-models.ts impl is
wrong as models from months ago are missing and only those deprecated
are accessible in the /models picker.
2025-12-14 17:18:13 -05:00
Mario Zechner 63b10905da Add empty Unreleased section to CHANGELOG 2025-12-13 23:56:41 +01:00
Mario Zechner aeb41c8ecd Release v0.21.0 2025-12-13 23:55:31 +01:00
Mario Zechner 1e5ecf2eaa Fix image rendering artifacts and improve show-images selector
- Image component returns correct number of lines (rows) for TUI accounting
- Empty lines rendered first, then cursor moves up and image is drawn
- This clears the space the image occupies before rendering
- Add spacer before inline images in tool output
- Create ShowImagesSelectorComponent with borders like other selectors
- Use showSelector pattern for /show-images command
2025-12-13 23:53:28 +01:00
Mario Zechner 3144c33091 Remove accidentally committed out.cast file 2025-12-13 23:22:45 +01:00
Mario Zechner 1cb273bf44 Merge feature/tui-inline-images: Inline image rendering for supported terminals 2025-12-13 23:22:31 +01:00
Mario Zechner fbbf49e4ac Update docs for inline images, remove PI_NO_IMAGES env var
- Add CHANGELOG entry for inline image rendering feature
- Add /show-images to slash commands table in README
- Expand Image Support section with inline rendering info
- Add terminal.showImages to settings documentation
- Remove PI_NO_IMAGES environment variable feature
2025-12-13 23:21:18 +01:00
Mario Zechner 36f791eb94 Update existing tool components when toggling show-images setting 2025-12-13 23:15:56 +01:00
Mario Zechner e18f96aa74 Only query cell size if terminal supports images 2025-12-13 23:15:15 +01:00
Mario Zechner 9a1d5df072 Add /show-images command to toggle inline image display
- Add terminal.showImages setting to settings-manager.ts
- Add /show-images slash command (only visible if terminal supports images)
- ToolExecutionComponent checks both terminal support and user setting
- Shows text fallback when inline images are disabled
2025-12-13 23:14:46 +01:00
Mario Zechner 19fcebd863 Fix image aspect ratio by querying terminal cell size
- Add getCellDimensions/setCellDimensions to terminal-image.ts
- TUI queries cell size on startup via CSI 16 t
- Parse response and filter it from user input
- Invalidate and re-render when cell dimensions received
- Pass rows parameter to Kitty protocol for correct aspect ratio
2025-12-13 23:09:05 +01:00
Mario Zechner 0c1f6c146d Add changelog entry for PR #181 - fix macOS screenshot filenames 2025-12-13 22:07:56 +01:00
Nico BailonandGitHub ee6ff952b2 coding-agent: fix macOS screenshot filenames with unicode spaces (#181) 2025-12-13 22:04:01 +01:00
badlogic 737d5e8603 Add timestamps to note skill and grep examples for searching 2025-12-13 21:01:32 +00:00
badlogic d2afd16d07 Add Creating a Skill example and clarify standard CLI tools 2025-12-13 21:00:28 +00:00
badlogic f98b2278b4 Update Message History section and remove Key Concepts 2025-12-13 20:48:47 +00:00
badlogic 2ffbda6d05 Simplify Skills section and move before Events 2025-12-13 20:43:16 +00:00
badlogic 2207680320 Update Memory section: remove sessions concept, clarify as rules/preferences 2025-12-13 20:35:34 +00:00
badlogic 6c20567ed0 Replace Claude mentions with LLM in README 2025-12-13 20:33:01 +00:00
badlogic 9dc1853b47 Clarify mom's message flow and context management in README 2025-12-13 20:31:04 +00:00
Nico Bailon 6552205f44 add image component docs to readme 2025-12-12 19:38:36 -08:00
Nico Bailon 6932570ac0 add PI_NO_IMAGES env var to disable inline image rendering 2025-12-12 19:35:54 -08:00
Nico Bailon 2954022690 add inline image rendering for terminals with graphics support 2025-12-12 19:30:50 -08:00
Mario Zechner 10288d96c5 Add coding-agent changelog entry for Gemini 3 Pro thinking levels 2025-12-13 02:11:25 +01:00
Mario Zechner 092021a519 Add changelog entry for #176 (Gemini 3 Pro thinking levels) 2025-12-13 02:10:38 +01:00
Markus YlisiurunenandGitHub 61e8d4f94e Support thinking level configuration for Gemini 3 Pro models (#176)
* support Google thinking level configuration for Gemini 3 Pro models

* relax model ID check for gemini 3 pro
2025-12-13 02:09:54 +01:00