Commit Graph

221 Commits

Author SHA1 Message Date
Mario Zechner df8b3544c3 Add [Unreleased] section for next cycle 2026-01-22 01:43:26 +01:00
Mario Zechner 0e5977ad39 Add [Unreleased] section for next cycle 2026-01-19 00:23:57 +01:00
Mario Zechner 632495338f Add [Unreleased] section for next cycle 2026-01-17 22:02:59 +01:00
Mario Zechner 7f9cf543d5 Add [Unreleased] section for next cycle 2026-01-17 00:32:57 +01:00
Mario Zechner ffdc8d686b docs: add OpenCode Zen to provider lists in coding-agent README 2026-01-16 21:20:52 +01:00
Mario Zechner 356a482527 fix(tui): add vertical scrolling to Editor when content exceeds terminal height
The Editor component now accepts TUI as the first constructor parameter,
enabling it to query terminal dimensions. When content exceeds available
height, the editor scrolls vertically keeping the cursor visible.

Features:
- Max editor height is 30% of terminal rows (minimum 5 lines)
- Page Up/Down keys scroll by page size
- Scroll indicators show lines above/below: ─── ↑ 5 more ───

Breaking change: Editor constructor signature changed from
  new Editor(theme)
to
  new Editor(tui, theme)

fixes #732
2026-01-16 04:12:21 +01:00
Mario Zechner 6484ae279d Finalize OpenAI Codex compatibility (#737)
- align Codex Responses provider with Pi static instructions
- simplify Codex request/stream handling and cleanup exports
- keep legacy OpenCode Codex prompt for testing until Pi prompt is allowlisted
2026-01-16 00:58:36 +01:00
Mario Zechner e46cc55fe0 Add [Unreleased] section for next cycle 2026-01-15 17:36:40 +01:00
Aadish Verma cd83e73845 feat: add gpt-5.2-codex models for copilot & zen (#734) 2026-01-15 03:24:20 +01:00
Mario Zechner cc8c51d9ae chore(ai): regenerate models 2026-01-14 22:25:21 +01:00
Mario Zechner 0a7537bf86 Revert "feat(ai): add gpt-5.2-codex to OpenAI provider (#730)"
This reverts commit 5a795b9857.
2026-01-14 22:22:55 +01:00
Anton 5a795b9857 feat(ai): add gpt-5.2-codex to OpenAI provider (#730)
* feat(ai): add gpt-5.2-codex to OpenAI provider

* fix(ai): avoid build break when model generation misses providers
2026-01-14 22:21:01 +01:00
Jian Zhang 558a77b45f feat(ai): add support for MiniMax China (minimax-cn) provider (#725)
Co-authored-by: Jian Zhang <jzhang@yanhuangdata.com>
2026-01-14 15:41:47 +01:00
Mario Zechner 09d409cc92 Fix z.ai thinking/reasoning params, fixes #688
Z.ai uses thinking: { type: "enabled" | "disabled" } instead of
OpenAI's reasoning_effort. Added thinkingFormat compat flag to handle
this. Thinking is now explicitly enabled/disabled based on user setting.
2026-01-13 18:34:07 +01:00
Timo Lins dd263f3c24 Update model list 2026-01-13 16:42:34 +01:00
Timo Lins 65eb738c90 Rename to vercel-ai-gateway for clarity 2026-01-13 16:42:34 +01:00
Timo Lins 9860ee86f3 Change to Anthropic compatible API
It seemed as if the OpenAI message spec tried to send non-compliant messages with { text: "" } instead of { contet: "" }, which the AI Gateway did not accept.
2026-01-13 16:42:34 +01:00
Timo Lins 164a69a601 Add Vercel AI Gateway support 2026-01-13 16:42:34 +01:00
Markus Ylisiurunen 922b0a4668 add eu cross-region inference model ids for anthropic models (#685) 2026-01-13 13:02:27 +01:00
Mario Zechner 8af8d0d672 Add MiniMax provider support (#656 by @dannote)
- Add minimax to KnownProvider and Api types
- Add MINIMAX_API_KEY to getEnvApiKey()
- Generate MiniMax-M2 and MiniMax-M2.1 models
- Add context overflow detection pattern
- Add tests to all required test files
- Update README and CHANGELOG with attribution

Also fixes:
- Bedrock duplicate toolResult ID when content has multiple blocks
- Sandbox extension unused parameter lint warning
2026-01-13 02:27:09 +01:00
Mario Zechner fd268479a4 feat(ai): Add Amazon Bedrock provider (#494)
Adds support for Amazon Bedrock with Claude models including:
- Full streaming support via Converse API
- Reasoning/thinking support for Claude models
- Cross-region inference model ID handling
- Multiple AWS credential sources (profile, IAM keys, API keys)
- Image support in messages and tool results
- Unicode surrogate sanitization

Also adds 'Adding a New Provider' documentation to AGENTS.md and README.

Co-authored-by: nickchan2 <nickchan2@users.noreply.github.com>
2026-01-13 00:32:59 +01:00
Mario Zechner 7cad705a15 Add [Unreleased] section for next cycle 2026-01-12 19:05:08 +01:00
Mario Zechner 5f380822ea Revert "Fix jiti alias resolution in dev mode with tsx"
This reverts commit c7aa2c97a9.
2026-01-12 17:41:46 +01:00
Mario Zechner c7aa2c97a9 Fix jiti alias resolution in dev mode with tsx
When running from source with tsx, the jiti aliases pointed to .js files
that don't exist (only .ts files exist). This caused jiti to fall back to
different module resolution, loading a separate instance of theme.ts where
initTheme() was never called, resulting in undefined theme.

Now checks if .js exists and falls back to .ts for dev mode compatibility.
2026-01-12 17:38:31 +01:00
Mario Zechner a46c4aab4f Revert "Initialize theme with default value at module load time"
This reverts commit d18e44d378.
2026-01-12 17:29:56 +01:00
Mario Zechner d18e44d378 Initialize theme with default value at module load time
Prevents undefined theme when extensions call ctx.ui.custom() in edge cases
where module resolution could cause the theme variable to be accessed before
initTheme() is called.
2026-01-12 17:27:59 +01:00
Aadish Verma 92eb6665fe feat: add API pricing for antigravity models (#588) 2026-01-09 22:20:51 +01:00
Mario Zechner 60f5a03576 Add [Unreleased] section for next cycle 2026-01-09 20:24:50 +01:00
Mario Zechner 97d0189eae Add OpenCode Zen provider support 2026-01-09 06:58:20 +01:00
Mario Zechner 307f9b4169 Add [Unreleased] section for next cycle 2026-01-09 00:10:41 +01:00
Mario Zechner 39fa25eb67 fix(ai): clean up openai-codex models and token limits
- Remove model aliases (gpt-5, gpt-5-mini, gpt-5-nano, codex-mini-latest, gpt-5-codex, gpt-5.1-codex, gpt-5.1-chat-latest)
- Fix context window from 400k to 272k tokens to match Codex CLI defaults
- Keep maxTokens at 128k (original value)
- Simplify reasoning effort clamping

closes #536
2026-01-07 20:39:46 +01:00
Zhou Rui d893ba7f20 fix(ai): clean up openai-codex models and token limits 2026-01-07 23:09:20 +08:00
Ben Vargas e80a924292 fix: add accurate pricing for openai-codex OAuth models (#501)
Previously all openai-codex models had pricing set to 0, causing the
TUI to always show $0.00 for cost tracking.

Updated pricing based on OpenAI Standard tier rates:
- gpt-5.2/gpt-5.2-codex: $1.75/$14.00 per 1M tokens
- gpt-5.1/gpt-5.1-codex/gpt-5.1-codex-max: $1.25/$10.00 per 1M tokens
- gpt-5/gpt-5-codex: $1.25/$10.00 per 1M tokens
- codex-mini-latest: $1.50/$6.00 per 1M tokens
- gpt-5-mini/gpt-5.1-codex-mini/gpt-5-codex-mini: $0.25/$2.00 per 1M tokens
- gpt-5-nano: $0.05/$0.40 per 1M tokens

Source: https://platform.openai.com/docs/pricing
2026-01-06 17:45:09 +01:00
Mario Zechner b85cb53dfb chore: update generated models from OpenRouter 2026-01-06 00:06:56 +01:00
Mario Zechner 0b9e3ada0c fix: clean up Codex thinking level handling
- Remove per-thinking-level model variants (gpt-5.2-codex-high, etc.)
- Remove thinkingLevels from Model type
- Provider clamps reasoning effort internally
- Omit reasoning field when thinking is off

fixes #472
2026-01-05 21:58:26 +01:00
Ben Vargas 02b72b49d5 fix: codex thinking handling 2026-01-05 21:55:47 +01:00
Mario Zechner bb50738f7e fix(ai): append system prompt to codex bridge message instead of converting to input
Previously the system prompt was converted to an input message in convertMessages,
then stripped out by filterPiSystemPrompts. Now the system prompt is passed directly
to transformRequestBody and appended after CODEX_PI_BRIDGE in the bridge message.
2026-01-05 06:03:07 +01:00
Mario Zechner 61cadc226c Add [Unreleased] section for next cycle 2026-01-04 20:30:34 +01:00
Mario Zechner 892acedb6b feat(hooks): add tools.ts example hook for interactive tool enable/disable
- /tools command opens SettingsList-based selector for all loaded tools
- Space/Enter toggles individual tools between enabled/disabled
- Changes apply immediately on toggle (like /settings)
- Tool selection persisted to session via appendEntry()
- State restored from current branch on session_start, session_tree, session_branch
- Uses getBranch() to respect branch-specific tool configuration
- Export getSettingsListTheme and getSelectListTheme for hooks to use
2026-01-04 18:13:30 +01:00
Anton Kuzmenko 3b61d83d29 Fix google-vertex build 2026-01-03 01:11:03 +01:00
Anton Kuzmenko 214e7dae15 Add Vertex AI provider with ADC support
- Implement google-vertex provider in packages/ai
- Support ADC (Application Default Credentials) via @google/generative-ai
- Add Gemini model catalog for Vertex AI
- Update packages/coding-agent to handle google-vertex provider
2026-01-03 01:11:03 +01:00
Mario Zechner e76ad7aebe Add [Unreleased] section for next cycle 2026-01-02 02:00:36 +01:00
Mario Zechner 256fa575fb WIP: Rewrite export-html with tree sidebar, client-side rendering
- Add tree sidebar with search and filter (Default/All/Labels)
- Client-side markdown/syntax highlighting via vendored marked.js + highlight.js
- Base64 encode session data to avoid escaping issues
- Reuse theme.ts color tokens via getResolvedThemeColors()
- Sticky sidebar, responsive mobile layout with overlay
- Click tree node to scroll to message
- Keyboard shortcuts: Esc to reset, Ctrl/Cmd+F to search
2026-01-01 03:36:47 +01:00
Mario Zechner 3d76a21036 Regenerate models after rebase 2025-12-30 22:43:02 +01:00
Mario Zechner c86f2a0136 Fix rebase issues: regenerate models, fix mom agent API 2025-12-30 22:42:25 +01:00
Mario Zechner 4ef3325cec Store file lists in BranchSummaryEntry.details for cumulative tracking
- BranchSummaryResult now returns readFiles and modifiedFiles separately
- BranchSummaryDetails type for details: { readFiles, modifiedFiles }
- branchWithSummary accepts optional details parameter
- Collect files from existing branch_summary.details when preparing entries
- Files accumulate across nested branch summaries
2025-12-30 22:42:24 +01:00
Mario Zechner 01dae9ebcc Fix branch summarization abort handling and tree navigation
- Check response.stopReason instead of catching errors for abort detection
- Return result object from _generateBranchSummary instead of throwing
- Fix summary attachment: attach to navigation target position, not old branch
- Support root-level summaries (parentId=null) in branchWithSummary
- Remove setTimeout hack for re-showing tree selector on abort
2025-12-30 22:42:23 +01:00
Mario Zechner 9dac0a1423 WIP: Add branch summarization abort support with loader and escape handler 2025-12-30 22:42:23 +01:00
Mario Zechner 159e19a010 Fix tree selector gutter alignment, add page navigation, improve styling
- Fix gutter/connector alignment by tracking gutter positions with GutterInfo
- Convert recursive markContains to iterative to avoid stack overflow
- Add left/right arrow keys for page up/down navigation
- Consistent assistant message styling (green prefix, appropriate status colors)
- Remove leaf marker (*), active path bullets are sufficient
- Add Expandable interface for toggle expansion
- Fix BranchSummaryMessageComponent expansion toggle
2025-12-30 22:42:23 +01:00
Mario Zechner 4958271dd3 feat(coding-agent): implement /tree command for session tree navigation
- Add TreeSelectorComponent with ASCII tree visualization
- Add AgentSession.navigateTree() for switching branches
- Add session_before_tree/session_tree hook events
- Add SessionManager.resetLeaf() for navigating to root
- Change leafId from string to string|null for consistency with parentId
- Support optional branch summarization when switching
- Update buildSessionContext() to handle null leafId
- Add /tree to slash commands in interactive mode
2025-12-30 22:42:22 +01:00