switchSession() was appending spurious thinking_level_change entries
to session log on resume because setThinkingLevel() unconditionally
persisted. Now only persists if the level actually changes.
fixes#1118
WSL2/WSLg often provides clipboard images as image/bmp only.
Previously this resulted in invalid PNG files being written.
Now readClipboardImage() converts unsupported formats to PNG
via Photon before returning.
Closes#1109
Based on #1112 by @lightningRalf
Package resolution now uses the same discovery logic as local extensions:
only index.ts (or manifest-declared entries) are loaded from subdirectories,
not helper modules.
fixes#1102
Adds a method to access the effective system prompt (after any per-turn
extension modifications) from the extension context.
Implementation:
- Add systemPrompt getter to AgentSession reading from agent.state.systemPrompt
- Wire getSystemPrompt through ExtensionContextActions to ExtensionRunner
- Add getSystemPrompt to interactive-mode's shortcut context
- Update docs with ctx.getSystemPrompt() section
- Add system-prompt-header.ts example
- Add example to docs reference table
Closes#1098
Fixes#1078
- Add tryNFDVariant() to normalize paths to NFD form
- Add tryCurlyQuoteVariant() to convert straight quotes to curly quotes
- Try combined NFD + curly quote variant for French macOS screenshots
- Add comprehensive tests for path-utils
- Add kimi-coding provider using Anthropic Messages API
- API endpoint: https://api.kimi.com/coding/v1
- Environment variable: KIMI_API_KEY
- Models: kimi-k2-thinking (text), k2p5 (text + image)
- Add context overflow detection pattern for Kimi errors
- Add tests for all standard test suites
Previously, within a single tool-use turn, rate limit retries would
accumulate across separate LLM calls. For example, if each of 3 tool
calls hit a 429 and retried once, the counter would show '3/3' and fail
even though each individual retry succeeded.
Now the counter resets immediately when a successful (non-error)
assistant message arrives, so each LLM call gets a fresh set of retries.
Fixes#1019
- Add alt+b/alt+f as alternative bindings for cursorWordLeft/cursorWordRight
- Add ctrl+d as alternative binding for deleteCharForward
- Fix ctrl+d in custom editor to perform delete when text is present
(previously it was always consumed, even with non-empty input)
Closes#1043
Co-authored-by: Jason Ish <ish@unx.ca>
Move setup callback handling from interactive/rpc modes into AgentSession.newSession().
After setup() runs, sync agent state via replaceMessages() so the LLM has context
and the UI renders the messages properly.
fixes#968
- Merged theme.md content into themes.md
- Added hot reload documentation
- Updated all references from theme.md to themes.md
- Fixed outdated info (vars not defs, complete example with all 50 tokens)
- Removed dev-focused Implementation section
* fix(coding-agent): HTML export sidebar click scrolls instead of truncating branch
Previously, clicking a message in the sidebar tree would set that message
as the new leaf, causing getPath() to only return messages up to that point
and hiding all messages below it.
Now handleTreeNodeClick() checks if the clicked entry is on the current path:
- If yes: just scrolls to it without re-rendering
- If no: finds the actual leaf of that branch and navigates to it, then
scrolls to the clicked message
Added childrenMap for parent->children lookup and findBranchLeaf() to
traverse down to a branch's leaf.
* fix(coding-agent): HTML export sidebar click scrolls instead of truncating branch
Previously, clicking a message in the sidebar tree would set that message
as the new leaf, causing getPath() to only return messages up to that point
and hiding all messages below it.
Now handleTreeNodeClick() checks if the clicked entry is on the current path:
- If yes: scrolls to it and updates the active marker
- If no: finds the branch's leaf, navigates to it, then scrolls to clicked message
Adds currentTargetId to track the selected entry separately from currentLeafId
(which branch to display), so the active marker follows user selection.
* most recent path wins
* reuse method
* revert
* feat(coding-agent): highlight active path in HTML export sidebar
- Add subtle accent background tint to in-path nodes
- Dim off-path nodes to 50% opacity (restore on hover)
- Makes current branch visually distinct in tree navigation
* docs(coding-agent): move changelog entry to Unreleased and add attribution
* chore(coding-agent): remove dead code and fix changelog attribution
- Remove unused childrenMap, findBranchLeaf, handleTreeNodeClick, scrollToEntry
- Split changelog entry: navigation (#853 by @mitsuhiko), highlighting (#929 by @hewliyang)
Extensions calling setWorkingMessage() in agent_start handlers previously
had no effect because the loading animation didn't exist yet. Now the
message is queued and applied once the loader is created.
Fixes#935
- Add resetApiProviders() to clear and re-register built-in providers
- Add createAssistantMessageEventStream() factory for extensions
- Add streamSimple support in ProviderConfig for custom API implementations
- Call resetApiProviders() on /reload to clean up extension providers
- Add custom-provider.md documentation
- Add custom-provider.ts example with full Anthropic implementation
- Update extensions.md with streamSimple config option
When set to true, the skill is hidden from the system prompt, preventing
agentic invocation. Users can still invoke explicitly via /skill:name.
Also fixes pre-existing test bug where source expectation was wrong.
Fixes#927
