Replace transient pendingWorkingMessage with a persistent workingMessage
field on InteractiveMode, matching the workingIndicatorOptions pattern.
New loaders now use this.workingMessage || this.defaultWorkingMessage
instead of always falling back to the default.
Also add working-message-test.ts extension example.
closes#3566
* fix(typebox): migrate to v1 with extension compat
Replace AJV-based validation with TypeBox-native validation, keep legacy extension imports working (including @sinclair/typebox/compiler), and restore coercion for serialized/plain JSON schemas.
This change closes#3112.
* fix(typebox): use canonical imports and harden coercion
Switch first-party code to canonical typebox imports while retaining legacy extension aliases in the loader.
Remove obsolete runtime codegen guards, expand serialized JSON-schema coercion coverage, and update related tests and fixtures.
Fixes#3112.
---------
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
Emit OSC 9;4 progress start/end sequences during agent streaming and
compaction so terminals (iTerm2, WezTerm, Windows Terminal, Kitty, etc.)
show activity in their tab bar.
Made with love for @lucasmeijer
marked v15 does not filter dangerous URL protocols. The default link
renderer passes href values through verbatim, so markdown like
`[click](javascript:alert(1))` renders as a clickable XSS link in
shared/exported session HTML.
Add custom link and image renderers that:
- Block javascript:, vbscript:, and data: protocol URLs
- Escape href/title/alt attributes via escapeHtml()
Also escape img.mimeType in session image rendering to prevent
attribute breakout from crafted session JSONL.
Fixes#3531
Replace the deprecated global anthropic-beta header with per-tool
eager_input_streaming: true. Fix empty anthropic-beta header causing
400 errors on models with no beta features.
fixes#3175
Add getCommandDiagnostics and getShortcutDiagnostics mocks to fix
'Cannot read properties of undefined' errors in InteractiveMode tests.
regression from 32a305cb
Bypass the Anthropic SDK streaming parser entirely. Use
client.messages.create().asResponse() and decode the SSE stream
ourselves with defensive JSON parsing that repairs invalid escape
sequences and control characters inside string literals.
- Switch from SDK .stream() to .asResponse() + pi-owned SSE decoder
- Add repairJson() / parseJsonWithRepair() to json-parse.ts
- Add anthropic-sse-parsing.test.ts regression for malformed tool deltas
- Update github-copilot-anthropic.test.ts mock to match new call path
- Update deprecated claude-3-5-haiku-20241022 refs to claude-haiku-4-5
- Remove stale non-reasoning model test
fixes#3175
promptGuidelines bullets are appended flat to the Guidelines section
with no tool name prefix. Using 'Use this tool when...' is ambiguous
because the LLM cannot tell which tool 'this' refers to. Updated docs
and examples to use explicit tool names instead.
Rename BUILTIN_TOOLS to TEMPLATE_RENDERED_TOOLS to match what the set
actually represents: tools rendered directly by the HTML template instead of
pre-rendered through the TUI→ANSI→HTML pipeline.
Move grep and find off the template-rendered exclusion path so they use their
existing TUI renderCall/renderResult output in HTML export.
Add a dedicated HTML renderer for ls and keep it in the template-rendered set.
Unlike grep and find, rendering ls through the terminal-oriented Text component
introduced spacing artifacts in exported HTML due to full-width line padding,
so ls is rendered natively in the export template instead.
