Changelog

IntentResult now carries an optional IReadOnlyList<string> Warnings property.

This allows the intent execution pipeline to report non-fatal issues like

unknown slot names back to the AI and user, enabling self-correction on

subsequent turns rather than silently ignoring invalid slots.

SDK version bumped 1.65.0 → 1.65.1.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

The AI was writing "✓ Created task X" with zero [ACTION] blocks,

fabricating success messages without actually executing anything.

Strengthened the ACTION format header to explicitly forbid claiming

completion without corresponding [ACTION] blocks. Added rules:

• Writing checkmarks/success without [ACTION] = lying to the user
• N actions requested = N [ACTION] blocks required, no shortcuts
• Never pretend you did something — say you can't if no action exists

Version: 1.65.3 -> 1.65.4

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

The link picker popup, ViewModel, XAML, and keyboard routing were all

implemented but the [[ detection never fired. The OnTextInput override

on the UserControl relied on TextInput events bubbling up from the

TextBox, but Avalonia's TextBox marks TextInput as handled, preventing

bubble propagation to parent controls.

Fixed by attaching a tunnel-phase TextInput handler directly on the

ChatInputBox via AddHandler with RoutingStrategies.Tunnel. Tunnel

routing intercepts the event BEFORE the TextBox processes it, so we

can detect the second [ keystroke, remove the first [ already in the

text, suppress the second [ from being inserted, and open the picker.

Version: 1.65.2 -> 1.65.3

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

The regex-based ACTION block parser used [^[]* which broke on any JSON

containing literal [ characters (e.g. checklist arrays, tags arrays).

This caused 0 blocks parsed despite valid-looking [ACTION] output,

silently dropping AI actions that would have updated tasks.

Replaced regex approach with brace-depth counting that handles nested

{}, [], and quoted strings correctly. Also added FlattenSlotValue()

which converts JSON arrays to newline-separated strings — so when the

AI sends "add_checklist": ["item1", "item2"], it becomes the

newline-delimited format the intent handler expects.

Added ACTION format header guidance for slot naming (add_checklist not

checklist) and array support.

Version: 1.65.1 -> 1.65.2

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Cloud providers handle their own context limits and bill per token, so

artificially capping them at 200/1200/2500 caused truncation errors

(MAX_TOKENS from Gemini). Raised cloud token budgets to 1024/4096/8192

— the system prompt's length guidance still controls actual verbosity.

Also bumped AiMemoryExtractor MaxTokens from 100 to 256 to prevent

JSON truncation that caused the JsonReaderException on memory extraction.

Version: 1.65.0 -> 1.65.1

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>