Changelog

ShellContentProvider now discovers all IQuickActionProvider plugins at

indexing time and creates individual RAG chunks per quick action. This

replaces the hardcoded shortcut list that was manually maintained and

had drifted out of sync (e.g. listed Cmd+B for transactions instead of

Cmd+Shift+T).

Each quick action gets its own searchable chunk with the action name,

plugin, description, keyboard shortcut, and usage instructions. The

global shortcuts chunk now dynamically appends plugin shortcuts instead

of hardcoding them, so adding a new quick action to any plugin

automatically makes it discoverable by Duncan via semantic search.

Shell-level shortcuts (Cmd+K, Cmd+I, Cmd+M, etc.) remain hardcoded

since they are not plugin-declared.

Desktop version 1.65.5 → 1.65.6.

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

Three fixes for the AI creating duplicate tasks and inventing fake slots:

1. IntentEngine.ExecuteDirectAsync now validates slot names against the

IntentDescriptor before calling the plugin. Unknown slots (e.g.

"parent_task_id", "parent_id") are stripped and warnings attached to

the IntentResult. This prevents silent data loss.

2. Action execution results are now injected into conversation history

as an [Action Results] block. On the next turn, the AI sees what

succeeded, what failed, and what warnings were raised — enabling

self-correction instead of blindly retrying or duplicating.

3. ActionFormatHeader updated with explicit guidance: only use declared

slot names, use tasks.add_link for linking existing entities instead

of re-creating them, and acknowledge action result feedback.

Desktop version 1.65.4 → 1.65.5.

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

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>