Changelog

IntentEngine.ExecuteAsync now resolves SourceLinkType from the source signal's

entity type and passes it to the IntentRequest. This enables consuming plugins

to create back-links to the originating entity when an intent is executed

(e.g., email triggers task creation → task links back to email).

Desktop v1.42.1

The 1B model was randomly picking from 10 intent IDs (e.g. webclips for

a doctor appointment). With too many options, small models can't

discriminate reliably. Now filters to only signal-relevant intents:

TextContent signals see calendar, tasks, contacts, email (4 options).

EmailReceived signals see calendar, tasks, contacts (3 options).

UserRequest (on-demand) still sees all intents. ParseAndAddSuggestions

still validates against the full intent list for execution.

Bumps desktop to v1.41.9.

The 1B model was inventing intent IDs like 'call' instead of using

tasks.create_task. Added a final IMPORTANT reminder listing all valid

intent_id values and 'Do NOT invent new IDs' to anchor the model to

the available actions. Bumps desktop to v1.41.8.

Example 4 was teaching the model that 'call the dentist to book

appointment' is a calendar event, but it's actually a task (an action

to perform). Rewrote examples to explicitly distinguish: confirmed

meetings at specific times = calendar.create_event, things the user

needs to DO (call, send, buy, book) = tasks.create_task. Added

explicit guidance at the top of the prompt for this distinction.

Bumps desktop to v1.41.7.

The 1B model was listing irrelevant intents (create_note from a note,

create_contact from appointment text) without extracting slots. Key

changes: (1) explicit instruction "most text has 0 or 1 actions, be

selective", (2) require filled slots, (3) added Example 4 showing a

mixed sentence where only one part is actionable — teaches the model to

be selective. Removed entity title/type from user prompt to avoid

confusing the model with source metadata. Bumps desktop to v1.41.6.