…ersion (#15191)

* 💄 style(QueueTray): use borderless variant for queued file preview

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ✨ feat(llm-generation-tracing): tag task-handoff scenario + prompt version

Task topic handoff was tracing as scenario=unknown / promptVersion=v0 because the
generateObject call only set metadata.trigger and that trigger isn't in the
registry. Add a TaskHandoff scenario const, version the prompt next to its
definition, and pass tracing options explicitly at the call site (mirroring
followUpAction).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

…k router (#15146)

* ✨ feat(llm-generation-tracing): pre-allocate tracingId + recordFeedback router

Wire up the per-call feedback loop foundation.

1. **Pre-allocate tracingId (plan A2)**
   - `TracingOptions.tracingId?: string` — optional caller-supplied UUID.
   - `LLMGenerationTracingService.record` generates one via `randomUUID()`
     when the caller doesn't supply one, so the id is always known
     before DB insert.
   - `LlmGenerationTracingModel.record` accepts an optional `id` and
     forwards it to the insert (Drizzle still autogens when omitted).
   - `aiChat.outputJSON` allocates the id up-front, threads it through
     `tracing.tracingId`, and returns `{ data, tracingId }` so the
     client can wire feedback against the id even though
     `service.record` runs inside Next's `after()`.
   - `aiChatService.generateJSON` consumers (InputEditor, supervisor)
     unwrap the envelope.

2. **New `llmGenerationTracingRouter.recordFeedback`**
   - Scenario-agnostic feedback endpoint at `lambda.llmGenerationTracing`.
   - Validates `{ tracingId (uuid), signal (positive|negative|neutral),
     source, score?, data? }` and forwards to
     `LLMGenerationTracingService.recordFeedback`.

Follow-up issues already filed:
- LOBE-9488 — `@lobehub/editor` AutoCompletePlugin needs
  `onAccept`/`onReject`/`onCancel` callbacks before the client side can
  capture Tab/Esc/keep-typing signals against the returned tracingId.
- LOBE-9489 — session-level signal modeling (multi-suggestion typing
  sessions) — deferred until per-row feedback data lands.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* 🐛 fix(llm-generation-tracing): surface feedback write failures instead of silent ok

The recordFeedback mutation used to always return `{ ok: true }` even when
the underlying write was silently dropped — `LLMGenerationTracingService`
swallowed both DB-init/update throws and the no-op case where the WHERE
clause (id + userId) matched zero rows. Callers couldn't tell
"persisted" from "lost", which would skew tracing-feedback metrics and
prevent reasoned retry/error handling.

Fix:

- `LlmGenerationTracingModel.updateFeedback` now returns
  `{ updated: boolean }` (via `.returning({ id })`), so the caller knows
  whether the WHERE clause actually matched a row.
- `LLMGenerationTracingService.recordFeedback` throws a typed
  `LLMGenerationFeedbackError` with `kind: 'not_found' | 'db_failure'`
  instead of swallowing — stops logging-only behaviour for DB errors and
  promotes the 0-rows case to an explicit signal.
- `llmGenerationTracingRouter.recordFeedback` catches that error and
  translates to `TRPCError({ code: 'NOT_FOUND' })` for stale-id and
  `INTERNAL_SERVER_ERROR` for DB outages — `{ ok: true }` only flows
  back when a row was actually patched.

Tests:
- Model: assert `{ updated: true/false }` for happy / cross-user / missing-id
- Service: assert throws on both not_found scenarios
- Router: assert TRPCError code translation for both error kinds

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* ✨ feat(input-completion): wire Tab/Esc/typing feedback to recordFeedback

- bump @lobehub/editor to ^4.12.0 for AutoComplete onSuggestion{Accepted,Rejected}
- add llmGenerationTracingService wrapping lambda.llmGenerationTracing.recordFeedback
- InputEditor: map suggestionId→tracingId, fire positive on accept, negative on
  esc, neutral on typing/cursor-move/blur/other; recode IME-driven escape as
  neutral/autocomplete_ime so CJK input doesn't poison the signal

Closes LOBE-9488

* ♻️ refactor(input-completion): fold recordTracingFeedback into aiChatService

Single trpc mutation didn't warrant a dedicated service file; aiChatService
already owns the paired `outputJSON` call that mints the tracingId, so
recordTracingFeedback belongs alongside it.

* 💄 style(llm-generation-tracing): tag task-handoff scenario + prompt version (#15191)

* 💄 style(QueueTray): use borderless variant for queued file preview

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ✨ feat(llm-generation-tracing): tag task-handoff scenario + prompt version

Task topic handoff was tracing as scenario=unknown / promptVersion=v0 because the
generateObject call only set metadata.trigger and that trigger isn't in the
registry. Add a TaskHandoff scenario const, version the prompt next to its
definition, and pass tracing options explicitly at the call site (mirroring
followUpAction).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(llm-generation-tracing): validate caller-supplied tracingId as UUID

The `outputJSON` route echoed `tracing.tracingId` back to clients without
checking the shape. Because the surrounding `tracing` record is free-form,
a malformed value passed request validation, then failed DB insertion on
the uuid PK and was later rejected by `recordFeedback` (`z.string().uuid()`),
so callers could receive a tracingId unusable for the feedback flow.

Tighten `StructureOutputSchema.tracing` to a `z.object({ tracingId: uuid }).catchall(unknown)`
so the validation happens at the request boundary; the route can then drop
the redundant `typeof === 'string'` guard.

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…k router (lobehub#15146)

* ✨ feat(llm-generation-tracing): pre-allocate tracingId + recordFeedback router

Wire up the per-call feedback loop foundation.

1. **Pre-allocate tracingId (plan A2)**
   - `TracingOptions.tracingId?: string` — optional caller-supplied UUID.
   - `LLMGenerationTracingService.record` generates one via `randomUUID()`
     when the caller doesn't supply one, so the id is always known
     before DB insert.
   - `LlmGenerationTracingModel.record` accepts an optional `id` and
     forwards it to the insert (Drizzle still autogens when omitted).
   - `aiChat.outputJSON` allocates the id up-front, threads it through
     `tracing.tracingId`, and returns `{ data, tracingId }` so the
     client can wire feedback against the id even though
     `service.record` runs inside Next's `after()`.
   - `aiChatService.generateJSON` consumers (InputEditor, supervisor)
     unwrap the envelope.

2. **New `llmGenerationTracingRouter.recordFeedback`**
   - Scenario-agnostic feedback endpoint at `lambda.llmGenerationTracing`.
   - Validates `{ tracingId (uuid), signal (positive|negative|neutral),
     source, score?, data? }` and forwards to
     `LLMGenerationTracingService.recordFeedback`.

Follow-up issues already filed:
- LOBE-9488 — `@lobehub/editor` AutoCompletePlugin needs
  `onAccept`/`onReject`/`onCancel` callbacks before the client side can
  capture Tab/Esc/keep-typing signals against the returned tracingId.
- LOBE-9489 — session-level signal modeling (multi-suggestion typing
  sessions) — deferred until per-row feedback data lands.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* 🐛 fix(llm-generation-tracing): surface feedback write failures instead of silent ok

The recordFeedback mutation used to always return `{ ok: true }` even when
the underlying write was silently dropped — `LLMGenerationTracingService`
swallowed both DB-init/update throws and the no-op case where the WHERE
clause (id + userId) matched zero rows. Callers couldn't tell
"persisted" from "lost", which would skew tracing-feedback metrics and
prevent reasoned retry/error handling.

Fix:

- `LlmGenerationTracingModel.updateFeedback` now returns
  `{ updated: boolean }` (via `.returning({ id })`), so the caller knows
  whether the WHERE clause actually matched a row.
- `LLMGenerationTracingService.recordFeedback` throws a typed
  `LLMGenerationFeedbackError` with `kind: 'not_found' | 'db_failure'`
  instead of swallowing — stops logging-only behaviour for DB errors and
  promotes the 0-rows case to an explicit signal.
- `llmGenerationTracingRouter.recordFeedback` catches that error and
  translates to `TRPCError({ code: 'NOT_FOUND' })` for stale-id and
  `INTERNAL_SERVER_ERROR` for DB outages — `{ ok: true }` only flows
  back when a row was actually patched.

Tests:
- Model: assert `{ updated: true/false }` for happy / cross-user / missing-id
- Service: assert throws on both not_found scenarios
- Router: assert TRPCError code translation for both error kinds

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* ✨ feat(input-completion): wire Tab/Esc/typing feedback to recordFeedback

- bump @lobehub/editor to ^4.12.0 for AutoComplete onSuggestion{Accepted,Rejected}
- add llmGenerationTracingService wrapping lambda.llmGenerationTracing.recordFeedback
- InputEditor: map suggestionId→tracingId, fire positive on accept, negative on
  esc, neutral on typing/cursor-move/blur/other; recode IME-driven escape as
  neutral/autocomplete_ime so CJK input doesn't poison the signal

Closes LOBE-9488

* ♻️ refactor(input-completion): fold recordTracingFeedback into aiChatService

Single trpc mutation didn't warrant a dedicated service file; aiChatService
already owns the paired `outputJSON` call that mints the tracingId, so
recordTracingFeedback belongs alongside it.

* 💄 style(llm-generation-tracing): tag task-handoff scenario + prompt version (lobehub#15191)

* 💄 style(QueueTray): use borderless variant for queued file preview

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ✨ feat(llm-generation-tracing): tag task-handoff scenario + prompt version

Task topic handoff was tracing as scenario=unknown / promptVersion=v0 because the
generateObject call only set metadata.trigger and that trigger isn't in the
registry. Add a TaskHandoff scenario const, version the prompt next to its
definition, and pass tracing options explicitly at the call site (mirroring
followUpAction).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(llm-generation-tracing): validate caller-supplied tracingId as UUID

The `outputJSON` route echoed `tracing.tracingId` back to clients without
checking the shape. Because the surrounding `tracing` record is free-form,
a malformed value passed request validation, then failed DB insertion on
the uuid PK and was later rejected by `recordFeedback` (`z.string().uuid()`),
so callers could receive a tracingId unusable for the feedback flow.

Tighten `StructureOutputSchema.tracing` to a `z.object({ tracingId: uuid }).catchall(unknown)`
so the validation happens at the request boundary; the route can then drop
the redundant `typeof === 'string'` guard.

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>