Reports client information and capabilities advertised to this MCP server.

Reads Handy's local history database without modifying it and imports new raw transcripts into the prompt lab.

Returns a bounded batch of raw transcripts. Generate a conservative corrected transcript for every record, then call save_correction_proposals.

Stores Codex-generated proposals for later user review. Proposals do not enter the evaluation set until the user approves them.

Opens a widget for editing and approving a batch of Codex transcript proposals.

Returns counts for imported, proposed, approved, edited, and skipped transcripts.

Loads a record from the current annotation widget batch.

Saves a user-reviewed transcript target, then returns the next record in the widget batch.

Creates a chronological development/holdout split and locks annotation access. Call only from a fresh Codex task that has not seen transcript proposals.

Returns approved raw/target pairs from the development split. Holdout records are never returned.

Lists downloaded local models and loaded instances from LM Studio. It does not download or change models.

Stores an immutable Handy-compatible prompt template, model, and inference settings for evaluation. The prompt must contain ${output}.

Sequentially evaluates a candidate against development examples, recording exact-match and latency metrics. LM Studio's prior model state is restored afterward.

Returns detailed failed examples for a development evaluation. Holdout evaluation details are never exposed.

Freezes a candidate before sealed holdout evaluation.

Evaluates a frozen candidate on the sealed holdout. Returns aggregate metrics only.

Shows the exact LM Studio per-model defaults file and fields that would be changed for a candidate. Makes no changes.

After form confirmation, backs up and updates LM Studio's per-model defaults for a frozen candidate that completed holdout evaluation. Handy remains read-only.

Unlocks annotation access for newly collected Handy transcripts after explicit confirmation. Use from a fresh annotation task.