indifferentketchup
b18de2a331
feat(booterm): structured pty_exited WS notifications. Plan-validated, impl-validated, code-reviewed green (contracts build clean, contracts test 29/29, booterm + web typecheck clean). wip: in-progress inference/provider refactor (agents.ts, provider.ts, new llama-providers.ts, removed llama-args-validator), plus arena, dispatcher, compaction, schema changes. openspec: pty-exit-notifications complete; x-agent-flags planned (not yet implemented).
58 lines
2.4 KiB
YAML
58 lines
2.4 KiB
YAML
id: utility-calls
|
|
name: Utility Calls
|
|
kind: chat
|
|
version: 1
|
|
description: Titles, summaries, compaction -- directly tunes the FAST_MODEL choice.
|
|
judge_model: null
|
|
tasks:
|
|
- id: auto-title
|
|
prompt: "Generate a concise title (max 5 words) for this chat session. The conversation is about: A user asking how to fix a PostgreSQL connection pool exhaustion error in their Express.js application."
|
|
rubric:
|
|
criteria:
|
|
- criterion: relevance
|
|
description: "Title relates to PostgreSQL connection pool issue"
|
|
weight: 2
|
|
- criterion: conciseness
|
|
description: "5 words or fewer"
|
|
weight: 2
|
|
- criterion: clarity
|
|
description: "Title is specific, not generic"
|
|
weight: 1
|
|
max_score: 5
|
|
- id: chat-summary
|
|
prompt: "Summarize this conversation in 2-3 sentences: User asked about Docker networking. Assistant explained bridge vs host mode. User asked about port mapping. Assistant showed docker run -p syntax. User confirmed it works."
|
|
rubric:
|
|
criteria:
|
|
- criterion: accuracy
|
|
description: "Summary captures all key topics discussed"
|
|
weight: 2
|
|
- criterion: length
|
|
description: "2-3 sentences as requested"
|
|
weight: 1
|
|
- criterion: readability
|
|
description: "Flows naturally, not a list of facts"
|
|
weight: 1
|
|
max_score: 4
|
|
- id: context-compaction
|
|
prompt: "Compress this conversation history into a single paragraph that preserves the essential context for continuing the discussion."
|
|
rubric:
|
|
criteria:
|
|
- criterion: preservation
|
|
description: "Retains key technical concepts: retry, backoff, circuit breaker"
|
|
weight: 2
|
|
- criterion: brevity
|
|
description: "Single paragraph, significantly shorter than original"
|
|
weight: 2
|
|
- criterion: usability
|
|
description: "Useful context for continuing the conversation"
|
|
weight: 1
|
|
max_score: 5
|
|
- id: label-generation
|
|
prompt: "Classify this user message into one of these labels: [question, bug-report, feature-request, small-talk, code-review]. Message: 'The app crashes when I click the submit button on the settings page. I'm using Chrome 120 on macOS.'"
|
|
rubric:
|
|
criteria:
|
|
- criterion: accuracy
|
|
description: "Classifies as 'bug-report'"
|
|
weight: 3
|
|
max_score: 3
|