-
Notifications
You must be signed in to change notification settings - Fork 3.4k
v0.9.0: complete versioned exec stream receipts and tool lifecycle metadata #4356
Copy link
Copy link
Closed
Labels
agent-readyBody is self-sufficient per docs/AGENT_RUNNER.md; a remote agent may claim itBody is self-sufficient per docs/AGENT_RUNNER.md; a remote agent may claim itbugSomething isn't workingSomething isn't workingenhancementNew feature or requestNew feature or requestreliabilityReliability, flaky behavior, retries, fallbacks, and robustnessReliability, flaky behavior, retries, fallbacks, and robustnesssubagentsSub-agent orchestration, lifecycle, and completion handlingSub-agent orchestration, lifecycle, and completion handlingtoolsTool execution, tool schemas, tool UX, and built-in tool behaviorTool execution, tool schemas, tool UX, and built-in tool behaviortuiTerminal UI behavior, rendering, or interactionTerminal UI behavior, rendering, or interactionv0.9.0Targeting v0.9.0Targeting v0.9.0workflow-runtimeWorkflow IR, executor, control flow, and replay runtimeWorkflow IR, executor, control flow, and replay runtime
Milestone
Description
Metadata
Metadata
Assignees
Labels
agent-readyBody is self-sufficient per docs/AGENT_RUNNER.md; a remote agent may claim itBody is self-sufficient per docs/AGENT_RUNNER.md; a remote agent may claim itbugSomething isn't workingSomething isn't workingenhancementNew feature or requestNew feature or requestreliabilityReliability, flaky behavior, retries, fallbacks, and robustnessReliability, flaky behavior, retries, fallbacks, and robustnesssubagentsSub-agent orchestration, lifecycle, and completion handlingSub-agent orchestration, lifecycle, and completion handlingtoolsTool execution, tool schemas, tool UX, and built-in tool behaviorTool execution, tool schemas, tool UX, and built-in tool behaviortuiTerminal UI behavior, rendering, or interactionTerminal UI behavior, rendering, or interactionv0.9.0Targeting v0.9.0Targeting v0.9.0workflow-runtimeWorkflow IR, executor, control flow, and replay runtimeWorkflow IR, executor, control flow, and replay runtime
Projects
StatusShow more project fields
Done
Problem
Exec-stream JSON now has the foundation for typed terminal outcomes, but the terminal receipt and tool lifecycle are not yet complete enough for replay, support, or cost attribution. Consumers need an additive, versioned contract rather than inferring execution facts from prose.
Evidence
The current release lane distinguishes success, cancellation, model error, tool error, and infrastructure error. It still lacks a complete terminal receipt covering routing, timing, retries, usage/cost inputs, sandbox posture, and artifact/config identity. Tool lifecycle records also need uniform timing, side-effect, error, and truncation metadata.
Expected behavior
Likely files
crates/tui/src/main.rscrates/tui/src/core/events.rscrates/tui/src/core/error_taxonomy.rscrates/tui/src/tools/truncate.rsAcceptance criteria
Related