[PierrotAWB]

Issue for this PR

Issues are disabled on this fork; motivation below. Stacked on #23 (extends the same turn.done line); re-target to dev after #23 merges.

Type of change

• New feature

What does this PR do?

prep_ms (#23) says how much time the harness spends before the provider request; this says where it goes. Four additive fields on turn.done, accumulated across the turn's steps with plain Date.now() pairs:

• history_ms — loading session history from SQLite (filterCompactedEffect, runs every step)
• tools_ms — SessionTools.resolve
• context_ms — the system-prompt/instructions/model-message Effect.all
• snapshot_ms — the pre-stream git snapshot.track() in the processor (exposed via a snapshotMs handle getter, mirroring firstTokenAt)

These four are the optimization targets of the per-step-prep workstream; this instrumentation lands first so each later change has a fleet-wide before/after, and so the p90 tail can be attributed before anyone chases it.

How did you verify your code works?

Extended the #23 turn.done test: all four fields present and ≥ 0 on a scripted two-step turn. bun run typecheck clean, bun run lint 0 errors, prompt.test.ts + compaction.test.ts 112/112.

Checklist

• I have tested my changes locally
• I have not included unrelated changes in this PR

🤖 Generated with Claude Code

---

Summary by cubic

Breaks down turn preparation time into four phases and logs them on turn.done. Previously we only emitted prep_ms; now we also emit history_ms, tools_ms, context_ms, and snapshot_ms to attribute pre-request latency.

• Instruments history loading, tools resolution, context construction, and pre-stream snapshot capture; accumulates per step and emits on turn.done.
• Adds snapshotMs to Handle/ProcessorContext and measures pre-stream snapshot.track() in the processor; exposes via handle.snapshotMs.
• Updates tests to assert the four new fields and adapts fakes to include snapshotMs.

Migration

• Add snapshotMs to any custom Handle implementations or test fakes.

^{Written for commit 6cb104c. Summary will update on new commits.}

[github-actions]

The following comment was made by an LLM, it may be inaccurate:

[cubic-dev-ai]

No issues found across 4 files

_{Re-trigger cubic}

[PierrotAWB]

Consolidated into #29 (one commit per concern there; review history for the prep_ms retry semantics is on this PR's threads).