refactor: single owners for knowledge/experience prompt blocks (plan 019)

[DavertMik]

Plan 019 — One owner for knowledge/experience prompt blocks

The "render relevant knowledge" and "render experience TOC" prompt blocks were re-implemented in 5 places with two different tag names (<knowledge> in the base class vs <hint> in Navigator/Researcher). This moves each to its owning tracker (per the CLAUDE.md Code Ownership Map):

• KnowledgeTracker.renderRelevantKnowledge(state)
• ExperienceTracker.renderExperienceTocFor(state)

Consumers now delegate:

• TaskAgent.getKnowledge / getExperience → one-line delegations (kept for subclasses).
• Navigator.resolveState + Navigator.verifyState knowledge/TOC blocks.
• Researcher.buildResearchPrompt — also switches the knowledge source from the StateManager copy to explorer.getKnowledgeTracker() (already ${env.*}-interpolated via plan 010).
• Pilot.getExperienceToc.

Tag unified on <knowledge> (Navigator/Researcher previously emitted <hint>). No prompt wording changed beyond the tag.

Drift reconciliation

This plan was written at 9e22b0d. Since then:

• Step 2 (shared tracker instances) is already done in main — Navigator uses explorer.getKnowledgeTracker() / getStateManager().getExperienceTracker(), Captain uses explorBot.experienceTracker(). No new KnowledgeTracker()/new ExperienceTracker() remain in these files.
• Step 3 (historian per-call new KnowledgeTracker()) — already gone from historian/.

Deferred

• Step 4 (deletion-scope + stop-meta dedup) — deferred; touches tester/pilot/test-plan and is a separable concern.
• Step 5 (Navigator.visitOnce → Explorer.visit) — DEFERRED: behavioral (AI navigation would start honoring knowledge wait/waitForElement hints); wants its own review, as the plan's checkbox allows.

Verification

• bun test tests/unit → 768 pass / 0 fail (+4 renderer tests).
• bun test tests/integration/ → 63 pass / 0 fail.
• bun run lint → clean; tsc in touched files neutral vs main (21).
• grep -rn "<hint>" src/ai/ → 0.
• Tracker mocks in tester/researcher tests updated to expose the new render methods (documented test change — no <hint> assertions existed).

🤖 Generated with Claude Code

[github-actions]

Explorbot Self-Regression

Commit fb63ca8 · run

Scenario	Result	Attempts	Duration
basic (native)	PASS	1/3	7m
experience: control	OK — failed as expected	1/1	2m
experience: seeded	PASS	1/3	1m

Attempt details

• basic (native) attempt 1 — PASS: login evidence: PASS (post-login plan=true, post-login research=true); research: PASS (files=6, wellFormed=true, keywords=7/3); scenarios: PASS (tests=5/5, features=4/3); tests passed: PASS (5 passed, 0 failed (reporter: 5 passed, 0 failed))
• experience: control attempt 1 — PASS: control: OK — failed as expected (0 passed, 1 failed)
• experience: seeded attempt 1 — PASS: seeded: PASS (1 passed, 0 failed)

---

Session analysis — basic (native):

Session Analysis

The Issues list page core functionality was validated: creating new issues, filtering by search/label/status, and opening issue details all work correctly. One test had a transient automation issue with modal field interaction but recovered successfully.

Coverage

• Pages: /issues, /issues?new=1, /issues?q=API&status=, /issues?q=&status=closed, /issues?label=2, /issues/5
• Features: Issue creation, search filtering, status filtering, label filtering, detail view navigation

What works

• Issue creation — ET-1 Create a new issue via toolbar button and verify it appears in the list
• Search filtering — ET-2 Filter issues by search term and verify results are narrowed
• Status filtering — ET-3 Filter issues by status using the status combobox
• Label filtering — ET-4 Filter issues by label using the label dropdown
• Issue detail navigation — ET-5 Open issue detail view by clicking an issue title in the table

Execution Issues

• ET-1 Create a new issue via toolbar button and verify it appears in the list — initial fillField failed on modal, recovered on second attempt and completed successfully

[DenysKuchma]

Merge only after 92 and before 91

[DavertMik]

@DenysKuchma please merge