FE-823: Elicitation backlog substrate and agenda read-back#178
Open
lunelson wants to merge 18 commits into
Open
FE-823: Elicitation backlog substrate and agenda read-back#178lunelson wants to merge 18 commits into
lunelson wants to merge 18 commits into
Conversation
Induces a fault-type lens from PR review-bot comments (or supplied observations), gates token-vs-symptom via a three-part promotion test, audits both family and ownership axes, and proposes graduating recurring lenses into ln-review's contract catalog. Wire into ln-consult routing and the ln-skills praxis reference; back-reference from ln-review. Amp-Thread-ID: https://ampcode.com/threads/T-019ea618-c2ac-721d-809a-a72bfd9ce453 Co-authored-by: Amp <amp@ampcode.com>
Anchor every prompt-resource family to an authoritative source (goals/methods have no README; goals->D59-L, methods->D58-L, strategies/lenses->README+SPEC), add a per-family facet checklist, make verification self-checkable via a required structural test, and add concurrency guardrails scoping edits to .pi/skills/**/*.md. Amp-Thread-ID: https://ampcode.com/threads/T-019ea2fc-9f12-767d-bd7a-08497f7307fd Co-authored-by: Amp <amp@ampcode.com>
Amp-Thread-ID: https://ampcode.com/threads/T-019ea2ec-7506-74ed-a4e0-99b8d800442f Co-authored-by: Amp <amp@ampcode.com>
This was referenced Jun 8, 2026
Contributor
Author
…authority-shell Prepares three mutually write-disjoint streams to launch from a clean base: - graph-observed-shapes--coverage-ledger: ratify the consumer-specific read-shape inventory (tool=6, RPC/web=2 is intentional) + coverage-guard test - minimal-authority-shell--audit-and-guard: pre-audit found most criteria already met (discriminants exist, needs_human unused, elicit blocks bash/edit/write, D34-L command policy present), so an audit + guard slice Records the parallel-stream plan and the src/.pi/agents/state.ts single-writer invariant in PLAN.md, plus Current execution pointers on both frontiers. Amp-Thread-ID: https://ampcode.com/threads/T-019ea2fc-9f12-767d-bd7a-08497f7307fd Co-authored-by: Amp <amp@ampcode.com>
Stream A (resource-body-depth) landed in 1ca02e3. Mark both Seam 3a/3b content-depth rows built in CROSS_CUT_PLAN.md, record the completion in PLAN.md (Recently Completed + parallel-stream note: A done, B and C remain), and delete the now-exhausted scope card. All cross-cut row-sized work is complete; only the unscoped live 'what to ask next' driver remains. Amp-Thread-ID: https://ampcode.com/threads/T-019ea2fc-9f12-767d-bd7a-08497f7307fd Co-authored-by: Amp <amp@ampcode.com>
Add 'rename blast-radius includes the data plane' cue to ln-review Contract integrity (and mirror into ln-judo-review): a reviewer-bot comment on renamed data samples one token of a wider syndrome; regenerate committed artifacts wholesale rather than field-patching, and check legacy-input policy against posture. Add memory/REFACTOR.md scoping the PR 177 (FE-811) reconciliation: regenerate two stale reference runs, add a residue guard, fix the edge-direction label. Output of an ln-induct run on PR 177 comments. Amp-Thread-ID: https://ampcode.com/threads/T-019ea618-c2ac-721d-809a-a72bfd9ce453 Co-authored-by: Amp <amp@ampcode.com>
Resolve the competing-thesis framing into engine (induction) + governor (triage gate). Name canonical clusters: ladder of abstraction (step 2), Parnas/blast radius (ownership axis). Merge the posture-check insight into the find/fix principle (a true diagnosis can carry a wrong prescription). Fold the gitignored-data-plane search craft into one clause. Keep 'defects cluster' as a convergent phrase without attribution (the principle's density is convergent, not Beizer-rooted). Gate, stopping rule, output template, routing, and reconciliation tail unchanged. Amp-Thread-ID: https://ampcode.com/threads/T-019ea618-c2ac-721d-809a-a72bfd9ce453 Co-authored-by: Amp <amp@ampcode.com>
Both graph-observed-shapes (85e73ba) and minimal-authority-shell (68474e3) landed in parallel; each reconciled its own slice but could not see the other's completion. Fix the residual drift: mark graph-observed-shapes done in the dependency node, update the context paragraph and parallel-stream note to reflect all three streams landed with no collisions, and delete the exhausted graph-observed-shapes card (B left it as a done tombstone; ln-scope deletes exhausted cards, matching C's cleanup). Amp-Thread-ID: https://ampcode.com/threads/T-019ea2fc-9f12-767d-bd7a-08497f7307fd Co-authored-by: Amp <amp@ampcode.com>
Correct the premature 'cross-cut exhausted' claim: the Seam 3a 'what to ask next' driver row is still partial, so the seam stays open. Dispose it as the promoted elicitation-driver frontier (buildable now). De-fog the remaining coverage frontiers rather than parking them: - runtime-affordances-and-legality reclassified buildable-now; scoped as a coverage ledger card with only review-set/turn-mode rows tripwired. - exchanges-and-generalized-capture is evidence-gated; named forcing function is a capture-quality fitness spike card (A22-L). Amp-Thread-ID: https://ampcode.com/threads/T-019ea2fc-9f12-767d-bd7a-08497f7307fd Co-authored-by: Amp <amp@ampcode.com>
- runtime-affordances card: widen the core derivation to affordances(resolvedState, readinessGrade); legality is not derivable from ResolvedBrunchAgentState alone (grade is a separate input per BrunchPostureToolPolicyInput / isGradeLegal). - Reorder Next: elicitation-driver precedes runtime-affordances so the last open cross-cut row closes before any fresh coverage frontier; runtime-affordances is parallel-eligible but must not preempt it. - Clarify the generalized-capture cross-cut row: 'built' = POC bar only; richer capture is owned by exchanges-and-generalized-capture, gated on capture-quality-spike, not unfinished in this row. Amp-Thread-ID: https://ampcode.com/threads/T-019ea2fc-9f12-767d-bd7a-08497f7307fd Co-authored-by: Amp <amp@ampcode.com>
Amp-Thread-ID: https://ampcode.com/threads/T-019ea2ec-7506-74ed-a4e0-99b8d800442f Co-authored-by: Amp <amp@ampcode.com>
…strate-and-agenda-read-back # Conflicts: # memory/PLAN.md
Reconcile runtime-affordances-and-legality to done (0010510), add its Recently Completed entry, archive the 06-05/06-06 completion bursts to PLAN_HISTORY, update the cross-cut capture-quality note, and add D40-L to the session topology README header for the new affordance ledger. Amp-Thread-ID: https://ampcode.com/threads/T-019ea6aa-0ce3-766e-8458-36e6a4450587 Co-authored-by: Amp <amp@ampcode.com>
lunelson
changed the title
PR SummaryMedium Risk Overview Product/runtime: Shared Process/docs: Adds Reviewed by Cursor Bugbot for commit 1447843. Bugbot is set up for automated code reviews on this repo. Configure here. |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 2 potential issues.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 1447843. Configure here.
| recommendation: 'keep_parked', | ||
| summary: | ||
| 'Do not graduate generalized capture until the extraction prompt/model can keep undecided implications out of high-confidence graph truth.', | ||
| }; |
There was a problem hiding this comment.
False-commit verdict mislabels confidence
Medium Severity
When falseCommitCount is positive, verdictFor reports a negative shift about committing a low-confidence implication, but falseCommitCount only counts high-confidence extractions that would wrongly enter graph truth. The gate still recommends keep_parked, yet the stated failure mode can misread probe output during graduation decisions.
Reviewed by Cursor Bugbot for commit 1447843. Configure here.
| "runId": "2026-06-08-capture-quality-sample", | ||
| "generatedAt": "2026-06-08T09:44:38.831Z", | ||
| "cwd": "/Users/lunelson/Code/hashintel/brunch-next-chi", | ||
| "extractorName": "sample-llm-output", |
There was a problem hiding this comment.
Committed probe report leaks cwd
Low Severity
The checked-in capture-quality sample report.json records a developer-machine absolute cwd, while the new probe writer normalizes ephemeral temp workspaces via portableCwd for committed artifacts. The sample run was persisted before that contract, so reference data carries a non-portable path the project treats as rename/residue drift.
Reviewed by Cursor Bugbot for commit 1447843. Configure here.
There was a problem hiding this comment.
Pull request overview
This PR materializes the FE-823 elicitation backlog substrate (a spec-scoped prospective register) and, in the same branch, lands several coverage/frontier hardening slices (graph observed-shape ledger + drift guards, runtime affordance legality derivation + ledger, and a deterministic capture-quality probe), plus planning/doc sync updates.
Changes:
- Adds a new
elicitation_backlogSQLite table + Drizzle migration, seeds grounding questions atcreateSpec, and routes create/close operations throughCommandExecutorwith spec-local{specId, lsn}+change_log. - Establishes “closed ledgers + drift guards” for graph observed read shapes and runtime affordances, and introduces a deterministic capture-quality measurement loop with fixture artifacts.
- Updates prompt-resource markdown bodies and planning/skill protocol docs to reflect new coverage-frontier guidance and the new
ln-inductskill.
Reviewed changes
Copilot reviewed 63 out of 63 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| src/web/README.md | Documents web client constraints and current graph read subset; updates target topology sketch. |
| src/session/runtime-affordances-coverage.test.ts | Adds a runtime-affordances coverage ledger + drift guard test. |
| src/session/README.md | Documents runtime affordance ledger and ownership/deferred rationale. |
| src/rpc/README.md | Documents deliberate graph RPC read subset and observed-shape ownership. |
| src/projections/session/runtime-policy.ts | Centralizes readiness-grade legality tables + axis option/default helpers. |
| src/projections/session/affordances.ts | Adds pure affordance derivation over resolved runtime state + readiness grade. |
| src/projections/session/affordances.test.ts | Tests affordance legality/default behavior and AUTO exclusions. |
| src/probes/capture-quality-loop.ts | Adds capture-quality probe runner, summarizer, artifact writer, CLI entry. |
| src/probes/capture-quality-loop.test.ts | Tests capture-quality summarization and artifact writing. |
| src/graph/schema/elicitation-backlog.ts | Adds domain types for elicitation backlog entries. |
| src/graph/README.md | Documents elicitation backlog ownership and observed read-shape ledger + guard. |
| src/graph/queries.ts | Adds getOpenElicitationBacklogEntries query + row mapping. |
| src/graph/queries.test.ts | Tests open elicitation backlog read-back and spec scoping. |
| src/graph/observed-shapes-coverage.test.ts | Adds drift guard tying tool/RPC/web surfaces to the observed-shape ledger. |
| src/graph/index.ts | Re-exports elicitation backlog types and query function. |
| src/graph/command-executor.ts | Seeds backlog at spec creation; adds create/close backlog entry commands. |
| src/graph/command-executor.test.ts | Tests backlog seeding, create/close commands, and invariants. |
| src/db/schema.ts | Adds enum arrays and elicitation_backlog table definition. |
| src/db/row-schemas.ts | Adds drizzle-typebox row schemas for elicitation_backlog. |
| src/db/README.md | Documents elicitation_backlog as graph-adjacent, spec-scoped substrate. |
| src/.pi/skills/strategies/step-wise-disambiguate.md | Deepens strategy guidance content. |
| src/.pi/skills/strategies/step-wise-decision-tree.md | Deepens strategy guidance content. |
| src/.pi/skills/strategies/propose-graph.md | Deepens strategy guidance content. |
| src/.pi/skills/strategies/project-graph.md | Deepens strategy guidance content. |
| src/.pi/skills/strategies/freestyle.md | Deepens strategy guidance content and constraints. |
| src/.pi/skills/methods/review-for-gaps.md | Deepens method guidance content. |
| src/.pi/skills/methods/read-context.md | Deepens method guidance content. |
| src/.pi/skills/methods/commit-graph.md | Deepens method guidance content. |
| src/.pi/skills/lenses/oracle.md | Deepens lens guidance content. |
| src/.pi/skills/lenses/intent.md | Deepens lens guidance content. |
| src/.pi/skills/lenses/design.md | Deepens lens guidance content. |
| src/.pi/skills/goals/grounding-advance.md | Deepens goal guidance content. |
| src/.pi/skills/goals/elicit-expand.md | Deepens goal guidance content. |
| src/.pi/skills/goals/commit-converge.md | Deepens goal guidance content. |
| src/.pi/skills/goals/capture-posture.md | Deepens goal guidance content. |
| src/.pi/extensions/runtime/authority-matrix.test.ts | Adds minimal authority-matrix guard test for tool blocking + result discriminants. |
| src/.pi/agents/state.ts | Refactors to reuse shared legality tables from runtime-policy. |
| src/.pi/agents/compose.test.ts | Adds manifest-wide prompt-resource depth/readability test. |
| memory/SPEC.md | Updates assumptions/decisions/invariants to reflect landed work. |
| memory/REFACTOR.md | Adds refactor note derived from ln-induct output (data-plane rename residue). |
| memory/PLAN.md | Syncs plan to reflect completed frontiers and promoted follow-ons. |
| memory/CROSS_CUT_PLAN.md | Syncs cross-cut ledger status and promotions. |
| memory/cards/elicitation-backlog--substrate.md | Deletes retired execution card. |
| memory/cards/crosscut-know--resource-body-depth.md | Deletes retired execution card. |
| drizzle/meta/0003_snapshot.json | Adds drizzle snapshot metadata for the new migration. |
| drizzle/meta/_journal.json | Records new migration in drizzle journal. |
| drizzle/0003_outstanding_black_bird.sql | Adds migration creating elicitation_backlog table. |
| docs/praxis/ln-skills.md | Documents coverage-frontier protocol maturity + adds ln-induct. |
| docs/archive/PLAN_HISTORY.md | Archives older plan history during sync. |
| .fixtures/runs/capture-quality/sample-llm-extractions.json | Adds sample extraction fixture for capture-quality probe. |
| .fixtures/runs/capture-quality/2026-06-08-capture-quality-sample/verdict.md | Adds sample run verdict artifact. |
| .fixtures/runs/capture-quality/2026-06-08-capture-quality-sample/scenarios.json | Adds sample run scenarios artifact. |
| .fixtures/runs/capture-quality/2026-06-08-capture-quality-sample/report.json | Adds sample run report artifact. |
| .fixtures/runs/capture-quality/2026-06-08-capture-quality-sample/extractions.json | Adds sample run extractions artifact. |
| .agents/skills/ln-sync/SKILL.md | Expands ln-sync checks for coverage protocol drift. |
| .agents/skills/ln-scope/SKILL.md | Adds coverage preflight guidance and explicit owner/oracle requirements. |
| .agents/skills/ln-review/SKILL.md | Adds contract-integrity lens about data-plane rename residue. |
| .agents/skills/ln-plan/SKILL.md | Adds coverage reference + sequencing precedence rule. |
| .agents/skills/ln-plan/references/coverage.md | Adds canonical coverage-frontier reference doc. |
| .agents/skills/ln-judo-review/SKILL.md | Expands ambient-contract cues to include data-plane rename residue. |
| .agents/skills/ln-induct/SKILL.md | Adds new ln-induct skill definition. |
| .agents/skills/ln-consult/SKILL.md | Routes systemic-review-bot findings to ln-induct and tightens coverage admission guidance. |
| .agents/skills/ln-build/SKILL.md | Tightens coverage-row execution discipline and stop conditions. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+126
to
+130
| const derivedRows = Object.entries(derived).flatMap(([axis, axisAffordance]) => | ||
| Object.keys(axisAffordance).map((field) => | ||
| field === 'legalOptions' ? `${axis}.options` : `${axis}.default_on_switch`, | ||
| ), | ||
| ); |
Comment on lines
+204
to
+211
| let report = summarizeCaptureQualityRun({ | ||
| runId: options.runId ?? defaultRunId(), | ||
| generatedAt: new Date().toISOString(), | ||
| cwd: options.cwd ?? process.cwd(), | ||
| extractorName: options.extractorName ?? 'sample-llm-output', | ||
| scenarios: CAPTURE_QUALITY_SCENARIOS, | ||
| extractions, | ||
| }); |
Comment on lines
+643
to
+647
| /** Create an elicitation-backlog entry through the command boundary. */ | ||
| createElicitationBacklogEntry( | ||
| input: CreateElicitationBacklogEntryInput, | ||
| ): CreateElicitationBacklogEntryResult { | ||
| const diagnostics = validateCreateElicitationBacklogEntry(input); |
graphite-app
Bot
changed the base branch from
ln/fe-811-poc-live-ship-blockers
to
graphite-base/178
Merge activity
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Materializes the D65-L prospective elicitation backlog and, alongside it, lands several coverage frontiers and cross-cut completion work that matured on this branch.
Core — elicitation backlog substrate (FE-823)
elicitation_backlogtable + generated migration (D65-L / A24-L); grounding agenda seeded atcreateSpec.CommandExecutoron the shared{specId, lsn}/change_logboundary; graph-owned per-spec open-entry read-back.Coverage frontiers landed alongside
src/graph/README.md+ drift guard (observed-shapes-coverage.test.ts); no transport shape shipped.CommandResultdiscriminants, structuredneeds_human, andelicittool authority derived from the shared projected runtime policy.(resolvedState, readinessGrade)affordance derivation (projections/session/affordances.ts); shared grade/AUTO legality lifted toruntime-policy.ts; coverage ledger + guard, withactive-review-set/turn-modetripwired.exchanges-and-generalized-capturenarrowly with an explicit false-commit guard.Cross-cut completion
.pi/skills/{goals,strategies,lenses,methods}plus a manifest-wide depth test. Closes the cross-cut body-depth row; the Seam 3a "what to ask next" driver is promoted to theelicitation-driverfrontier.Tooling / process
ln-inductskill (generative diagnostic lens from review-bot comments) and coverage-frontier protocol hardening across theln-*skills.Housekeeping
brunch-next-chi; canonical-memory sync (PLAN / SPEC / CROSS_CUT_PLAN / PLAN_HISTORY / topology READMEs).Note: this branch carries more than the FE-823 frontier — the coverage frontiers above matured here rather than on separate branches. The FE-811 ship-gate rename-residue + mention-autocomplete follow-ups are stacked separately on
ln/fe-811-ship-gate-residue-and-mentions.Verification
npm run verify(fix → test → build) green; 68 test files / 568 tests at merge.