Set up source-grounded frontend research workflows with infospace-bench

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0cffe-206f-7323-89d3-b20ca4cf4bf9

workplans/FEP-WP-0002-seed-language-validation.md

@@ -99,3 +99,12 @@ assessed before execution.
   walkthrough reviews, explicit counterevidence and the M1 acceptance review.
 - Done-condition: the phase acceptance section above; hypotheses may be rejected
   or deferred with reasons rather than falsely confirmed to close a task.
+
+
+## Source investigation tooling
+
+FEP-WP-0005 established `research/bench/README.md` and `scripts/research_bench.py`.
+Use one isolated workspace per source excerpt, review original-source-grounded
+claims/candidates/relations/critique, and follow `research/bench/Admission.md`.
+The fixture run is synthetic and does not complete any task in this workplan.
+T02 still owns source acquisition/review; T03 owns cross-source synthesis and cases.

workplans/FEP-WP-0005-research-bench-setup.md

@@ -0,0 +1,70 @@
+---
+id: FEP-WP-0005
+type: workplan
+title: "Set up the frontend research bench"
+domain: infotech
+repo: frontend-patterns
+status: finished
+owner: codex
+topic_slug: canon
+created: "2026-09-24"
+updated: "2026-09-24"
+---
+
+# Set up the frontend research bench
+
+Implement the user's accepted infospace-bench integration inside this repository.
+The research corpus stays repository-owned; bench executes inspectable source
+investigations. Live research generation and canonical promotion are outside setup.
+
+## Install the domain workflow and intake adapter
+
+```task
+id: FEP-WP-0005-T01
+status: done
+priority: high
+```
+
+Added bibliography-bearing source intake, immutable source digests, copied workflow
+profiles and four ordered stages: claims, candidates, relation proposals, critique.
+Each review sees the original source and all intermediate results. One source per
+workspace avoids the upstream stage-output isolation limitation. Empty proposals
+are permitted; no automatic entity or canon admission occurs.
+
+## Verify fixture execution and failure boundaries
+
+```task
+id: FEP-WP-0005-T02
+status: done
+priority: high
+```
+
+The synthetic fixture completed all four stages at
+`research/bench/infospaces/fixture-smoke/`. `make bench-test` checks the real bench
+workflow adapter: source and intermediate prompt context, provenance, source
+mutation, multiple-source rejection, call cap, missing bibliography, failure receipt
+and refusal to overwrite attempted runs. No live provider calls occurred.
+
+## Document research operation and admission
+
+```task
+id: FEP-WP-0005-T03
+status: done
+priority: medium
+```
+
+`research/bench/README.md`, `SourceInput.md` and `Admission.md` describe setup,
+fixture/live commands, evidence status, ID mapping and review boundaries. Updated
+agent workflow and research program entry points.
+
+## Residual handoff
+
+- Original source acquisition and evidence review: FEP-WP-0002-T02.
+- Resolve metadata contract and provisional canonical ID mapping: FEP-WP-0002-T01.
+- Cross-source synthesis and VC-01/VC-02 walkthroughs: FEP-WP-0002-T03.
+- Typed graph export, metadata validator and retrieval evaluation: FEP-WP-0004.
+
+Known limits: structural validation does not validate research claims; critique is
+assisted self-review; custom run supports explicit OpenRouter or fixture adapters;
+call caps do not enforce dollar/token budgets; one source per run; failed runs
+require a fresh workspace rather than an automatic resume.