coulomb/frontend-patterns
5
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

repo.work.assign_missing_identifiers

Browse source 
source: repo-manager
reason: deterministic projection registration

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0cffe-206f-7323-89d3-b20ca4cf4bf9
This commit is contained in:
repo-manager 2026-09-24 07:58:10 +02:00
parent 8a141b7fe5
commit c161369ad5
2 changed files with 8 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

4
workplans/FEP-WP-0004-reference-surface.md
View file

@ -9,6 +9,7 @@ owner: codex
topic_slug: canon
created: "2026-09-24"
updated: "2026-09-24"
state_hub_workstream_id: "831bbc30-30c0-5df3-a315-5355cd3b8ee5"
---
# Evaluate retrieval and real repository applicability
@ -23,6 +24,7 @@ Individual task descriptions identify any work that can start earlier.
id: FEP-WP-0004-T01
status: todo
priority: high
state_hub_task_id: "4fec98f6-fee2-52fc-a01c-f490c79ee0f8"
```
After the schema and seed examples pass M1, implement the smallest validator/exporter needed to check unique IDs, allowed values, relation targets and evidence references. Add meaningful invalid and valid fixtures; preserve prose and source provenance.
@ -33,6 +35,7 @@ After the schema and seed examples pass M1, implement the smallest validator/exp
id: FEP-WP-0004-T02
status: todo
priority: medium
state_hub_task_id: "4bdd4c53-fcdb-5dfd-9a37-ebc3fee4d445"
```
After M2, freeze a corpus revision and evaluate at least six unseen prompts following ValidationCases.md. Record expected alternatives, abstentions, unsupported claims and missed constraints; compare with manual navigation. Address Q07.
@ -43,6 +46,7 @@ After M2, freeze a corpus revision and evaluate at least six unseen prompts foll
id: FEP-WP-0004-T03
status: todo
priority: medium
state_hub_task_id: "ab66848b-1045-54dd-9711-52c5560faafa"
```
Study at least two contrasting accessible repositories at recorded revisions. Separate observed implementation from inferred intent. Write research/reviews/M3-EmpiricalReview.md, publish limitations, and hand remaining findings into live work records.