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

Diagnose table-padding truncation and complete local-first investigation

Browse source 
Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0cffe-206f-7323-89d3-b20ca4cf4bf9
This commit is contained in:
tegwick 2026-09-25 01:55:22 +02:00
parent 509e86d9c5
commit 90d1f86b8f
50 changed files with 2197 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

31
research/bench/README.md
View file

@ -64,8 +64,8 @@ Then run in a fresh workspace:
../infospace-bench/.venv/bin/python scripts/research_bench.py run \
research/bench/infospaces/carniato-review-01 \
--llm-connect-url http://127.0.0.1:18081 \
--model custodian-triage-balanced --reasoning-effort low \
--max-tokens 6000 --max-calls 4
--model custodian-triage-balanced --diagnostics \
--max-tokens 3000 --max-calls 4
```
In-cluster consumers can use `http://llm-connect.activity-core.svc.cluster.local:8080`.
@ -115,7 +115,7 @@ the workflow and retain diagnostic metadata. Successful runs remain unreviewed.
| Investigation | Input readiness | Work record |
| --- | --- | --- |
| Carniato first source case | Manual review plus completed llm-connect draft; admission rejected | FEP-WP-0002-T02 |
| Contrasting local-first source | Manual review; llm-connect claims response truncated | FEP-WP-0002-T02 |
| Contrasting local-first source | Manual plus completed bounded live review; no candidates justified | FEP-WP-0002-T02 |
| VC-01 and VC-02 synthesis | Depends on reviewed source claims and candidate patterns | FEP-WP-0002-T03 |
Do not ingest the existing Carniato research stub as if it were the original article.
@ -183,3 +183,28 @@ That attempt (`local-first-authority-03`) truncated at claims: one request, 6,52
reported total tokens. No further retry was made. See
[refinement review](../reviews/ResearchPipelineRefinement.md) for the remaining
execution limitation and the captured-failure screening report.
## Execution diagnostics and compact output
`--diagnostics` requests llm-connect's per-call debug capture but stores only an
allowlisted summary: numeric generation settings, presence of reasoning fields,
numeric usage/cost and reasoning-token counts. It never writes raw debug bodies,
headers, prompts or internal reasoning text. The service response may contain those
fields transiently; this consumer discards them. Availability depends on the server.
Normal model-generated incomplete content is quarantined separately as
`reports/rejected-response.md`, with a hash and rejected status in the receipt;
it is not registered as a completed research artifact.
The inspected llm-connect OpenRouter adapter drops `reasoning_effort`. Live diagnostic
capture confirmed its absence at the provider boundary. Do not use that flag as a
working control for this route; it remains available for other service implementations.
The local-first diagnostic output was a table header followed by tens of thousands
of spaces. Current prompts use compact records and explicitly forbid padded tables.
See the [truncation diagnosis](../reviews/TruncationDiagnosis.md) for measured outcomes.
Local-first `-06` subsequently completed all four stages at the 3,000-token response
cap using compact records. Its empty candidate/relation outcome passes structural
screening; editorial review admits no patterns. The next work is source expansion,
not another truncation retry.