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

Retain failed authorized replication and reconcile gap work

Browse source 
Assistant: codex
Assistant-Model: gpt-6.1-sol
Assistant-Session: 01a1045b-933d-7aa1-b2db-104557487a79
This commit is contained in:
tegwick 2026-10-04 11:15:05 +02:00
parent 88826ca598
commit 5da8b2405c
40 changed files with 2816 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

11
workplans/FEP-WP-0006-language-evolution.md
View file

@ -253,3 +253,14 @@ local links/whitespace passed. [Review snapshot](../research/evolution/snapshots
pins the committed assessment at implementation revision `d8d3a22`; it is a
measurement-review boundary, not an additional empirical cycle. The original
baseline and all previous snapshots are unchanged.
## Retained failed replication cycle — 2026-10-04
LEARN-0019 preregistered at `1e2741a` is an inconclusive attempted presentation
replication in a new protocol group. All twelve attempts failed; no usable answers,
ratings or quality result. Research effort is unknown; request duration is separately
measured. The ledger now has nine prospective attempts/cycles in eight groups,
including this wholly failed run. Largest group remains two, with LEARN-0017 effort
unknown. This failure is retained and cannot establish returns or close T03's
three-cycle prerequisite. WP-0009 T02 owns restoration/future authorized replication.

21
workplans/FEP-WP-0009-m1-independent-validation.md
View file

@ -4,7 +4,7 @@ type: workplan
title: "Obtain independent validation for the M1 seed gate"
domain: infotech
repo: frontend-patterns
status: active
status: blocked
owner: codex
topic_slug: canon
origin: residual
@ -43,7 +43,8 @@ submitted-review-01 worksheet was a model review and does not count.
```task
id: FEP-WP-0009-T02
status: progress
status: wait
blocking_reason: "All 12 authorized attempts failed; llm-connect endpoint unreachable. A future replication requires restored service and fresh explicit execution authorization; no retries allowed."
priority: medium
state_hub_task_id: "8e0ac763-eba4-5625-ad63-af53322bcac4"
```
@ -94,3 +95,19 @@ The user then explicitly authorized **up to 12 calls, 1,400 output tokens per ca
no retries**. This is the fresh replication budget only, not a grant for further model
reviews, autonomous editing, policy changes or human-score substitution. Freeze and
commit the packet/runner before execution; reserve every attempt and retain failures.
## Retained failed replication — 2026-10-04
The preregistered packet/runner was committed and synced at `1e2741a` before
execution. All twelve reserved attempts failed with no retained answer or provider
usage receipt. Both sandbox and host health probes found the configured llm-connect
endpoint unreachable. No call was retried. The budget is conservatively exhausted
as twelve reserved attempts, without claiming twelve provider executions or zero cost.
[Execution record](../research/evaluations/language-replication-02/README.md) retains
all failures, null ratings and six excluded pairs. Packet construction, validation
and bounded execution are implemented; T02 remains wait because no empirical
comparison exists. Future execution needs a new registered packet/run identity and
fresh explicit authorization after service restoration. T01 and T03 retain their
existing gates. LEARN-0019 records one inconclusive attempted cycle, not useful
validation or independent evidence.