docs(evals): retain continued initial measurements and held corrections

doc/plans/2026-10-26-chat-catalog-eval-progress.md

@@ -7,10 +7,18 @@ Updated: 2026-10-27. This is the single progress record for [the saved goal](202
 - **244 scenarios / 35 areas / 191 capabilities**, frozen inventory digest `9dc9cf6a5426cf1b56bc30a3571851f233f9dd5e93a1292eaee414d33b52df77`. All original queries, contexts and expected outcomes remain unchanged. **196 passes required**; blocked, partial, unsupported and unrun remain in the denominator.
 - **229 authored: 220 without declared coverage gaps, 9 partial, 15 unimplemented** at exact committed-source metadata checkpoint `32b472dfa5640987e199c2e0aa21b2c7c02555c6`. There are 227 concrete lazy descriptors plus two legacy task cases. Actual callbacks, bounds, policies and source dependencies were reconciled from this one Git archive; newer area work remains pending. These are authoring counts, not acceptance.
 - Five partial definitions contain concrete executable supported-surface/context blocker probes: two access grants, subscription provenance, skill-use authority/context and genuine prior-day routine history. Four have unfinished required branches: the Grok origin integration closure, named ChatGPT setup, team installer failures and private-repository after-grant completion. **225 authoring-resolved; 4 unfinished; 15 absent.** Only actual reserved execution can process a concrete blocker; offline probes/calibrations do not establish processing. Incomplete conditions cannot pass.
-- **9 scenarios admitted; 10 launched measurements; 9 terminal measurements; 1 real first-attempt pass, pending final current-identity eligibility.** Running: `tasks.delegate-announcement`. Original failures remain unchanged; goal-tree exhausted and all final-B retries held.
-- **The approved unaffected11 initial batch is running sequentially from qualified immutable6be**, maxParallel1/retries0. Profile and quick-search remain unreserved/quarantined because their selected setup accepts invitations; other selected callbacks do not execute that credential-bearing route. No scanner exception or test logging adapter was added. Separate isolated core fixes are manager-owned; measured product baseline remains8373.
-- Current recovery: semaphore cleanup approval is still pending and no set has been removed. Read-only discovery verified an already running local Docker Linux/arm64 engine; an explicit owned PostgreSQL18.6 lane is being qualified. Its one infrastructure-only health check at `772c29dad9` failed before container start because Docker Desktop represents the exact host password bind with `/host_mnt`; no Paperclip, native or model work began. The initial failed cleanup receipt is preserved; separate authorized cleanup verified exact container/volume absence and removed only its password. The separately authorized corrected infrastructure-only health at `325af67e3d` passed PostgreSQL18.6, normal onboarding/migrations/API and zero work; exact owned resources were removed with no cleanup failures. The Docker lane is qualified; host IPC cleanup is no longer required. AgentMail/GitHub read-only discovery is authorized/completed; designated self-email and repository choices remain pending.
-- Production baseline `8373d7867963674ff960d2345d0d28086f799bc7`; branch `codex/chat-catalog-evals`. PR #17794 merged via `2ee36a4`. No eval/core PR has been created. No merge is eligible.
+- **27 scenarios admitted; 28 launched measurements; 27 terminal measurements; 4 real first-attempt passes, pending final current-identity eligibility.** Running at this checkpoint: `projects.project-defaults`. Original failures remain unchanged; goal-tree exhausted and all final-B retries held.
+- **The approved unaffected11 batch completed; the next24 independent initials are running sequentially from qualified immutable6be**, maxParallel1/retries0. The original next25 selection excludes `projects.project-work` before reservation because its exact-same-title fixture reproduces the known public creation deduplication alias. Initial passes: create-backlog, delegate-announcement, rename-company and list-model-options; all retain their measured identities and remain provisional until final current-closure verification. Profile and quick-search remain unreserved/quarantined because their selected setup accepts invitations; other selected callbacks do not execute that credential-bearing route. No scanner exception or test logging adapter was added. Separate isolated core fixes are manager-owned; measured product baseline remains8373.
+- Current recovery: semaphore cleanup approval is still pending and no set has been removed. Read-only discovery verified an already running local Docker Linux/arm64 engine; the explicit owned PostgreSQL18.6 lane is qualified. Its one infrastructure-only health check at `772c29dad9` failed before container start because Docker Desktop represents the exact host password bind with `/host_mnt`; no Paperclip, native or model work began. The initial failed cleanup receipt is preserved; separate authorized cleanup verified exact container/volume absence and removed only its password. The separately authorized corrected infrastructure-only health at `325af67e3d` passed PostgreSQL18.6, normal onboarding/migrations/API and zero work; exact owned resources were removed with no cleanup failures. The Docker lane is qualified; host IPC cleanup is no longer required. AgentMail/GitHub read-only discovery is authorized/completed; designated self-email and repository choices remain pending.
+- Production baseline `8373d7867963674ff960d2345d0d28086f799bc7`; branch `codex/chat-catalog-evals`. PR #17794 merged via `2ee36a4`. No eval PR has been created. Separate unmerged core fixes are [invite URL logging #17848](https://github.com/paperclipai/paperclip/pull/17848) and [doctor DATABASE_URL handling #17847](https://github.com/paperclipai/paperclip/pull/17847); neither changes the measured8373 baseline. No merge is eligible.
+
+## Current measured continuation and held corrections
+
+The current ledger is authoritative; archived selection summaries remain historical. Every completed case in the current two batches has verified cleanup and exact owned Docker removal. Native subscription dollar amounts remain unpriced; synthetic imported fixture costs never enter campaign billing. Counts of human turns refer to the source standing chat, while separate operator actions remain in case evidence.
+
+Coherent final-B corrections are accumulating without reruns. `983f15394e` removes the archive reply-link overconstraint while exercising actual historical project/task UI and API access, accepts truthful common audit actor headers, grades meaningful Orchid plan requirements without nonce repetition, and fixes hire-denied's public permissions payload without widening task authority. `200e7fc3ac` refreshes the API-created company inventory before the canonical turn and binds the retained UI journeys to actual status labels, original interaction IDs and the visible organization toggle. Focused internal controls113, runtime-agent controls26 and relevant identity/runtime controls49 passed; scoped E2E typecheck passed. Raw failed initial evidence remains unchanged.
+
+Necessary-question's retained observation contains no saved task, document or result link. Its original answered question asked for product, audience and CTA; the supplied short product-name answer was followed by another actual pending positioning question. This is retained for exact YAML/fixture diagnosis, not reclassified as a passing saved brief. Goal-tree remains exhausted; all final-B attempts remain held.
 
 ## Measured evidence — all failures retained