PaperClipAI/tests/runner-e2e/CHAT-FEATURES.md

Chat feature evals

chat-features promotes two entries from the scenario catalog into real Product E2E executions. The scope is deliberately small: prove the fixture, browser interaction, independent grading and report loop before adding more features. Catalog coverage is not live acceptance.

Scenario	Actual user request	Independent outcome
tasks.create-backlog	Add a task for Morgan to draft the launch announcement in Launch, but don't start it yet.	Exactly one task, Launch project, Morgan assignee, backlog at creation, no worker execution, usable chat link after reload.
tasks.delegate-announcement	Have Morgan write a two-sentence launch announcement using the Launch project brief, save it on the task, and send me the result here when it's finished.	Exactly one task, actual Morgan execution, current worker-authored document grounded in the project brief, task Done, automatic completion response in the original chat, usable result after reload.

The queries are read directly from chat-scenarios/tasks.yaml. Context and expected outcomes stay evaluator-side. The fixture creates a disposable company, CEO, Morgan and Launch project through production APIs; both agents use the shipped role instructions. The brief contains a product, date and random invitation code absent from the user query. The browser sends one message through Agent Chat. The harness never creates the result task, writes the announcement, completes the task, or sends a hidden follow-up.

Run the first slice

Follow the installation steps in README.md. The Codex subscription profile uses the catalog's recorded default model and an explicit CODEX_AUTH_JSON login. Load that login privately into the launcher environment; do not print it or save it in tracked configuration. The existing subscription fixture stages only auth.json in the disposable company login slot and removes it with the isolated instance.

The local native OpenCode profile uses the current production-qualified model and OPENROUTER_API_KEY through the existing encrypted company-secret fixture. Each of the two journeys has a cell for each profile. All four cells are manual.

pnpm test:e2e:runner:typecheck
pnpm test:e2e:runner:unit
pnpm test:e2e:runner -- --list --suite chat-features
pnpm test:e2e:runner -- --id chat-features.runner-codex-subscription.local.create-backlog --max-automatic-retries 0
pnpm test:e2e:runner -- --id chat-features.runner-codex-subscription.local.delegate-announcement --max-automatic-retries 0
pnpm test:e2e:runner -- --id chat-features.runner-opencode.local.delegate-announcement --max-automatic-retries 0

Run creation first and inspect its packaged report before delegation. For initial acceptance, run each cell three times against fresh fixtures on the same definition revision. Keep every attempt, including failures; a retry does not erase one. A fixture or product correction starts a new three-sample measurement. All cells are explicit-only and excluded from --all; this does not implement or qualify the rest of the YAML inventory.

Bounds and grading

Creation expects one accounted native work run; delegation expects three (CEO handoff, Morgan work, CEO completion response). Runs have a 120-second timeout and attempts a seven-minute deadline. The visible task and completion reply must settle within five minutes after the human request, including a five-second stable observation. This is an independent journey acceptance bound: three runs may not each consume their maximum timeout and still pass. The outer attempt also covers fixture setup, reload and link checks, and evidence collection. A failed provider run rejects immediately; the historical missing turn-start event was not a five-minute poll timeout. Automatic retries are disabled. Company and agent budgets are 500 cents each, CEO daily work runs are capped at three, Morgan at one, and periodic heartbeats are disabled. Initial production hello probes fall outside heartbeat usage and budget accounting; detailed setup tokens and cost are unavailable. These limits are not an absolute inference or cash cap. Subscription cost coverage must remain explicit in the report.

An obsolete CEO assignment can leave a cancelled queue entry when the CEO creates a task and then assigns it to Morgan. Grader v2 distinguishes that entry from provider work only when the dispatch gate records issue_assignee_changed, an explicitly null start time, no native issue, and its unchanged stale-queue stop receipt. The entry must belong to this company and the one task now assigned to Morgan. It stays in the full observation and final ledger, with its events and an explicit provider-log omission reason. Active, unrelated, or unproved cancellations still fail. The three successful work runs, worker output, completion delivery, and original deadlines remain required. Backlog creation still permits no task wake.

Because this subscription currently reports unpriced usage, setup explicitly sets unpricedUsagePolicy: allow on the disposable company and both agents through the public budget API and verifies all three policies. The 500-cent hard stops remain enabled for reported costs; they cannot cap unknown dollar usage. Run caps and deadlines remain independent bounds. Without this explicit funding prerequisite, the default policy pauses the company after the first unpriced run and cancels the delegated worker. Such a pause is not a successful chat journey.

chat-feature.json retains the scenario ID, capability IDs, grader version, saved records, audit attribution, rendered links and individual checks. chat-feature-runs.json uses the existing native run evidence collector, including on failures. Setup evidence records fixture IDs, synthetic brief, readiness and saved budgets. Ordinary Product E2E evidence packaging, redaction, cleanup, failure classification and dashboards own the result. The definition digest includes the query, defaults, flow and grader sources. Individual saved-state checks are also recorded when the journey fails, so the report shows partial progress without turning it into a passing workflow.

The grader rejects duplicate tasks, wrong owners/projects/companies, early execution, missing audit attribution, missing or stale deliverables, extra human nudges and uncorrelated completion replies. Document provenance binds the current revision to Morgan's actual run. The completion check reuses completionDelivery; a handoff promise or a marker alone cannot establish delivery. Chromium verifies the task link and reload persistence.

The checks establish the specified saved state, two-sentence structure, required brief facts and result access. They do not score writing quality or every semantic claim in the response. Inspect the retained conversation and announcement before accepting the first samples; the existing completion semantic-review rubric still applies. Oracle calibration tests exercise both valid evidence and plausible wrong outcomes without calling a model.

Only after this loop is stable should another scenario be promoted. Keep each starting condition explicit: connected versus missing connection, allowed versus approval-required, and so on. Reuse the fixture/report infrastructure and add a case-specific outcome oracle; do not make all YAML paragraphs executable through an unconstrained model judge.

Initial measurement — 2026-10-26

Three fresh samples per cell on definition 7fb20426ce3f1dd4efeddfb79f231336ea65a16b9c2a73bf6131e997acd74e9d produced 5/6 passes: backlog creation 3/3 and delegation 2/3. These used local native Codex subscription execution with gpt-5.6-sol. All six cleaned up successfully. Both workflows have successful browser-to-provider evidence, but the initial repeatability target is not met.

In campaign local-2026-10-26T15-48-12-199Z, the first CEO run in delegation failed before creating a task: runnerd did not report the provider turn identity. Retained events show submission and provider startup, followed by the transport's turn-start deadline. The precise cause of the missing event remains unresolved; the existing machine classification is retained without claiming that the provider or infrastructure has been proven responsible. Investigate this before expanding the suite. No replacement sample erased this failure.

The local results/chat-feature-acceptance/acceptance.md records every sample and earlier failed revision; its sibling dashboard uses the standard report generator. Results are ignored generated artifacts, so retain or publish them through the existing Product E2E pipeline when handing this measurement to another machine.

Follow-up measurement — 2026-10-26

The unchanged delegation cell subsequently passed three fresh executions: local-2026-10-26T16-50-50-751Z, local-2026-10-26T16-54-58-203Z, and local-2026-10-26T16-58-39-074Z. The latter two campaigns also ran backlog creation concurrently and passed both cells. All five selected executions used one attempt with zero automatic retries, retained the same definition above, and passed cleanup. Five existing turn-identity, early-terminal and runner-exit regressions passed as well.

These are green rechecks, not a demonstrated repair of the earlier startup interruption: no production code, timing limits or oracle assertions changed, and the missing turn-start event did not reproduce. Keep the original failure in the history. Across the original final-definition batch and this recheck, backlog is 5/5 and delegation is 5/6. The local results/chat-feature-recheck/verification.md records the follow-up evidence; its standard dashboard is explicitly scoped to the latest campaign.