DottaandClaude Opus 5
fb006b75ca
Implements the standalone, package-local Phase 7 scenario explorer against the approved interaction map (docs/design/phase-7-scenario-explorer-ux.md). Scenario runtime (src/phase7, no DOM, no network): - Scenario index over all 106 eval cases and 16 groups, with actor role, task mode, fixture seed, and catalog claims declared in a profile table rather than inferred from case prose. Claims that cannot unlock an operation in a scenario's task mode or for its actor role are dropped, so no scenario shows a grant that unlocks nothing. - Deterministic fixture seeds and fake-agent plans: twelve authored plans for the UX acceptance scenarios, derived plans for the rest. Derived plans only invoke operations the run actually exposes, so any denial in a derived transcript is a real policy result, not a scripting artefact. - A run-artifact builder that executes each plan against the Phase 7C mock control plane through the Phase 7D authorization engine and records the ordered timeline (both channels), tool exposure, authorization records, an immutable ten-domain state diff, and a parity verdict. Descriptor redaction rules are applied at the artifact boundary so no raw secret can reach a rendered record. - Parity is judged in the runtime, never in a component. Phase 7E's per-case result is carried through verbatim in its own labelled block and renders "Not run" when no report is bundled. Explorer (examples/phase7-explorer): - Read-only surface over the frozen SDK: hash routing, scenario picker with faceted filters, agent and control-plane transcript channels, and Context, Authorization, State diff, and Parity inspector tabs. Tokens only; the 0.1.2 export surface is unchanged and the runtime is reached through the deliberately package-local @paperclip-runner-local/phase7 alias. - Checked-in inputs arrive as declared virtual modules, so the example consumer keeps its boundary and fake mode does no network I/O. Verification: 45 unit tests (index, plans, all-scenario runs and parity, components, routes), 19 Playwright tests (route determinism, evidence routes, credential boundary, keyboard paths, responsive), and the 24-image screenshot acceptance set. Fixes found while building: SDK badges overflowed at 390px inside disclosure summaries; SDK badge capitalisation broke the label vocabulary; hash-change deep links left the wrong mobile segment; screenshot capture leaked run state between shots. All recorded as revisions in the interaction map. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
4.1 KiB
Native Runner Knowledge Update Log
2026-08-07
- Creation: Established the OKF v0.2 bundle, typed Phase 0 journal, verification evidence, template, and progressive-disclosure indexes.
- Rust boundary correction: Added the production-direction Cargo workspace, shared-fixture parity evidence, negative Cargo boundary coverage, and a superseding journal entry after the Phase 0 checkpoint exposed the TypeScript-only omission.
- Phase 1 static replay: Added executable PRP v1 schemas, cross-language fixture/golden parity, deterministic reducer, CLI/browser replay, compatibility policy, tutorial, screenshot, and verification evidence.
- Phase 2 local runner: Added the deterministic Rust supervisor, stdio fake-harness protocol, scripted scenarios, bounded logs, cleanup and terminal guards, TypeScript mock core, validated live browser mode, screenshots, tutorial, and verification evidence.
- Phase 3 durable recovery: Added package-local WebSocket authentication, a durable outbox, cumulative acknowledgements, restart replay, command deduplication, recovery diagnostics, tutorial, and evidence.
2026-08-08
- Phase 4 skillless Codex driver: Added the direct app-server v2 driver, compact task envelope, isolated model context, semantic completion tools, canonical event/replay mapping, safe real-model example, tutorial, journal, and exact verification trace.
- Phase 4b UX gate: Approved the live-console interaction map, the shadcn/AI Elements adapt/reject decision record with a zero-new-runtime- dependency rule, keyboard/accessibility acceptance criteria, four token additions, and annotated desktop/mobile mockups.
- Phase 4b protocol/server layer: Added deterministic Codex request, goal, lineage, control-race, reconnect, replay, and redaction fixtures; a typed server-only demo boundary; and a passing real Codex server trace.
- Phase 4b live console: Added the package-local browser tracer over the canonical protocol — transcript, composer, same-turn steering, three interrupt races, runtime request cards, capability-gated goals, parent/child lineage, reconnect, refresh, replay, and a redacted protocol inspector — plus a deterministic demo driver, eleven demo chats, adapted shadcn/AI Elements components with no new runtime dependencies, and a boundary check that keeps it that way.
- Phase 5 browser SDK: Extracted versioned browser, React, and scoped-style exports; added a public-API-only reference console and mini consumer; proved the five approved extension points, keyboard/accessibility contracts, reconnect and replay parity, package boundaries, and safe real-Codex use.
2026-08-09
-
Phase 7F browser scenario explorer: Added the package-local scenario index with declared actor roles, task modes, and catalog claims; deterministic fixture seeds and fake-agent plans for all 106 eval cases; a run-artifact runtime producing tool exposure, control-plane actions, authorization records, a ten-domain immutable state diff, and a parity verdict that carries Phase 7E output through without re-judging it; the read-only explorer over the frozen SDK with hash routing, both transcript channels, and four inspector tabs; 45 unit and 19 browser tests; and the twenty-four-image screenshot acceptance set.
-
Phase 6 integration design: Specified the default-off thin Paperclip adapter seam, public port reconciliation, first-class persisted mode/result recovery, canonical per-run event allocation, typed credential-free native input, complete Section 18 finalization/arbitration, kill switch, exact file allowlist, conformance matrix, and mock/native/legacy tutorial commands before production code.
-
Phase 6 integration implementation: Added persisted default-off runtime selection, the database-backed public control-plane port, package-owned normalized Codex sessions, canonical event allocation/replay, immutable completion/result/finalization records, server-owned status arbitration and audit, native cancellation, migration coverage, a runnable tutorial, and deterministic mock/real-port evidence while retaining legacy as the kill- switch path.