# Agent Lab MVP Todos

## Workflow

- Main session owns this file and evaluates progress after each todo.
- Work on one todo at a time: write its plan, execute it, verify it, then update this file.
- Do not plan all implementation details upfront. Later todos may change after each evaluation.
- Detailed plans live beside this file as `docs/plans/todo-N-*.md`.
- Status values: `pending`, `in_progress`, `done`, `blocked`.

## Current State

- Branch: `codex/agent-lab-mvp`.
- MVP committed at `6babafa` with FastAPI, WebSocket, static UI, OpenAI-compatible streaming, EventAgent handoff, provider-compatibility guards, and tests.
- Post-MVP work now evolves toward the original queue/event-driven debugging-console requirements.

## Coverage Review

- OpenAI Chat Completions compatible streaming and provider payload guards are covered by todos 2, 5, and 7.
- Queue/event-driven ChatAgent and EventAgent handoff is covered by todo 9.
- EventAgent tool loading and UI management is covered by todo 10.
- Prompt/pre-message editing, parameter controls, and reusable prompt sets are covered by todos 3 and 11.
- Chat-window token, cached-token, TTFT, elapsed-time, and per-round stats are covered by todo 12.
- Review follow-up gaps in real queue boundaries, API validation, packaging, and tool error isolation are covered by todos 13-16.

## Todos

| ID | Status | Plan | Goal | Verification |
| --- | --- | --- | --- | --- |
| 1 | done | `docs/plans/todo-1-project-foundation.md` | Establish uv/FastAPI project skeleton, DDD package layout, and core failing tests for parser, event agent, and runtime routing. | `uv run pytest` fails only because implementation is missing, not because tests or imports are malformed. |
| 2 | done | `docs/plans/todo-2-domain-runtime.md` | Implement domain models, OpenAI Chat Completions compatible stream parsing, EventAgent tools, and the direct async runtime loop. | Core tests pass with mocked ChatAgent client. |
| 3 | done | `docs/plans/todo-3-websocket-api.md` | Add FastAPI config, HTTP routes, WebSocket protocol, static debug page, and assistant transcript persistence for multi-turn LLM calls. | WebSocket contract tests pass; app imports successfully. |
| 4 | done | `docs/plans/todo-4-real-llm-smoke.md` | Document env-based real LLM run flow, add a lightweight manual smoke helper, and make sure settings names are clear. | App starts with env-based config; docs show exact `uv` commands and required env vars. |
| 5 | done | `docs/plans/todo-5-tool-call-history.md` | Harden Chat Completions history so assistant tool calls and tool replies are sent in provider-compatible order. | Tests prove the next model call includes assistant `tool_calls` before `tool` replies. |
| 6 | done | `docs/plans/todo-6-cleanup-closeout.md` | Clean temporary/generated files, update contributor docs, and run final verification. | Git status contains only intended source/docs files; `uv run pytest` passes. |
| 7 | done | `docs/plans/todo-7-provider-compatibility.md` | Fix review findings for real Chat Completions compatible providers: default model fallback, role-aware message serialization, and configurable usage streaming. | Tests prove provider payload shape and full suite passes. |
| 8 | done | `docs/plans/todo-8-tool-pre-message-guard.md` | Prevent manually configured pre-messages from producing invalid provider `tool` payloads without `tool_call_id`. | Tests prove invalid tool pre-messages are rejected and UI no longer exposes `tool` role. |
| 9 | done | `docs/plans/todo-9-explicit-runtime-queues.md` | Refactor runtime internals to explicit input, output, and event queues while preserving the WebSocket stream contract. | Tests prove ChatAgent consumes input queue, EventAgent consumes event queue, and output queue drives streamed responses. |
| 10 | done | `docs/plans/todo-10-tool-registry-management.md` | Replace the single hardcoded EventAgent tool checkbox with a backend tool registry and UI-managed loaded tools. | Tests prove available tools are listed by API and selected tools control EventAgent behavior. |
| 11 | done | `docs/plans/todo-11-prompt-workspace.md` | Improve prompt/pre-message editing with browser-side persistence and reusable prompt sets. | UI tests or focused JS tests prove prompts persist and can be restored. |
| 12 | done | `docs/plans/todo-12-round-stats.md` | Move round statistics to structured backend events for token counts, cached tokens, TTFT, elapsed time, and per-turn summaries. | `uv run pytest tests/test_debug_runtime.py tests/test_websocket_api.py`; `uv run pytest`. |
| 13 | done | `docs/plans/todo-13-real-queue-websocket-loop.md` | Make runtime queues real producer/consumer boundaries and let WebSocket run separate upstream/downstream tasks. | `uv run pytest tests/test_debug_runtime.py tests/test_websocket_api.py`; `uv run pytest`. |
| 14 | done | `docs/plans/todo-14-message-role-validation.md` | Reject provider-invalid API message roles and malformed tool replies before network calls. | `uv run pytest tests/test_websocket_api.py tests/test_event_agent.py`; `uv run pytest`. |
| 15 | done | `docs/plans/todo-15-static-package-data.md` | Include static UI assets in installed package builds. | `uv run pytest tests/test_packaging.py`; `uv run pytest`; `uv build`; wheel inspection. |
| 16 | done | `docs/plans/todo-16-tool-error-isolation.md` | Convert EventAgent tool handler exceptions into structured tool-result errors instead of aborting the session. | `uv run pytest tests/test_event_agent.py tests/test_debug_runtime.py`; `uv run pytest`. |
| 17 | done | `docs/plans/todo-17-agent-config-audit-tools.md` | Align ChatAgent/EventAgent config, add extra_body defaults, default EventAgent to one event round, add mock tools, audit events, and backend logging. | `uv run pytest` passes (`42 passed`, one existing Starlette deprecation warning). |
| 18 | done | `docs/plans/todo-18-prompt-modal-tool-ui.md` | Move prompt workspace into a modal and improve visible tool-management UI. | `uv run pytest` passes (`46 passed`), plus local browser check confirms modal and tool UI render. |
| 19 | done | `docs/plans/todo-19-latency-oriented-polish.md` | Do one optimization pass focused on reducing perceived reply wait time and cleaning frontend/backend rough edges. | `uv run pytest` passes (`49 passed`), plus local browser check confirms tools are visible in the first viewport. |
| 20 | done | `docs/plans/todo-20-agent-config-modals.md` | Split ChatAgent and EventAgent settings into separate configuration modals so the sidebar is no longer crowded. | `uv run pytest` passes. |
| 21 | done | `docs/plans/todo-21-event-agent-context-summary.md` | Make EventAgent config part of parameter generation context and enqueue an aggregated tool-result summary for the next ChatAgent round. | `uv run pytest` passes (`50 passed`, one existing Starlette deprecation warning). |
| 22 | done | `docs/plans/todo-22-text-event-protocol.md` | Replace ChatAgent tool calls with streamed text event parsing, inject generated event descriptions as a system message, and harden Agent config buttons. | `uv run pytest` passes (`50 passed`, one existing Starlette deprecation warning), plus local browser click check. |
| 23 | done | `docs/plans/todo-23-agent-prompt-and-event-llm.md` | Move Prompt Config into ChatAgent config, show available-event prompt by default, and make EventAgent use LLM tool calls to generate tool arguments. | `uv run pytest` passes (`51 passed`, one existing Starlette deprecation warning); changed Python modules compile; local server returned page/static assets/tools API. |
| 24 | done | `docs/plans/todo-24-chat-agent-prompt-list.md` | Put all ChatAgent prompts, including generated EventAgent event rules, into one ordered prompt list with add/delete/drag controls. | `uv run pytest` passes (`51 passed`, one existing Starlette deprecation warning), plus local browser prompt-list check. |
| 25 | done | `docs/plans/todo-25-prompt-list-message-types.md` | Make the ChatAgent prompt list visually compact and show the message type for each prompt item. | `uv run pytest` passes (`51 passed`, one existing Starlette deprecation warning); local service returned `/health` and versioned JS asset. |
| 26 | done | `docs/plans/todo-26-workspace-snapshot-save.md` | Move save/load/delete out of ChatAgent config and save one workspace snapshot covering prompts, Agent config, and selected tools. | `uv run pytest tests/test_websocket_api.py -q` passes (`27 passed`, one existing Starlette deprecation warning). |
| 27 | done | `docs/plans/todo-27-event-agent-tool-arguments.md` | Make EventAgent tool argument generation robust for compatible providers that do not emit the expected tool-call finish reason or ignore tool calls. | `uv run pytest` passes (`53 passed`, one existing Starlette deprecation warning). |
| 28 | done | `docs/plans/todo-28-session-turns.md` | Split WebSocket session lifetime from user turns so one conversation can run multiple user messages while each turn has its own event budget. | `uv run pytest` passes (`56 passed`, one existing Starlette deprecation warning). |
| 29 | done | `docs/plans/todo-29-rich-audit-log.md` | Add audit entries for ChatAgent/EventAgent model parameters, prompts/messages, results, and usage without logging secrets. | `uv run pytest` passes (`57 passed`, one existing Starlette deprecation warning). |
| 30 | done | `docs/plans/todo-30-sqlite-session-store.md` | Add a SQLite-backed store and REST APIs for sessions, chat messages, audit replay data, and usage summaries. | `uv run pytest tests/test_sqlite_store.py tests/test_websocket_api.py -q` passes (`36 passed`, one existing Starlette deprecation warning); `uv run pytest` passes (`66 passed`, one existing warning). |
| 31 | done | `docs/plans/todo-31-runtime-persistence.md` | Persist runtime Agent config snapshots, user/assistant messages, audit entries, and per-call usage during WebSocket turns. | `uv run pytest tests/test_sqlite_store.py tests/test_debug_runtime.py tests/test_websocket_api.py -q` passes (`55 passed`, one existing warning); `uv run pytest` passes (`66 passed`, one existing warning). |
| 32 | done | `docs/plans/todo-32-session-ui.md` | Add new-session/session-list UI, separate audit replay panel, and single-call/turn/session usage displays. | `node --check src/agent_lab/presentation/static/app.js`; `uv run pytest tests/test_websocket_api.py -q` passes (`34 passed`, one existing warning); `uv run pytest` passes (`66 passed`, one existing warning). |
| 33 | done | `docs/plans/todo-33-audit-replay-stream-ui.md` | Redesign Audit Replay as a clickable event stream, keep audit events out of chat, and fix fixed/scrolling layout boundaries. | `node --check src/agent_lab/presentation/static/app.js`; `uv run pytest tests/test_websocket_api.py -q` passes (`36 passed`, one existing warning); `uv run pytest` passes (`68 passed`, one existing warning); `git diff --check` passes. |
| 34 | done | `docs/plans/todo-34-event-agent-history-boundary.md` | Restrict EventAgent context to conversational user/assistant messages instead of the full ChatAgent context list. | `uv run pytest tests/test_debug_runtime.py -q` passes (`21 passed`); `node --check src/agent_lab/presentation/static/app.js`; `uv run pytest` passes (`70 passed`, one existing warning); `git diff --check` passes. |
| 35 | done | `docs/plans/todo-35-audit-modal-raw-llm-events.md` | Make Audit Replay a modal, fix round event metadata after EventAgent follow-up rounds, and expose raw LLM response chunks. | `node --check src/agent_lab/presentation/static/app.js`; `uv run pytest tests/test_debug_runtime.py tests/test_event_agent.py tests/test_websocket_api.py -q` passes (`63 passed`, one existing warning); `uv run pytest` passes (`71 passed`, one existing warning); `git diff --check` passes. |
| 36 | done | `docs/plans/todo-36-audit-detail-compact-ui.md` | Make Audit Detail modal metadata and event lists compact, and version CSS to avoid stale oversized styling. | `node --check src/agent_lab/presentation/static/app.js`; `uv run pytest tests/test_websocket_api.py -q` passes (`36 passed`, one existing warning); `uv run pytest` passes (`71 passed`, one existing warning); `git diff --check` passes. |
| 37 | done | `docs/plans/todo-37-audit-detail-flow-layout.md` | Fully replace Audit Detail grid/card layout with compact flow layout so metadata cannot stretch vertically. | `node --check src/agent_lab/presentation/static/app.js`; `uv run pytest tests/test_websocket_api.py -q` passes (`36 passed`, one existing warning); `uv run pytest` passes (`71 passed`, one existing warning); `git diff --check` passes. |
| 38 | done | `docs/plans/todo-38-audit-round-event-semantics.md` | Make `events_enabled` mean current-round enabled events and move full configured event list to `configured_events`. | `node --check src/agent_lab/presentation/static/app.js`; `uv run pytest tests/test_debug_runtime.py tests/test_websocket_api.py -q` passes (`58 passed`, one existing warning); `uv run pytest` passes (`71 passed`, one existing warning); `git diff --check` passes. |
| 39 | done | `docs/plans/todo-39-audit-turn-relative-time.md` | Add per-audit-event elapsed time relative to the user message that started the current turn. | `uv run pytest` passes (`72 passed`, one existing Starlette deprecation warning); `node --check src/agent_lab/presentation/static/app.js`; `git diff --check` passes. |
| 40 | done | `docs/plans/todo-40-chat-message-stream-audit.md` | Add audit events before ChatAgent visible message streaming starts and after it ends. | `uv run pytest` passes (`73 passed`, one existing Starlette deprecation warning); `node --check src/agent_lab/presentation/static/app.js`; `git diff --check` passes. |
| 41 | done | `docs/plans/todo-41-session-button-feedback.md` | Add explicit Sessions-panel feedback for New, Refresh, and Load clicks. | `uv run pytest` passes (`73 passed`, one existing Starlette deprecation warning); `node --check src/agent_lab/presentation/static/app.js`; `git diff --check` passes. |
| 42 | done | `docs/plans/todo-42-session-switch-idle-socket.md` | Allow switching sessions after a turn completes while the reusable WebSocket is still open. | `uv run pytest tests/test_websocket_api.py -q` passes (`37 passed`, one existing Starlette deprecation warning); `uv run pytest` passes (`74 passed`, one existing warning); `node --check src/agent_lab/presentation/static/app.js`; `git diff --check` passes. |
| 43 | done | `docs/plans/todo-43-typed-provider-tool-calls.md` | Preserve native provider tool calls as a distinct stream event without changing the existing text-event path. | `uv run pytest tests/test_openai_stream_parser.py -q`; focused typed-event regressions; full suite passes (`82 passed`, one existing warning). |
| 43.1 | done | `docs/plans/todo-43.1-typed-event-consumer-regression.md` | Repair Runtime and EventAgent consumers after typed stream kinds exposed legacy `event` assumptions. | Runtime consumes `text_event`, EventAgent consumes `provider_tool_call`; focused and full tests pass. |
| 43.2 | done | `docs/plans/todo-43.2-remove-legacy-event-consumption.md` | Remove legacy `event` consumption from production paths and migrate remaining fixtures to typed stream kinds. | Wrong-source negative tests and real client `[DONE]` integration pass; full suite passes (`82 passed`). |
| 44 | done | `docs/plans/todo-44-provider-tool-transcript.md` | Add provider-compatible assistant tool-call and tool-result message serialization plus explicit tool-choice behavior. | Focused transcript tests pass (`97 passed`); full suite passes (`108 passed`, one existing warning). |
| 44.1 | done | `docs/plans/todo-44.1-tool-transcript-hardening.md` | Harden transcript identity, reserved payload fields, EventAgent history projection, and public pre-message boundaries. | Duplicate IDs, invalid choices, reserved overrides, projected history, and pre-message boundaries are covered; full suite passes. |
| 45 | done | `docs/plans/todo-45-generic-event-kernel.md` | Build a generic event kernel with definition metadata, deterministic-first resolution, policies, execution ports, and result aggregation. | Generic kernel, EventAgent compatibility, and event-name decoupling pass final gates; full suite passes (`203 passed`, one existing warning). |
| 45.1 | done | `docs/plans/todo-45.1-event-kernel-boundary-hardening.md` | Harden JSON Schema validation, normalized failures, fallback raw arguments, async handlers, and existing EventAgent concurrency. | JSON Schema, normalized failure, strict argument, async handler, and concurrency regressions pass. |
| 45.2 | done | `docs/plans/todo-45.2-event-fallback-semantics.md` | Restrict fallback to incomplete resolution, enforce JSON-type-sensitive raw consistency, and distinguish definition failures. | Fallback is limited to missing-only/incomplete-valid input; complete-invalid and provider-resolved input never call LLM fallback. |
| 45.3 | done | `docs/plans/todo-45.3-sync-resolution-completeness.md` | Make synchronous kernel execution reject explicitly incomplete deterministic resolution instead of invoking the handler. | Sync structured incomplete input returns `INVALID_ARGUMENTS` without handler execution. |
| 45.4 | done | `docs/plans/todo-45.4-event-kernel-quality-boundaries.md` | Close reviewed configuration, composed-schema fallback, mutation isolation, registry encapsulation, and payload-serialization gaps. | EventAgent config, mutation isolation, registry encapsulation, and strict JSON payload failures are covered. |
| 45.5 | done | `docs/plans/todo-45.5-composed-schema-and-copy-failures.md` | Prevent unrelated composed-schema branches from triggering fallback and normalize argument snapshot failures without exposing validator internals. | Branch-aware composed validation and immutable validation summaries pass direct reproductions. |
| 45.6 | done | `docs/plans/todo-45.6-mixed-validation-and-handler-snapshot.md` | Require every validation failure to be missing-only before fallback and contain arbitrary handler payload serialization exceptions. | Mixed validation skips fallback; arbitrary handler snapshot exceptions become stable `HANDLER_ERROR`. |
| 45.7 | done | `docs/plans/todo-45.7-structured-incomplete-mixed-validation.md` | Prevent an explicit structured `complete=False` flag from bypassing substantive validation failures. | Structured incomplete plus substantive errors skips fallback; bounded final gate APPROVED. |
| 46 | done | `docs/plans/todo-46-configurable-tool-invocation-mode.md` | Add `dual_agent` and `chat_agent_tools` runtime modes on the shared event kernel. | Both modes share registry/kernel/results while preserving mode-specific protocol and valid transcripts; full suite passes (`217 passed`, one existing warning). |
| 46.1 | done | `docs/plans/todo-46.1-mode-parity-and-duplicate-call-safety.md` | Reject repeated provider call IDs before side effects, align direct multi-call concurrency with dual mode, and enforce the same event budget in both modes. | Duplicate IDs are rejected before side effects; direct batches overlap with stable order; dual/direct budgets are symmetric; final gates pass. |
| 47 | done | `docs/plans/todo-47-built-in-event-plugins.md` | Add terminate-session, device-volume, schedule, and web-search as built-in plugins on the generic event kernel. | Four namespaced plugins use injectable ports/default adapters with no generic name branches; full suite passes (`313 passed`, one existing warning). |
| 47.1 | done | `docs/plans/todo-47.1-plugin-normalization-and-validation.md` | Share plugin normalization across invocation modes and harden negation, numeric, date/timezone, query, and adapter idempotency boundaries. | Direct/dual normalization matches; strict date/timezone/query validation and canonical adapter keys pass final gates. |
| 47.2 | done | `docs/plans/todo-47.2-plugin-token-and-compatibility-boundaries.md` | Reject remaining negated/non-integer volume tokens, canonicalize integral JSON numbers, preserve fallback state, use standard date-time semantics, and restore positional dataclass compatibility. | Named negation/token cases, integral floats, fallback provenance, RFC3339, and positional compatibility pass. |
| 47.3 | done | `docs/plans/todo-47.3-bare-volume-numeric-guard.md` | Apply malformed numeric rejection to the existing bare `volume to`, `volume at`, and `volume=` syntaxes. | Bare decimal/grouped tokens are rejected with no side effect; integer forms remain valid; bounded gate APPROVED. |
| 48 | done | `docs/plans/todo-48-parallel-event-batches.md` | Execute multiple flat events with bounded parallelism, failure isolation, aggregation, and a terminal barrier. | Direct/dual share bounded policy-driven batches with stable order, failure isolation, terminal barrier, and four built-in user flows; full suite passes (`372 passed`, one existing warning). |
| 48.1 | done | `docs/plans/todo-48.1-batch-canonical-replay-and-terminal-safety.md` | Canonicalize batch keys, make replay atomic and bounded, guarantee terminal grace after sibling timeout, enforce async timeout around sync handlers, and ensure termination has a farewell. | Canonical/in-flight replay, terminal grace, sync timeout responsiveness, farewell, and search two-answer regressions pass. |
| 48.2 | done | `docs/plans/todo-48.2-outcome-cache-and-sync-resource-lifecycle.md` | Preserve full replay outcomes, generation-scope cleanup, invalid-key isolation, sync worker resource leases, and deduplicated result correlation/policy cardinality. | Outcome cache, scope invalidation, deferred sync resource leases, correlation, and single policy messages pass. |
| 48.3 | done | `docs/plans/todo-48.3-strict-canonical-types-and-scope-token-cleanup.md` | Align canonical-key equality with strict JSON types and replace retained generation tombstones with unique releasable scope tokens. | Strict nested JSON types and 1000-cycle scope cleanup pass; final bounded gate APPROVED. |
| 49 | done | `docs/plans/todo-49-tool-mode-ui-session-restore.md` | Add UI mode selection, workspace/session restoration, and clear EventAgent applicability feedback. | Static/WebSocket tests prove requests, snapshots, loaded sessions, and audit context preserve the selected mode. |
| 49.1 | done | `docs/plans/todo-49.1-session-mode-and-atomic-transcript-safety.md` | Enforce persisted mode, atomically store direct tool rounds, repair incomplete legacy tails, serialize SQLite migration, and hide empty protocol bubbles. | Mode mismatches are rejected without config overwrite; disconnect cannot leave unresolved tool calls; concurrent migration succeeds; replay shows only visible assistant content. |
| 49.2 | done | `docs/plans/todo-49.2-session-load-race-and-visible-repair.md` | Prevent stale session loads from overwriting the selected session and preserve visible text while stripping incomplete tool protocol. | Out-of-order loads cannot mutate the active session UI; whitespace-only protocol bubbles stay hidden; incomplete tool rounds retain provider-valid visible content. |
| 49.3 | done | `docs/plans/todo-49.3-stale-replay-token-order.md` | Prevent a stale replay invocation from invalidating an already-running replay for the current session. | A late stale invocation exits before advancing the replay token; the current session still restores normally. |
| 50 | done | `docs/plans/todo-50-comparable-model-tool-metrics.md` | Record mode-aware model/tool spans and include EventAgent usage so both architectures can be compared fairly. | Persistence/API tests report agent, call kind, tokens, TTFT, tool latency, fallback usage, and total turn wall time without double counting. |
| 50.1 | done | `docs/plans/todo-50.1-metric-key-migration-dedup.md` | Deduplicate legacy metric keys before creating the idempotency index so existing experiment databases remain openable. | Migration keeps the earliest row for each duplicate non-null session/metric key, creates the unique index, and remains safe under concurrent initialization. |
| 51 | done | `docs/plans/todo-51-comparison-matrix-closeout.md` | Add repeatable comparison fixtures, update project documentation, and close the experimental implementation. | Both modes pass the same 12-run scenario matrix; focused (`231 passed`) and full (`417 passed`) tests, JS syntax, app import, and documentation checks pass. |
| 51.1 | done | `docs/plans/todo-51.1-first-reply-and-protocol-matrix.md` | Require fast visible first replies for event scenarios and prove each mode uses its intended capability protocol surface. | Matrix asserts first reply ordering, no unintended second reply, dual compact event catalog/no provider tools, direct enabled schemas/no generated event catalog, and correct event source. |
| 52 | done | `docs/plans/todo-52-agent-benchmark-runner.md` | Add a configurable in-process benchmark CLI with deterministic mock cases and live OpenAI-compatible execution. | Mock/live runs compare both modes, measure provider/visible TTFT, wall time, tokens and event correctness, write secret-safe JSON/Markdown reports, and use stable exit codes. |
| 52.1 | done | `docs/plans/todo-52.1-benchmark-url-control-characters.md` | Reject non-printable/control characters in benchmark target URLs before constructing the HTTP client. | Strict config tests cover NUL, CR/LF, tabs, and other Unicode/control characters while valid HTTP(S) URLs remain accepted. |
| 52.2 | done | `docs/plans/todo-52.2-benchmark-url-transport-compatibility.md` | Validate benchmark target hostname/URL compatibility with the production HTTP transport at the config boundary. | Invalid IDNA/port/transport URLs are rejected as config errors while valid Unicode hostnames accepted by the transport remain valid. |
| 52.3 | done | `docs/plans/todo-52.3-benchmark-case-mode-single-source.md` | Make benchmark case IDs and invocation modes single-source enums shared by config, catalog, runner, and tests. | Adding or removing an enum member cannot leave config literals, exported choices, and catalog keys silently inconsistent. |
| 52.4 | done | `docs/plans/todo-52.4-benchmark-visible-ttft-and-call-counts.md` | Measure the first non-whitespace visible content and enforce each case's expected ChatAgent/fallback call counts. | Blank deltas cannot reduce visible TTFT; extra or missing model/fallback calls produce semantic failures even when timing and ledger agree. |
| 52.5 | done | `docs/plans/todo-52.5-benchmark-ledger-event-identity.md` | Cross-check detected, batch-result, and tool-metric event identities and preserve attempted model counts on failed runs. | A successful result from the wrong event cannot pass; failed streams still report started ChatAgent/fallback attempts from timing records. |
| 52.6 | done | `docs/plans/todo-52.6-benchmark-report-auditability.md` | Complete report latency coverage, concurrent pair reservation, runner-level error auditability, and byte-bounded errors. | Reports aggregate model/tool latency, concurrent writers cannot mix pairs, catastrophic runner errors appear in report totals/details, zero samples warn, and errors stay within 2 KiB UTF-8. |
| 52.7 | done | `docs/plans/todo-52.7-benchmark-output-reservation-and-cardinality.md` | Prevent report overwrite/stale reservations, suppress argparse value echoes, and reject missing or extra benchmark results. | Final paths are atomically reserved without lock files, malformed CLI values are not echoed, and actual run cardinality must equal cases × modes × iterations. |
| 52.8 | done | `docs/plans/todo-52.8-benchmark-no-overwrite-publication.md` | Publish completed report files with atomic no-overwrite hard links instead of check-then-replace ownership logic. | A destination created at any point wins without being overwritten; the writer retries another suffix or fails cleanly with no mixed pair. |
| 52.9 | done | `docs/plans/todo-52.9-atomic-report-bundles-and-audit-parity.md` | Replace two-path report publication with one atomic bundle boundary and close report/CLI audit parity gaps. | Concurrent writers publish complete bundles without rollback deletion races; Markdown preserves all failure facts and output errors map to exit code 2. |
| 52.10 | done | `docs/plans/todo-52.10-benchmark-bundle-cli-contract.md` | Align CLI report discovery tests with the atomically published bundle layout. | CLI tests consume the reported bundle paths without restoring root-level compatibility copies or weakening redaction, exit-code, and cardinality checks. |
| 52.11 | done | `docs/plans/todo-52.11-bundle-interrupt-and-path-safety.md` | Preserve complete bundles across post-symlink interrupts and reject unsafe report timestamp path components. | Interruptions cannot leave dangling public bundles; explicit timestamps stay inside output_dir; fsync tests verify both files and both directories. |
| 52.12 | done | `docs/plans/todo-52.12-benchmark-metric-integrity-and-parallel-proof.md` | Exclude consumer backpressure from model elapsed, reject missing token usage, and prove parallel handlers overlap. | Model latency measures provider-await time; absent usage cannot appear as zero cost; the parallel case fails unless both handlers start concurrently. |
| 52.13 | done | `docs/plans/todo-52.13-provider-cleanup-exception-priority.md` | Preserve active provider/cancellation exceptions when iterator cleanup also fails. | Provider failures and cancellation retain priority; cleanup failures propagate only when no earlier exception is active; timing attempts are still recorded. |
| 53 | done | `docs/plans/todo-53-professional-debug-console-ui.md` | Redesign the static UI as a professional debug console and make EventPrompt visibility/content follow invocation mode and selected tools. | Final automated gate passes (`617 passed`, one existing warning); JS syntax, diff, import, HTTP asset smoke, and independent reviews pass. Desktop/narrow browser QA was explicitly waived by the user on 2026-07-15. |
| 53.1 | done | `docs/plans/todo-53.1-event-prompt-order-preservation.md` | Preserve the user-selected EventPrompt position while mode/tool refreshes still deduplicate and regenerate its content. | RED: `3 failed, 5 passed`; GREEN: focused `8 passed`, full WebSocket file `84 passed`; Node syntax and diff checks pass; behavior tests cover refresh, mode round trip, restore position, and duplicate cleanup. |
| 53.2 | done | `docs/plans/todo-53.2-console-interaction-state.md` | Make the new collapsible control sections and Audit/Usage drawer operable, persistent, and synchronized with session/mode status. | RED: `6 failed, 9 passed`; GREEN: focused `15 passed`, full WebSocket file `94 passed`; Node/diff checks and independent spec/code-quality reviews pass. |
| 53.3 | done | `docs/plans/todo-53.3-event-prompt-payload-singleton.md` | Enforce the EventPrompt singleton at the outbound payload boundary in both invocation modes, including stale or user-edited generated-signature custom prompts. | RED: `1 failed, 4 passed`; GREEN: focused `5 passed`, full WebSocket file `94 passed`; collector includes managed EventPrompt only in dual mode. |
| 53.4 | done | `docs/plans/todo-53.4-managed-event-prompt-test-identity.md` | Make the payload-singleton regression distinguish the managed EventPrompt from a generated-signature custom impostor. | Focused `1 passed`, full WebSocket file `94 passed`; mutation check proves the test fails if the impostor survives instead of the managed item. |
| 53.5 | done | `docs/plans/todo-53.5-event-prompt-order-independent-identity.md` | Prove EventPrompt payload selection depends on managed prompt identity rather than whether it appears before or after a generated-signature impostor. | Focused `1 passed`, full WebSocket file `94 passed`; both item orderings pass and bounded code-quality review is approved. |
| 53.6 | done | `docs/plans/todo-53.6-browser-visual-qa.md` | Complete desktop and narrow-screen visual/interaction QA before closing Todo 53 and merging locally. | Browser QA was explicitly waived by the user on 2026-07-15 after Chrome extension communication remained unavailable; automated and HTTP verification remain the accepted closeout evidence. |
| 54 | pending | `docs/superpowers/specs/2026-07-15-chat-agent-event-prompt-design.md` | Balance ChatAgent text-event recall and false positives with a decision-oriented EventPrompt while preserving the existing protocol and invocation-mode boundaries. | TDD prompt-contract and compatibility tests pass; focused/full suites, JS syntax, app import, and diff checks pass; live A/B evidence is recorded when a provider target is available. |