Commit Graph
985 Commits
Author SHA1 Message Date
Devika Verma f75fef424a feat(gui): Steps panel in the UX-059 look (OPE-244)
Colours, fonts and layout as the UX-059 mock, light and dark: the step
colour tokens, the time axis with gridlines, and a step's details in a
pane beside the list. The details show a model call's tokens, context,
input and output; a tool's arguments, approval wait and how it was
allowed; a check's questions and the call it judged.

The step endpoint now returns a tool call's arguments, its approval
wait, and for a check the step it judged.
2026-11-02 17:29:42 +05:30
Devika Verma 57589cce14 fix(observability): CI: Steps button class and a title-call race in a server test (OPE-244)
- The Steps button shared the Artifacts button's class, so window-drag.spec's
  `.topbar-artifacts-btn` locator found two buttons. It has its own class now,
  styled the same.
- test_ws_error_persists_notice_and_retry_reruns: the fire-and-forget title call
  could take the one scripted outage meant for the chat call. Title calls are
  answered apart, as test_server already does for the concurrency test.
2026-11-02 14:36:47 +05:30
Devika Verma 0cb2d9fb2b fix(observability): keep build_app's signature; read a saved window after the call (OPE-244)
- Turns left open are closed when the server holds the engine lock, checked
  inside build_app, whose signature stays as it was (test_server stubs it).
- A model step starts with the catalogue's window only; the user's saved size
  or Ollama's num_ctx is filled in when the call ends, so recording never
  delays the request (a title call raced ahead of the main call in
  test_server).
2026-11-02 13:46:11 +05:30
Devika Verma 2293dfcb40 feat(gui): Steps header with mode and stamps, answer link (OPE-244)
- Header: a pill with the approval mode and, in Auto-approve or Shadow, the
  reviewer; a stamp line with machine, sandbox, coworker fingerprint, model
  and provider (UX-059 OB-1, OB-12, OB-14, OB-15).
- The Auto-approve line also gives the checks' time and the reviewer.
- A Steps link under each answer opens the panel at that turn.
2026-11-02 13:32:42 +05:30
Devika Verma 8bf0c8874a fix(gui): Steps panel fixes from the second in-app check (OPE-244)
- Row badges as in the mock: exit code, failed call type, over the context
  limit, no usage, auto-approved, shadow checks, Inbox waits, unknown steps.
- Details show what the recording has: request and response ids, attempts,
  result size, call id, the context's contents, summary tokens, breaker,
  decision-model answers.
- Values in details are words in English and Chinese, not raw codes.
- A session switch opens the newest turn; a narrow rail stacks details.
- Context size shown when the window is not known; a line for steps still
  running when the app stopped.
2026-11-02 12:50:03 +05:30
Devika Verma cc15eff4f7 fix(observability): fixes from the second in-app check (OPE-244)
- Turns left open by a crash or restart are closed at start as unknown, with a
  recording_gap notice (TD-12), only by the process that holds the engine lock.
- Steps closed without their own end keep their kind's fields as "not known";
  interactive tools get an empty decision path.
- A Stop at a card, or one that kills a running command, is interrupted, not
  denied or ok.
- The skills menu is the one the turn offered; a skill turned off leaves it.
- Model steps carry the window the engine compacts against (saved size,
  Ollama num_ctx), so local models show the context.
- Decision-model checks record each question's answer; a session grant set
  aside in Auto-approve is in the decision path.
2026-11-02 12:50:02 +05:30
Devika Verma be474879b8 fix(gui): Steps panel fixes from the in-app check (OPE-244)
Found by running the panel on real turns:
- picking another turn closes the open step's details (they showed the
  old turn's step, with its start measured from the new turn);
- no empty message box under a model call whose reply was only tool calls;
- a duration between 0 and 100 ms reads "<0.1s", not "0.0s";
- a model call's details show the coworker fingerprint, as in OB-2.
2026-11-02 10:59:18 +05:30
Devika Verma ff9b955494 fix(observability): a streamed model step ends as its reply arrives; a turn's end waits for shadow checks (OPE-244)
Two races found by running the schema test repeatedly:

- The streamed view ended its model step only after the engine had read
  the final piece. The engine could add the reply and end the turn first,
  and the turn's end then closed the step as interrupted, without its
  usage or finish reason. The step now ends when the final piece
  arrives, before the engine sees it.
- A shadow check runs in the background and can outlast the turn's last
  event. The turn's end is now recorded with the time of its ending
  event but sent once running shadow checks finish (at most 30 s), so
  their steps are not closed as interrupted while they run.

Also: a server test's fake provider answers the session title apart, so
the title call can no longer take the turn's only reply.
2026-11-02 10:50:08 +05:30
Devika Verma 3b9e0d46df test(observability): the shared schema copy is recording format 1.1 (OPE-244) 2026-11-02 10:41:15 +05:30
Devika Verma 158c4bb004 fix(observability): recordings fit the shared schema; test the engine's own recordings against it (OPE-244)
A new test runs representative engine turns (approval cards, session
grants, a summary, live and shadow auto-approver checks, the explore
helper, context steps, notices and sandbox facts) and validates each
recording against recording-format.schema.json, copied from ocw-context
next to the golden test. It found three differences, now fixed:

- blocked sites are {host, port, ...}, not {site, ...};
- the context step's folders and skills_menu are counts, never null,
  and skills_hash is the short code of the session's skill names;
- a step with no session or no turn records null, not an empty string.
2026-11-02 10:39:05 +05:30
Devika Verma a6d7ebdaec feat(gui): Steps panel with the timeline, step details and session usage (OPE-244)
Phase 1 screens from UX-059 (OB-1 steps timeline, OB-2 step details,
OB-4 session usage), reading the engine's recording endpoints.

- A Steps button in the session header opens the panel in the right
  rail's full-view slot. Turn picker; tiles for Total and every time
  bucket that is not zero, plus Other when it is 1% or more; the
  auto-approve line; every step of the turn on one time axis, nested
  steps (helper calls, a check's model call) under their parent.
- Clicking a row shows its details: status, timing, model and provider,
  first reply time, finish reason, tokens split by type (a count not
  reported shows as a dash, never 0), the decision path and who decided,
  the transcript message, and the exact request and response.
- The Usage tab: input, output and cache share, the at-least and
  failed or over-limit lines, by purpose, by model (in, cache, out) and
  context now. /usage gains the per-model parts and totals for it.
- The panel refreshes on live step events and at a turn's end.

The Issues tab (OB-3) is Phase 2.
2026-11-02 09:51:10 +05:30
Devika Verma ed34b59e13 test: the server's provider is the router wrapped for recording (OPE-244) 2026-11-02 09:45:08 +05:30
Devika Verma 4dc6dbad44 feat(observability): read endpoints, screen numbers and live step messages (OPE-244)
Phase 1 read side (ocw-context docs/observability/phase-1/technical-design.md
§6.3, §7.1, §12).

- coworker/observability/calculator.py: the token pill, the "at least"
  marker, failed and over-limit calls, by purpose and model, cache share,
  and each turn's time buckets. The shared golden test now also checks
  expected-numbers.json: 30 of 30.
- GET /v1/sessions/{id}/turns (turns with stamp, buckets and usage),
  /turns/{turn_id}/steps (a light list in canonical order),
  /steps/{step_id} (one step in full: content, the exchange rebuilt from
  its pieces, the transcript message it points at cut at 4 KB, its audit
  rows and child steps) and /usage (the session's numbers and context
  fill). A session recorded before Phase 1 answers recorded: false.
- While a turn runs, the recording events go to the session's sockets as
  {"type": "step", "events": [...]}, batched every 100 ms.

Not yet: sending an explore helper's steps only when its step ends, and
computing /usage from the store's columns instead of the loaded recording.
2026-11-02 09:17:42 +05:30
Devika Verma d57db12942 feat(observability): decision-model reviewer checks get a model step with usage (OPE-244)
Phase 1 engine item E23 (ocw-context
docs/observability/phase-1/technical-design.md §5.5, §8.1, TD-16).

OpenAI Decisions and TypeSafe Jev call their own service, not the
provider router. DecisionReviewer.review takes the check's view and
records the request through ProviderView.record_call: a model step
nested in the auto-approver check, purpose auto_approver, provider
openai_decisions or typesafe_jev, with the exchange, provider_meta and
provider_facts from the HTTP capture, and usage read from the service's
reply (the shared usage vectors for both services pass).

Not yet: the per-question answers in the check's content, and score and
cutoff.
2026-11-02 09:13:37 +05:30
Devika Verma e0a6400a4e feat(observability): turn stamps, coworker fingerprint, context step, notices and sandbox facts (OPE-244)
Phase 1 engine items E15a, E16, E5 and E13 (ocw-context
docs/observability/phase-1/technical-design.md §5.6, §5.8, §9).

E15a: every turn's stamp has the machine (this machine, own machine or
cloud, from remote.json; id, name, app version, never 0.0.0), the model
and its provider, and the sandbox (provider, enforcement, profile).
E16: the session build computes the coworker fingerprint from its id,
its instructions and its own skill files; it is on every turn's stamp.
E5: a context step at the turn's first model call: session prompt hash,
per-turn block size and hash, mode note, folders, and on the session's
first turn the memories, memory mode, rules and AGENTS.md counts. A
change of the per-turn block mid-turn is a context_changed notice.
Error, interrupted, reviewer_paused, step_limit and truncated are
zero-length notice steps.
E13: network_note keeps per-site counts, first times and the late flag
(V-04) in a private key the engine takes out of the result before the
model sees it; the tool step gets attrs.sandbox (blocked_known,
blocked_count) and the sites in content.

Known gaps: skills_menu and skills_hash are not read yet, and the
fingerprint hashes the coworker's instructions text rather than its
manifest file.
2026-11-02 09:02:46 +05:30
Devika Verma 075c80f9d1 feat(observability): auto-approver checks and explore helper calls as nested steps (OPE-244)
Phase 1 engine items E12 and E6 (ocw-context
docs/observability/phase-1/technical-design.md §5.3, §5.5, §8.2).

E12: each auto-approver check (pre-consulted batch, single, delegated and
shadow) is its own step, named after the tool and linked to the call by
call_id, with the reviewer's model call nested inside through a view
whose parent is the check. Attrs: mode, result (allow, deny, unsure,
could_not_run, context_changed), reviewer kind and model,
usage_reported, the breaker for live checks, and matched_user for shadow
checks, filled when you answer. The reason goes in content.
Reviewer.review takes an optional view for this.

E6: a running tool can read its own step, turn and the engine's view.
The explore helper tags its child engine's provider with purpose
helper, parented to the explore step on the parent's turn, and records
its tool steps there with decision {helper: true}; the helper's own run
is not recorded as a turn.
2026-11-02 08:56:09 +05:30
Devika Verma 5eed698c65 feat(observability): wait steps, summary steps and each tool call's decision path (OPE-244)
Phase 1 engine items E20 and E4 (ocw-context
docs/observability/phase-1/technical-design.md §5.4, §5.7, §8.3).

E20: every human wait (approval card, question, plan, team, items,
connector, tool install, folder) is a wait step from the moment the card
is shown to the answer, linked to its tool call, with kind, attended,
where (session or inbox, reported by the Inbox when the card is added or
moved there) and outcome; who answered goes in content. The summary's
"Retry or trim?" question is a wait nested under the summary step.

E4: a summary or trim is a summary step, written only if one happened,
with its model calls nested inside, reason, tokens_before, and
tokens_after from the next main call. Each tool call that went through
_authorize carries attrs.decision = {path, origin}: permission, grant,
auto_approver, card and resolved stages with ids from fixed lists.

Also: every recordings store now shares one writer thread, held weakly,
instead of one thread per store that never exited.
2026-11-02 08:45:40 +05:30
Devika Verma 1e010d1996 feat(observability): every model call is a model step with its exact exchange and correct token counts (OPE-244)
Phase 1 engine items E2, E22 and E3 (ocw-context
docs/observability/phase-1/technical-design.md §3.3, §5.2, §5.2.1, §6).

E2: the provider router is wrapped once in a RecordingProvider; each
caller holds a tagged view (main in the engine, summary, auto_approver,
title, proxy). Each call is a model step with purpose, provider, model,
tool count and hash, time to first streamed piece, finish reason and
usage. A main call's step points at the reply message's mid; a title
tagged with a turn that already ended is after_turn; an untagged call is
recorded as unattributed. Errors get error.type from the root cause.

E22: requests are captured below the SDKs, at httpx's HTTPTransport,
only while a recorded call is reading on its own thread. Each step keeps
the exact exchange (request as a manifest of SHA-256 pieces, response
body as one piece), provider_meta without content or secrets, and
provider_facts with fixed names.

E3: TokenUsage carries reasoning and whether cache counts were sent, so
a count not sent is recorded as unknown, never 0. Cache writes are read
where sent and taken out of fresh input on OpenAI-style wires; Ollama's
cached prompt count is used; Anthropic streams take the final
message_delta totals. The shared usage vectors pass through each
provider's own code.

Also fixes the store's usage_reported column for usage {"reported": false}.
2026-11-02 08:30:49 +05:30
Devika Verma 22e8c889c0 fix(observability): time steps with perf_counter, which ticks every millisecond on Windows (OPE-244)
time.monotonic ticks every 15.6 ms on Windows, so a short tool step was
recorded as 0 or 16 ms. perf_counter is monotonic too and has
millisecond resolution everywhere. Found in the manual test.
2026-11-02 07:40:14 +05:30
Devika Verma a08e856a5f feat(observability): the engine records turns and tool steps (OPE-244)
Phase 1 engine item E1 (ocw-context docs/observability/phase-1/
technical-design.md §4, §5.3, §10).

- run, retry and resume send turn_started at TURN_START and turn_ended
  at TURN_END, INTERRUPTED or ERROR; a turn that ends with none of
  these (an abandoned generator, a resume stopped mid-tools) is closed
  as interrupted after Stop, else unknown. A retry's start waits for
  the first message it adds, so it can carry that message's mid.
- Callers pass trigger= (user, channel, schedule, team_wake); anything
  that does not say is recorded as unknown.
- Every call that runs is a tool step from _execute_sync to its raw
  result, with its call id, position in the reply, result message mid,
  risk class, result size and exit code. A call that never ran is a
  zero-length step with its status (error, denied, interrupted,
  skipped).
- While recording, UI events carry turn_id and ts_ms, and tool events
  their tool_call_id and step_id. Six TOOL_FINISHED events and both
  TOOL_STARTED events now carry tool_call_id.
- The server gives every engine it builds its recorder, so real turns
  are saved in recordings.db.
2026-11-01 13:10:13 +05:30
Devika Verma e51bc1cc23 feat(observability): recorder, recordings.db store and stable message ids (OPE-244)
Phase 1 of agent observability, engine items E7 and E21
(ocw-context docs/observability/phase-1/technical-design.md v1.0).

E7: coworker/observability/recorder.py is the one sink for the five
recording events. It folds them into turns and steps by recording
format 1.0 and keeps the canonical step order. coworker/observability/
store.py saves them in recordings.db next to coworker.db: pending
writes are merged by id and written by one background thread, so a
turn never waits and nothing is dropped. A daily sweep deletes
recordings older than 30 days in small batches, and deleting a session
deletes its recordings and the exchange pieces only it used.

E21: every message appended or inserted into the engine's history gets
a `mid` (a ULID) through one _add_message() helper. `mid` is a sidecar
like `ts`: stripped before any provider sees it. Older transcripts
without mids keep working.

The shared golden test (30 scenarios, copied into tests/corpora/
observability) passes 30 of 30, folded in memory and read back from
recordings.db.
2026-11-01 12:08:27 +05:30
Rohit Prasad bea25db6f2 Merge pull request #758 from andrewyng/issue/ope-225-reviewer-eval-common-schema
chore(eval): unify Auto-approve reviewer eval corpora on one schema, drop run reports (OPE-225)
2026-10-31 11:11:17 -07:00
Rohit Prasad 84ea3baaeb Merge pull request #759 from andrewyng/issue/ope-224-auto-approve-decision-reviewers
feat(auto-approve): OpenAI Decisions and TypeSafe Jev as Auto-approve reviewer choices (OPE-224)
2026-10-31 11:11:08 -07:00
Rohit Prasad e29dfcb46f Merge pull request #814 from andrewyng/issue/ope-234-readonly-commands-auto-approve
feat(auto-approve): read-only shell commands run without a reviewer call on macOS/Linux (OPE-234)
2026-10-31 11:08:55 -07:00
Rohit Prasad 99e6ff4c78 Merge pull request #813 from andrewyng/issue/ope-237-plan-approval-auto-approve
feat(auto-approve): an approved plan is evidence for exactly its steps (OPE-237)
2026-10-31 11:08:50 -07:00
Rohit Prasad 4266383127 Merge pull request #812 from andrewyng/issue/ope-238-changes-without-asking-summary
feat(gui): show the changes auto-approve made, at the end of a turn (OPE-238)
2026-10-31 11:08:45 -07:00
Rohit Prasad 8bab603c4e Merge pull request #811 from andrewyng/issue/ope-236-secrets-egress-floor
feat(permissions): secret-looking data leaving the machine always needs a person (OPE-236)
2026-10-31 11:08:40 -07:00
Rohit Prasad 8924a548d7 Merge pull request #810 from andrewyng/issue/ope-235-reviewer-computed-facts
feat(reviewer): facts computed by code reach the Auto-Approve reviewer (OPE-235)
2026-10-31 11:08:35 -07:00
Rohit Prasad afb91cf049 Merge pull request #809 from andrewyng/issue/ope-233-inert-reversible-writes
feat(auto-approve): inert, reversible writes inside the workspace run without a reviewer call (OPE-233)
2026-10-31 11:08:30 -07:00
Rohit Prasad 68f3990d7d Merge pull request #808 from andrewyng/issue/ope-231-protected-paths-case-and-list
fix(permissions): protected in-project files match any letter case and cover more auto-running files (OPE-231)
2026-10-31 11:08:25 -07:00
Rohit Prasad 737e1c00ca Merge pull request #806 from andrewyng/issue/ope-232-readonly-shell-aware
fix(permissions): the read-only session grant knows its shell and fails closed (OPE-232)
2026-10-31 11:08:20 -07:00
Rohit Prasad ba549ef7d6 Merge pull request #772 from andrewyng/issue/ope-228-headless-runner-mcp
run: attach MCP servers via --mcp / --mcp-config (OPE-228)
2026-10-31 11:08:15 -07:00
Rohit Prasad 431d307036 Merge pull request #770 from andrewyng/issue/ope-227-shell-task-wait
shell_task_output: wait_seconds, so an agent can wait for a background task instead of polling it (OPE-227)
2026-10-31 11:08:11 -07:00
Rohit Prasad 8b66151ddd Merge pull request #818 from andrewyng/issue/ope-243-transcript-save-mid-history
fix(sessions): a change in the middle of a session's history is saved, not lost or repeated (OPE-243)
2026-10-31 11:07:42 -07:00
Devika Verma 9368a47b42 fix(sessions): a change in the middle of a session's history is saved, not lost or repeated (OPE-243)
ConversationStore.save() appended messages[existing:] by count, so a repair
in the middle of the history (TurnEngine._repair_dangling_tool_calls, or
load()'s _repair_tool_pairing) was never written and the message after it was
written twice, again on every reopen-and-save.

* save() appends only when the part of the file already written still matches
  the start of the history; otherwise it rewrites the file atomically
  (temporary file, then replace).
* The match is checked by message identity against the list last saved or
  loaded for the session, falling back to comparing the file's lines. load()
  records the list only when its repair changed nothing; delete() forgets it.
* tests/test_conversation_save_mid_change.py: load repair then save and
  reload, a mid-history insert, restart mid-approval then a mode notice then a
  new turn, and a plain append that stays an append.
2026-10-31 08:33:33 +05:30
Devika Verma 8de76c5cd6 Merge remote-tracking branch 'origin/main' into issue/ope-227-shell-task-wait 2026-10-29 20:12:08 +05:30
Devika Verma c6d75b4f08 test_shell: capped-wait test uses a silent command, so only the exit can end the wait
The test started an echo in the background and expected a huge wait to
come back with the task exited. The wait also returns on new output, and
the echo's line can arrive a moment before the process exits, so under
load the wait returned "running" (reproduced: 3 of 300 runs on a loaded
machine; 0 of 600 with this change).
2026-10-29 19:55:41 +05:30
Devika Verma c628ea93b5 chore(eval): one common schema for every reviewer corpus, owner-ruling re-keys and sealed fresh rows, old run reports out of the repo (OPE-225)
Restacked onto the OPE-231..238 stack and OPE-224:
- Test rows keep their hand-written source label as report-only data; the reviewer is never shown it (main had started rendering it into the prompt). The reviewer is tested with what production gives it.
- Rows may carry the engine's fact lines (facts, OPE-235/OPE-237), checked against review_facts.FACT_VOCABULARY.
- The seven plan rows added on main as review-122..128 keep their content and become review-284..290, after this change's rows, so the sealed holdout ids stay stable.
- Six layered rows the new secrets floor sends to a person are labelled human_only and left out of the score (review-066, 077, 091, 122, 159, 218); danger-022 stays out of the legacy corpus as on main.
2026-10-29 16:54:24 +05:30
Devika Verma add11a4ed3 feat(auto-approve): decision reviewers take the engine's facts; an approved plan step counts as asked for (OPE-224)
Jev and OpenAI Decisions now accept the same fact lines the session-model reviewer gets (OPE-235, OPE-237). They are used in code, not added to what the model reads, so the measured answers stay as they were. A plan step the user approved sets 'requested' to 1.0, with the model's own answer kept for the audit log; every other rule still applies, so a stop signal on a planned step gives a card. The other facts are accepted and not used yet.

The agent-made-file check now reads only the engine's own line ('<path> was created|downloaded by the agent ...'); any other text in that slot, such as an eval harness's corpus label, no longer marks every action as running an agent-made file.
2026-10-29 16:46:22 +05:30
Devika Verma 5b11e633ef feat(auto-approve): Jev's reworked question set with a card-only named-item/place net (OPE-224)
Jev now asks 29 questions: wrong target and wrong place asked directly and gated on whether the user named one; 'requested' counts the look-ups a task needs; 'contrary' is split into 'did the user set a limit' x 'does this break it'; a new 'deletes something the user did not name' ask signal; a stop signal on a read under a request that hands the task to a file, message or list is a card instead of a block; and the earlier named-item/place questions stay as a net that turns an allow into a card. The allow line moves from 0.90 to 0.80.

Measured outside the repo on the same rows for the old and new sets: AgentDojo normal calls allowed 65 -> 147 of 263 and attacks let through 1 -> 0; InjecAgent unchanged (0 misses); our 128 sealed rows and 40 fresh blind rows let through the same mistakes as before. The product code reproduces the tested variant's verdicts on all 3,067 saved answers. Decisions is unchanged apart from the card rule.
2026-10-29 16:37:19 +05:30
Devika Verma df25480d10 fix(auto-approve): the decision reviewer's state limit fits Jev's 32k per-question limit (OPE-224)
The limit assumed 4 characters per token, so 120,000 characters was about 36,000 tokens at the 3.3 characters per token measured on Jev traffic, over Jev's documented 32k for the state plus one question. It now assumes 3 characters per token: 90,000 characters. An oversized state still fails closed to a card before any vendor call; a test pins both.
2026-10-29 16:37:19 +05:30
Devika Verma d1e1f3a93b fix(auto-approve): a decision reviewer's stop signal on an action the user asked for shows a card instead of blocking (OPE-224)
When Jev or Decisions say both "the user asked for this kind of action" (requested >= 0.50) and "this looks wrong" (a stop signal), the answers contradict each other, so the person decides on a card. A stop signal still blocks when requested is below 0.50. Re-scored from saved answers on AgentDojo: wrong blocks on normal calls 64 -> 40 (Decisions) and 70 -> 29 (Jev), with no new allow on any attack row or sealed row.
2026-10-29 16:37:18 +05:30
Devika Verma db99f675bf fix(auto-approve): shadow evaluation and the reviewer sit at the same level as Auto-approve, since neither depends on it (OPE-224) 2026-10-29 16:37:18 +05:30
Devika Verma c4f75a2740 fix(auto-approve): reviewer before shadow evaluation in Settings, drop the '(for measuring)' note (OPE-224) 2026-10-29 16:37:18 +05:30
Devika Verma 90cf2d2745 fix(auto-approve): shadow export shows progress and the save time, check/checks plural (OPE-224) 2026-10-29 16:37:18 +05:30
Devika Verma cd63cbab05 feat(auto-approve): shadow results summary for the chosen reviewer, with a readable CSV export (OPE-224) 2026-10-29 16:37:18 +05:30
Devika Verma 5d4a57b05e feat(auto-approve): the reviewer is a dropdown, shown only when Auto-approve or shadow evaluation is on (OPE-224) 2026-10-29 16:37:18 +05:30
Devika Verma 0e23ae1015 fix(reviewer): drop the one-meaning clause from Rule 1b; the session model already handled it and the clause caused side effects (OPE-224) 2026-10-29 16:37:18 +05:30
Devika Verma 4e4f1d6a7c fix(reviewer): the hour rule covers the hour only, a one-meaning target is judged from the words alone; pin Jev to jev-1.13.0 (OPE-224) 2026-10-29 16:37:18 +05:30
Devika Verma 35ccbc87b5 fix(reviewer): a one-meaning description pins the target, an agent-chosen hour is asked; Jev counts rule-picked items as chosen (OPE-224) 2026-10-29 16:37:18 +05:30