Say only what the code knows: neutral cause sentences, exact-name dedupe

Roast round 1: four cause sentences claimed more than the record proves —
"too few reviewers could be read" is false when the reviewers were read and
the cycle cap refused the re-authored answer; "failed before any reviewer
answered", "after it was reviewed" and "the review was skipped" likewise.
They now state the cause neutrally. The X › X dedupe compares the two names
exactly (a prefix rule folded "Art" into "Arthur"). The JS test that parsed
the Python table with a regex was a second SSOT parser and is gone; the
shared parity fixture is the pin. The long-work sentence says "one message
saying what I will check and why"; the promote description names the queue
slot, admission and reviews an independent task gets; send_user_message says
"card". Outcome honesty is shorter than the original (prompts/SYSTEM.md
24391 -> 24289 bytes). The configuration chapter no longer says direct turns
are not named.

Co-authored-by: Ouroboros <311266734+ouroboros-agent@users.noreply.github.com>

docs/architecture/07-configuration.md

@@ -85,7 +85,7 @@ A registry of `config.SETTINGS_DEFAULTS` (exact defaults stay canonical in `conf
 | OUROBOROS_MODEL_MAX_CONCURRENCY | 3 | Per-(model,route) concurrent provider-call cap (`model_concurrency.py`) |
 | OUROBOROS_MODEL_SLOT_MAX_WAIT_SEC | 180 | Concurrency-slot wait bound |
 | OUROBOROS_PROJECT_NAMING_TIMEOUT_SEC | 60 | Project-naming call ceiling |
-| OUROBOROS_PROJECT_NAMING_ASYNC_TIMEOUT_SEC | 8 | Bound of the inline naming call when a card is turned into a project (`gateway/projects.py`); direct turns are not named in the background |
+| OUROBOROS_PROJECT_NAMING_ASYNC_TIMEOUT_SEC | 8 | Bound of the inline naming call when a card is turned into a project (`gateway/projects.py`); a direct Main turn is named in the background once it starts working (`spawn_turn_namer`, bounded by `OUROBOROS_PROJECT_NAMING_TIMEOUT_SEC` + 30 s) |
 | OUROBOROS_UPDATE_LETTER_TIMEOUT_SEC | 120 | Update-letter LIGHT one-shot ceiling, slot wait and provider call together (`update_letter.py`) |
 | OUROBOROS_FALLBACK_COOLDOWN_ENABLED | true | 429-aware per-process model cooldown |
 | OUROBOROS_FALLBACK_COOLDOWN_SEC | 120 | Cooldown window |

ouroboros/project_dialogue.py

@@ -543,8 +543,8 @@ TASK_CAUSE_PHRASES = {
     # Acceptance-decision reasons. An accepted decision renders no clause at
     # all, so clean_pass and clean_pass_obligations_closed carry no sentence.
     "author_finish": "The answer was delivered on Main's own judgement; the reviewers had not signed it off.",
-    "review_degraded": "Not enough reviewer verdicts could be read to settle the answer.",
-    "infra_failure": "The review could not run: it failed before any reviewer answered.",
+    "review_degraded": "No reviewer verdict was established for this answer.",
+    "infra_failure": "A review infrastructure failure prevented a settled verdict.",
     "dialogue_terminal": "The reviewers and Main could not agree, and both positions were kept.",
     "improvement_capsule": "The reviewers asked for one more pass and Main was given their notes.",
     "fence_reopen_failed": "The requested extra pass could not be started, so the answer stands as it was.",
@@ -556,11 +556,11 @@ TASK_CAUSE_PHRASES = {
     "no_actionable_changes": "The re-review was not clean and suggested nothing to change.",
     "identical_acceptance_refused": "Nothing had changed since the last review, so the recorded verdict stands.",
     "review_skipped_deadline_reserve": "There was not enough time left to review the answer.",
-    "delivery_binding_superseded": "The answer changed after it was reviewed, so the review no longer covered it.",
+    "delivery_binding_superseded": "The answer or its evidence changed, so the earlier review no longer covered it.",
     "owner_followup": "A new message from you arrived, so the review was set aside for it.",
     "evidence_refresh": "The work changed after the review was frozen, so it no longer covered the answer.",
     "revision_unavailable_on_forced_rail": "The task had to stop, so the requested rework never happened.",
-    "owner_hurry": "You asked me to hurry, so the review was skipped.",
+    "owner_hurry": "You asked me to hurry, so no further review was started.",
     "unspecified": "The answer was not signed off, and no cause was recorded.",
     # The rail that ended the task before an owed acceptance panel could run.
     "acceptance_bypassed_budget_exhausted": "The task ran out of budget before the answer could be reviewed.",

ouroboros/projects_registry.py

@@ -831,11 +831,11 @@ def task_presentation_snapshot(drive_root: Any, task_id: str, *, task: Any = Non
             break
     task_name = task_name or "Task"
     label = f"{pname} › {task_name}" if pname else task_name
-    # One name, said once: a task whose own name IS the project name (or its
-    # opening words) renders "Launch › Launch" / "Launch › Launch release",
-    # which reads as two different things. Keep the longer half alone.
-    if pname and (task_name.startswith(pname) or pname.startswith(task_name)):
-        label = task_name if len(task_name) >= len(pname) else pname
+    # One name, said once: a task whose own name IS the project name renders
+    # "Launch › Launch", which reads as two different things. Exact equality
+    # only — a prefix rule would fold "Art" into "Arthur".
+    if pname and task_name == pname:
+        label = task_name
     return {"project_id": pid, "project_name": pname, "task_id": tid,
             "project_routable": registered, "task_name": task_name,
             "target_label": label}

ouroboros/tools/control.py

@@ -102,10 +102,10 @@ log = logging.getLogger(__name__)
 # 300-line function gate; v6.70.0 added the ground-truth-probe contract).
 _PROMOTE_CHAT_DESCRIPTION = (
     "Promote real work out of this conversation into a supervised pooled task "
-    "while the conversation remains available. This conversation keeps its own "
-    "tools, files and multi-step work; promote when the work is better as an "
-    "independent task — its own card, queue slot, admission and reviews, steerable "
-    "from chat — or when the owner asked for a task or a project. "
+    "while the conversation remains available. Tools, files and several steps can "
+    "stay in the conversation; promote when independent work is useful — its own "
+    "queue slot, admission and reviews, steerable from chat — or when the owner "
+    "explicitly asks for a separate task. "
     "Before framing the objective around an EXISTING artifact "
     "('check/fix/extend the X skill/file'), ground-truth its existence with one cheap probe "
     "first (skills: list_skills; files: list_files) — memory of past work is not evidence "
@@ -341,7 +341,7 @@ def get_tools() -> List[ToolEntry]:
                            "line of longer work (what I am about to do and why), or a mid-work "
                            "insight, a question, or an invitation to collaborate. It appears in "
                            "the conversation as a normal reply and leaves the work running; later "
-                           "progress stays in the activity block and the final answer is delivered "
+                           "progress stays in the card and the final answer is delivered "
                            "automatically.",
             "parameters": {"type": "object", "properties": {
                 "text": {"type": "string", "description": "Message text"},

prompts/SYSTEM.md

@@ -225,11 +225,11 @@ need it.
   broad fallbacks, silent catches, or shims lacking a concrete reachable
   failure mode. Mid-task I ask: am I solving the class or patching symptoms, am
   I adding surface area, am I still within my human's stated scope?
-- For long work, my first line to my human is what I am about to do and why,
-  while the work continues; later progress is concise — what I learned and
-  the next step — explaining the thought, not narrating tool calls. After a
-  repeatable workflow I capture the recipe: trigger, authoritative files and
-  logs, commands, validation, known false leads.
+- Before long work I send my human one message saying what I will check and
+  why; progress after that is concise — what I learned and the next step —
+  explaining the thought, not narrating tool calls. After a repeatable
+  workflow I capture the recipe: trigger, authoritative files and logs,
+  commands, validation, known false leads.
 - `task_acceptance_review` can nominate my complete task result for review.
   After the whole tool-result block, the host advances the same operation as
   final delivery; checking an intermediate artifact is not whole-task acceptance.
@@ -239,16 +239,14 @@ need it.
 
 ### Outcome honesty
 
-Every task ends in one of three honest states, and I say which one plainly.
-Either I solved it and verified that against the task's own surface; or I got
-part of the way and hand over the real partial result with the unverified and
-incomplete parts marked; or something blocked me, and I say what it was, show
-the exact evidence, and name the next action someone could take. When a
-deadline, a budget or a round limit forces me to finish, I extract the best
-verified result I have and mark the gaps. Handing over an honest partial result
-is an expected ending, not a failure; returning nothing is the only real failure
-mode. I never claim more than I verified: calling something solved without
-checking it is worse than admitting it is partial.
+Every task ends in one of three honest states, and I say which plainly:
+solved and verified against the task's own surface; partly done, with the
+real partial result handed over and its unverified or missing parts marked;
+or blocked, with what blocked me, the exact evidence and the next action
+someone could take. When a deadline, budget or round limit forces me to
+finish, I extract the best verified result I have and mark the gaps. An
+honest partial result is an expected ending; returning nothing is the only
+real failure mode. I never claim more than I verified.
 
 ## Capability Acquisition
 

tests/test_project_plain_rows.py

@@ -504,7 +504,7 @@ def test_host_verdict_leads_both_lifecycle_rows(tmp_path, monkeypatch):
     ) is True
     assert queued[0]["text"] == (
         "Launch 🚀 › Ship release · Done with warnings\n"
-        "Not enough reviewer verdicts could be read to settle the answer. "
+        "No reviewer verdict was established for this answer. "
         "Open the Project for details."
     )
     assert "final_message" not in queued[0]["text"]
@@ -533,7 +533,7 @@ def test_host_verdict_leads_both_lifecycle_rows(tmp_path, monkeypatch):
     projection = next(row for row in rows if row.get("summary_kind") == "terminal_root_projection")
     assert projection["text"] == (
         "Done with warnings. Root task root-project. "
-        "Not enough reviewer verdicts could be read to settle the answer."
+        "No reviewer verdict was established for this answer."
     )
     assert "final_message" not in projection["text"]
     # The room is the project and result_ref is the reader, so neither the id

web/modules/log_events.js

@@ -409,8 +409,8 @@ export function taskStoppedWithSummary(evt) {
 // web/tests/fixtures/outcome_phase_parity.json pins both.
 const TASK_CAUSE_PHRASES = {
     author_finish: "The answer was delivered on Main's own judgement; the reviewers had not signed it off.",
-    review_degraded: "Not enough reviewer verdicts could be read to settle the answer.",
-    infra_failure: "The review could not run: it failed before any reviewer answered.",
+    review_degraded: "No reviewer verdict was established for this answer.",
+    infra_failure: "A review infrastructure failure prevented a settled verdict.",
     dialogue_terminal: "The reviewers and Main could not agree, and both positions were kept.",
     improvement_capsule: "The reviewers asked for one more pass and Main was given their notes.",
     fence_reopen_failed: "The requested extra pass could not be started, so the answer stands as it was.",
@@ -422,11 +422,11 @@ const TASK_CAUSE_PHRASES = {
     no_actionable_changes: "The re-review was not clean and suggested nothing to change.",
     identical_acceptance_refused: "Nothing had changed since the last review, so the recorded verdict stands.",
     review_skipped_deadline_reserve: "There was not enough time left to review the answer.",
-    delivery_binding_superseded: "The answer changed after it was reviewed, so the review no longer covered it.",
+    delivery_binding_superseded: "The answer or its evidence changed, so the earlier review no longer covered it.",
     owner_followup: "A new message from you arrived, so the review was set aside for it.",
     evidence_refresh: "The work changed after the review was frozen, so it no longer covered the answer.",
     revision_unavailable_on_forced_rail: "The task had to stop, so the requested rework never happened.",
-    owner_hurry: "You asked me to hurry, so the review was skipped.",
+    owner_hurry: "You asked me to hurry, so no further review was started.",
     unspecified: "The answer was not signed off, and no cause was recorded.",
     acceptance_bypassed_budget_exhausted: "The task ran out of budget before the answer could be reviewed.",
     acceptance_bypassed_round_limit: "The task hit its round limit before the answer could be reviewed.",

web/tests/fixtures/outcome_phase_parity.json

@@ -111,7 +111,7 @@
       },
       "phase": "warn",
       "headline": "Done with warnings",
-      "acceptance_clause": "Not enough reviewer verdicts could be read to settle the answer."
+      "acceptance_clause": "No reviewer verdict was established for this answer."
     },
     {
       "name": "an accepted decision leaves the execution reason standing",
@@ -211,14 +211,14 @@
       "record": {"status": "completed", "outcome_axes": {"execution": {"status": "ok"}, "review": {"status": "degraded", "acceptance_decision": {"status": "finalized_unaccepted", "reason": "review_degraded"}}}},
       "phase": "warn",
       "headline": "Done with warnings",
-      "acceptance_clause": "Not enough reviewer verdicts could be read to settle the answer."
+      "acceptance_clause": "No reviewer verdict was established for this answer."
     },
     {
       "name": "acceptance reason infra_failure says its own sentence",
       "record": {"status": "completed", "outcome_axes": {"execution": {"status": "ok"}, "review": {"status": "degraded", "acceptance_decision": {"status": "finalized_unaccepted", "reason": "infra_failure"}}}},
       "phase": "warn",
       "headline": "Done with warnings",
-      "acceptance_clause": "The review could not run: it failed before any reviewer answered."
+      "acceptance_clause": "A review infrastructure failure prevented a settled verdict."
     },
     {
       "name": "acceptance reason dialogue_terminal says its own sentence",
@@ -302,7 +302,7 @@
       "record": {"status": "completed", "outcome_axes": {"execution": {"status": "ok"}, "review": {"status": "degraded", "acceptance_decision": {"status": "finalized_unaccepted", "reason": "delivery_binding_superseded"}}}},
       "phase": "warn",
       "headline": "Done with warnings",
-      "acceptance_clause": "The answer changed after it was reviewed, so the review no longer covered it."
+      "acceptance_clause": "The answer or its evidence changed, so the earlier review no longer covered it."
     },
     {
       "name": "acceptance reason owner_followup says its own sentence",
@@ -330,7 +330,7 @@
       "record": {"status": "completed", "outcome_axes": {"execution": {"status": "ok"}, "review": {"status": "degraded", "acceptance_decision": {"status": "finalized_unaccepted", "reason": "owner_hurry"}}}},
       "phase": "warn",
       "headline": "Done with warnings",
-      "acceptance_clause": "You asked me to hurry, so the review was skipped."
+      "acceptance_clause": "You asked me to hurry, so no further review was started."
     },
     {
       "name": "acceptance reason unspecified says its own sentence",

web/tests/reason_detail.test.js

@@ -93,19 +93,6 @@ test('every acceptance reason the host can record has a sentence', () => {
     }
 });
 
-test('the host and the card carry the same cause table', () => {
-    // ONE table, two languages. The fixture pins the sentences a record can
-    // reach; this pins the table itself, so an entry added on one side only
-    // fails here instead of silently drifting.
-    const py = readFileSync(new URL('../../ouroboros/project_dialogue.py', import.meta.url), 'utf8');
-    const block = py.split('TASK_CAUSE_PHRASES = {')[1].split('\n}')[0];
-    const entries = [...block.matchAll(/^ {4}"([a-z_]+)": "((?:[^"\\]|\\.)*)",$/gm)];
-    assert.ok(entries.length >= 30, `expected the host table, saw ${entries.length}`);
-    for (const [, code, sentence] of entries) {
-        assert.equal(taskReasonPhrase(code), sentence, code);
-    }
-});
-
 test('one status-word family: the card phase matches the host over the shared fixture', () => {
     // The same fixture is read by tests/test_project_plain_rows.py, so a
     // divergence between this severity fold and the host's durable label word
@@ -149,7 +136,7 @@ const A4 = {
 test('an unaccepted decision explains the warning in its own words', () => {
     assert.equal(
         taskReasonDetail(A4),
-        'Not enough reviewer verdicts could be read to settle the answer.',
+        'No reviewer verdict was established for this answer.',
     );
     assert.doesNotMatch(taskReasonDetail(A4), /final_message/);
     // The stored reviewer rationale belongs to the card body, the task result

web/tests/task_presentation.test.js

@@ -418,7 +418,7 @@ test('a review-caused warning names the acceptance decision on the card and in L
     const live = summarizeChatLiveEvent(evt);
     const replay = summarizeLogEvent(evt);
     assert.deepEqual({ phase: live.phase, headline: live.headline }, { phase: 'warn', headline: 'Done with warnings' });
-    assert.match(live.body, /Not enough reviewer verdicts could be read to settle the answer\./);
+    assert.match(live.body, /No reviewer verdict was established for this answer\./);
     assert.doesNotMatch(live.body, /final_message/);
     // The raw code lives on in the record half, never in the card body.
     assert.doesNotMatch(live.body, /finalized_unaccepted/);