@windyroad/itil 0.47.11 → 0.47.12-preview.593

package/.claude-plugin/plugin.json

@@ -497,5 +497,5 @@
     }
   },
   "name": "wr-itil",
-  "version": "0.47.11"
+  "version": "0.47.12"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@windyroad/itil",
-  "version": "0.47.11",
+  "version": "0.47.12-preview.593",
   "description": "ITIL-aligned IT service management for Claude Code (problem, and future incident/change skills)",
   "bin": {
     "windyroad-itil": "./bin/install.mjs"

package/skills/manage-problem/SKILL.md

@@ -694,7 +694,7 @@ fi
 
 Detection is intentionally **strict** (explicit label or scoped-npm package only) to avoid prompt fatigue (P063 Direction decision). A passing reference to a bare package name (`gh`, `npm`) does NOT trigger the prompt.
 
-**Already-noted check** — before firing the prompt, grep the ticket for the stable marker `- **Upstream report pending** —` (written by option 2 / the AFK fallback below) or `- **Reported Upstream:**` / a `## Reported Upstream` section (written by `/wr-itil:report-upstream` Step 7 back-write per ADR-024 Confirmation criterion 3a). If any of those are already present, skip the prompt — the detection has already fired on a prior run.
+**Already-noted check** — before firing the prompt, grep the ticket for the stable marker `- **Upstream report pending** --` (canonical ASCII form per P210) or the legacy em-dash variant `- **Upstream report pending** —` (written by option 2 / the AFK fallback below; the grep MUST match BOTH variants for backward compatibility) or `- **Reported Upstream:**` / a `## Reported Upstream` section (written by `/wr-itil:report-upstream` Step 7 back-write per ADR-024 Confirmation criterion 3a). If any of those are already present, skip the prompt — the detection has already fired on a prior run.
 
 **If the detection fires and nothing has been noted yet**, use `AskUserQuestion`:
 
@@ -702,15 +702,15 @@ Detection is intentionally **strict** (explicit label or scoped-npm package only
 - `multiSelect: false`
 - Options:
   1. `Invoke /wr-itil:report-upstream now` — halt the transition; the skill runs (it writes the `## Reported Upstream` appendage per ADR-024 Confirmation criterion 3a); the transition resumes afterwards.
-  2. `Defer and note in ticket` — append a pending-upstream-report line to the ticket's `## Related` section using the stable marker `- **Upstream report pending** — external dependency identified; invoke /wr-itil:report-upstream when ready`. The marker wording is fixed so subsequent runs (and the work-problems `upstream-blocked` skip path) can detect "already noted" without re-firing.
-  3. `Not actually upstream` — proceed without invocation; append the same marker with text `- **Upstream report pending** — false positive; detection misfire` so the prompt does not re-fire on later reviews.
+  2. `Defer and note in ticket` — append a pending-upstream-report line to the ticket's `## Related` section using the stable marker `- **Upstream report pending** -- external dependency identified; invoke /wr-itil:report-upstream when ready`. The marker wording is fixed (ASCII `--` per P210 — ASCII-only in machine-parseable identifiers; em-dash permitted in pure narrative prose) so subsequent runs (and the work-problems `upstream-blocked` skip path) can detect "already noted" without re-firing.
+  3. `Not actually upstream` — proceed without invocation; append the same marker with text `- **Upstream report pending** -- false positive; detection misfire` so the prompt does not re-fire on later reviews.
 
 **Non-interactive (AFK) branch** (per ADR-013 Rule 6 + ADR-024 2026-06-04 (P270) amendment): when `AskUserQuestion` is unavailable, **auto-invoke `/wr-itil:report-upstream`** instead of deferring with the marker. The skill composes the report draft via its own Steps 1–5/4b/5c/6 then scores the drafted prose via the `wr-risk-scorer:external-comms` agent (ADR-028) per the ADR-024 2026-06-04 amendment's orchestrator-side pre-fire gate. Branches:
 
 - **Below external-comms appetite** → the skill proceeds (public-issue path Step 5, comment path Step 5c, or security path Step 6 per the existing classification routing); commits the `## Reported Upstream` back-write per Step 7 / Step 8.
 - **Above appetite** → the skill takes risk-reducing measures (per ADR-042 within-axis precedent generalised to the external-comms risk class — the measures vocabulary is **open-ended LLM judgement** per ADR-024 2026-06-04 second-amendment ratification leaf (a): the `wr-risk-scorer:external-comms` agent's own scoring picks the remedy case-by-case, matching ADR-042's open-vocabulary precedent — NOT a bounded enumeration); re-scores; if within appetite → sends; else → **queues** an `outstanding_questions` entry naming the local ticket ID + queued report path + risk-reduce attempts + residual band + remedy ("review the queued report at `/wr-itil:report-upstream <NNN> <upstream-repo-url>` on return"). The orchestrator continues (P352 queue-and-continue). The `## Queued Upstream Report` section (renamed from `## Drafted Upstream Report` per ADR-024 2026-06-04 second-amendment leaf (c) — same shape; new name reflects the queue-for-review-on-return semantics) carries the report content for the queued question's reference. Security-path routing follows leaf (b) ratification: upstream-with-`SECURITY.md` + below-appetite → file via the declared channel; upstream-without-`SECURITY.md` but with another disclosure channel → external-comms-gated assessment considering impact to (i) our repository, (ii) our reputation, (iii) the party we are reporting to.
 
-The legacy `- **Upstream report pending** —` marker append (the pre-2026-06-04 AFK default) is **superseded** by this auto-invoke branch for all classifications including security. Tickets that already carry the marker from prior sessions are still handled correctly by the work-problems Step 4 classifier — the new path's "already-noted check" matches the legacy marker shape and routes to the report-upstream invocation. The marker shape is retained for backward compatibility on the parking + interactive fallback paths (interactive option 2 still appends it; see options 1/2/3 above).
+The legacy `- **Upstream report pending** --` marker append (canonical ASCII per P210; em-dash variant is the pre-P210 form, still matched for backward compatibility) — the pre-2026-06-04 AFK default — is **superseded** by this auto-invoke branch for all classifications including security. Tickets that already carry the marker from prior sessions (either form) are still handled correctly by the work-problems Step 4 classifier — the new path's "already-noted check" matches both variants and routes to the report-upstream invocation. The marker shape is retained for backward compatibility on the parking + interactive fallback paths (interactive option 2 still appends it; see options 1/2/3 above).
 
 **Scope**: this detection block fires at two points —
 

package/skills/manage-problem/test/manage-problem-external-root-cause-detection.bats

@@ -6,9 +6,12 @@
 #
 # Doc-lint structural test (Permitted Exception per ADR-005) — asserts
 # SKILL.md wording for detection tokens, AskUserQuestion three-option
-# prompt, AFK fallback, and the stable `- **Upstream report pending** —`
-# marker. Mirrors work-problems-release-cadence.bats and
-# report-upstream-contract.bats patterns.
+# prompt, AFK fallback, and the stable `- **Upstream report pending** --`
+# marker (canonical ASCII form per P210; the legacy em-dash variant is
+# still matched by the SKILL's already-noted check for backward
+# compatibility, but is not the canonical-write target). Mirrors
+# work-problems-release-cadence.bats and report-upstream-contract.bats
+# patterns.
 
 setup() {
   REPO_ROOT="$(cd "$(dirname "$BATS_TEST_FILENAME")/../../../../.." && pwd)"
@@ -40,8 +43,17 @@ setup() {
   [ "$status" -eq 0 ]
 }
 
-@test "manage-problem: SKILL.md defines the stable Upstream report pending marker with fixed wording" {
-  run grep -F -- '- **Upstream report pending** — external dependency identified; invoke /wr-itil:report-upstream when ready' "$MP_SKILL"
+@test "manage-problem: SKILL.md defines the stable Upstream report pending marker with fixed wording (canonical ASCII per P210)" {
+  run grep -F -- '- **Upstream report pending** -- external dependency identified; invoke /wr-itil:report-upstream when ready' "$MP_SKILL"
+  [ "$status" -eq 0 ]
+}
+
+@test "manage-problem: SKILL.md still references the legacy em-dash marker variant for backward compatibility (P210)" {
+  # P210: canonical write form is ASCII `--`, but the already-noted
+  # check MUST still match the legacy em-dash variant so tickets
+  # written in prior sessions are detected correctly. Asserts the
+  # legacy form remains documented in the SKILL prose.
+  run grep -F -- '- **Upstream report pending** —' "$MP_SKILL"
   [ "$status" -eq 0 ]
 }
 
@@ -101,7 +113,7 @@ setup() {
   [ "$status" -eq 0 ]
 }
 
-@test "work-problems: uses the same stable marker wording as manage-problem" {
-  run grep -F -- '- **Upstream report pending** — external dependency identified; invoke /wr-itil:report-upstream when ready' "$WP_SKILL"
+@test "work-problems: uses the same stable marker wording as manage-problem (canonical ASCII per P210)" {
+  run grep -F -- '- **Upstream report pending** -- external dependency identified; invoke /wr-itil:report-upstream when ready' "$WP_SKILL"
   [ "$status" -eq 0 ]
 }

package/skills/transition-problem/SKILL.md

@@ -112,21 +112,23 @@ fi
 
 Detection is intentionally **strict** (explicit label or scoped-npm package only) to avoid prompt fatigue (P063 Direction decision). A passing reference to a bare package name (`gh`, `npm`) does NOT trigger the prompt.
 
-**Already-noted check** — before firing the prompt, grep the ticket for the stable marker `- **Upstream report pending** —` (written by option 2 / the AFK fallback below) or `- **Reported Upstream:**` / a `## Reported Upstream` section (written by `/wr-itil:report-upstream` Step 7 back-write per ADR-024 Confirmation criterion 3a). If any of those are already present, skip the prompt — the detection has already fired on a prior run.
+**Already-noted check** — before firing the prompt, grep the ticket for the stable marker `- **Upstream report pending** --` (canonical ASCII form per P210) or the legacy em-dash variant `- **Upstream report pending** —` (written by option 2 / the AFK fallback below; the grep MUST match BOTH variants for backward compatibility) or `- **Reported Upstream:**` / a `## Reported Upstream` section (written by `/wr-itil:report-upstream` Step 7 back-write per ADR-024 Confirmation criterion 3a). If any of those are already present, skip the prompt — the detection has already fired on a prior run.
 
 **If the detection fires and nothing has been noted yet** (per ADR-044 framework-resolution boundary): the agent applies the AFK fallback default WITHOUT firing `AskUserQuestion`. Per ADR-044, this decision IS framework-resolved — the safe action is "defer and note marker", and the user can correct via authentic-correction (ADR-044 category 6) if a manual `/wr-itil:report-upstream` invocation is wanted instead. Per-transition `AskUserQuestion` for upstream-detection is sub-contracting framework-resolved decisions back to the user (lazy deferral per Step 2d Ask Hygiene Pass classification).
 
 **Default behaviour (silent agent action, per ADR-044)**: append the pending-upstream-report line to the ticket's `## Related` section using the stable marker:
 
 ```
-- **Upstream report pending** — external dependency identified; invoke /wr-itil:report-upstream when ready
+- **Upstream report pending** -- external dependency identified; invoke /wr-itil:report-upstream when ready
 ```
 
+ASCII `--` per P210 — ASCII-only in machine-parseable identifiers; em-dash permitted in pure narrative prose. The legacy em-dash variant is matched by the already-noted check for backward compatibility.
+
 The marker wording is fixed so subsequent runs (and the work-problems `upstream-blocked` skip path) can detect "already noted" without re-firing. The transition proceeds normally after the marker is appended.
 
 **Recovery / override paths** (user-initiated, not asked-per-transition):
 
-- If the detection misfired (false positive — not actually upstream), user appends `- **Upstream report pending** — false positive; detection misfire` directly to the ticket's `## Related` section. The next detection-pass observes the marker and skips firing again.
+- If the detection misfired (false positive — not actually upstream), user appends `- **Upstream report pending** -- false positive; detection misfire` directly to the ticket's `## Related` section (ASCII `--` per P210; legacy em-dash variant remains matched for backward compatibility). The next detection-pass observes the marker and skips firing again.
 - If the user wants to invoke `/wr-itil:report-upstream` immediately rather than deferring, they invoke it directly (`/wr-itil:report-upstream <NNN> <upstream-repo-url>`). The skill writes the `## Reported Upstream` appendage per ADR-024.
 
 **AFK and interactive modes use identical behaviour** — the silent-default-with-recovery-path shape is the framework-resolution boundary application; there's no `AskUserQuestion`-vs-fallback differentiation.

package/skills/transition-problems/SKILL.md

@@ -120,12 +120,12 @@ if grep -iE '\b(upstream|third-party|external|vendor)\b|@[[:alnum:]_-]+/[[:alnum
 fi
 ```
 
-**Already-noted check** — before firing, grep for `- **Upstream report pending** —` or `- **Reported Upstream:**` or a `## Reported Upstream` section. If present, skip the prompt for this pair.
+**Already-noted check** — before firing, grep for `- **Upstream report pending** --` (canonical ASCII per P210) or the legacy em-dash variant `- **Upstream report pending** —` (the grep MUST match BOTH variants for backward compatibility) or `- **Reported Upstream:**` or a `## Reported Upstream` section. If present, skip the prompt for this pair.
 
 **Branch on interactivity (per ADR-013 Rule 1 / Rule 6):**
 
 - **Interactive** (`AskUserQuestion` available): use the same three-option prompt the singular's Step 5 documents (invoke /wr-itil:report-upstream / defer-and-note / not-actually-upstream).
-- **AFK / non-interactive** (orchestrator markers — "AFK", "work-problems", "batch-work", "ALL_DONE" — present in the invoking context): default to defer-and-note. Append `- **Upstream report pending** — external dependency identified; invoke /wr-itil:report-upstream when ready` to the ticket's `## Related` section. Do NOT auto-invoke `/wr-itil:report-upstream` (its Step 6 security branch is interactive — per ADR-024).
+- **AFK / non-interactive** (orchestrator markers — "AFK", "work-problems", "batch-work", "ALL_DONE" — present in the invoking context): default to defer-and-note. Append `- **Upstream report pending** -- external dependency identified; invoke /wr-itil:report-upstream when ready` (canonical ASCII per P210) to the ticket's `## Related` section. Do NOT auto-invoke `/wr-itil:report-upstream` (its Step 6 security branch is interactive — per ADR-024).
 
 The detection is per-pair; each Open → Known Error pair runs its own check independently.
 

package/skills/work-problems/SKILL.md

@@ -385,7 +385,7 @@ Read the problem file and apply these deterministic rules:
 | Problem previously attempted twice without progress in this session | **Skip** — mark as stuck, needs interactive attention | user-answerable (direction) |
 | Open problem with outstanding user-answerable design question (naming, direction, pacing, scope) | **Skip** — surface the question at stop (Step 2.5) | user-answerable (design) |
 | Open problem needing architect design judgment (new-ADR-level question) | **Skip** — note the architect-design blocker; Step 2.5 may elevate via a pre-triggered architect call in `--deep-stop` mode | architect-design |
-| Open problem blocked on upstream dependency or Claude Code capability gap | **Auto-invoke `/wr-itil:report-upstream` via the AFK fallback** (per ADR-024 2026-06-04 (P270) amendment — manage-problem Step 6 external-root-cause detection AFK fallback owns the actual invocation; this row routes through it). The report-upstream skill composes the draft then scores the prose via `wr-risk-scorer:external-comms` (ADR-028); below-appetite → sends; above-appetite → risk-reduces (open-ended LLM judgement per ADR-024 2026-06-04 second-amendment leaf (a)) then re-scores → sends-or-queues. Security routing per leaf (b): upstream-with-`SECURITY.md` + below-appetite → files via declared channel; upstream-without-`SECURITY.md` → external-comms-gated impact assessment to (i) our repo, (ii) our reputation, (iii) reported party. Queued reports save to `## Queued Upstream Report` (renamed from `## Drafted Upstream Report` per leaf (c)). Queue does NOT halt — outstanding_question surfaces at Step 2.4 / Step 2.5b end-of-loop per P352. Iter still classifies the ticket as `upstream-blocked` (the local ticket itself is still blocked on the upstream fix) and **skips work on it** after the report-upstream invocation completes — the report-upstream call is the action this row takes; classification stays `upstream-blocked` so Step 4 routes to skip-rather-than-work. Tickets already carrying `- **Upstream report pending** —` from prior sessions are detected via the already-noted check and routed to the report-upstream invocation (the marker shape is retained as the detection substrate per the 2026-06-04 amendment). | upstream-blocked |
+| Open problem blocked on upstream dependency or Claude Code capability gap | **Auto-invoke `/wr-itil:report-upstream` via the AFK fallback** (per ADR-024 2026-06-04 (P270) amendment — manage-problem Step 6 external-root-cause detection AFK fallback owns the actual invocation; this row routes through it). The report-upstream skill composes the draft then scores the prose via `wr-risk-scorer:external-comms` (ADR-028); below-appetite → sends; above-appetite → risk-reduces (open-ended LLM judgement per ADR-024 2026-06-04 second-amendment leaf (a)) then re-scores → sends-or-queues. Security routing per leaf (b): upstream-with-`SECURITY.md` + below-appetite → files via declared channel; upstream-without-`SECURITY.md` → external-comms-gated impact assessment to (i) our repo, (ii) our reputation, (iii) reported party. Queued reports save to `## Queued Upstream Report` (renamed from `## Drafted Upstream Report` per leaf (c)). Queue does NOT halt — outstanding_question surfaces at Step 2.4 / Step 2.5b end-of-loop per P352. Iter still classifies the ticket as `upstream-blocked` (the local ticket itself is still blocked on the upstream fix) and **skips work on it** after the report-upstream invocation completes — the report-upstream call is the action this row takes; classification stays `upstream-blocked` so Step 4 routes to skip-rather-than-work. Tickets already carrying `- **Upstream report pending** --` (or the legacy em-dash variant) from prior sessions are detected via the already-noted check and routed to the report-upstream invocation (the marker shape is retained as the detection substrate per the 2026-06-04 amendment; ASCII `--` is the canonical form per P210, em-dash is the legacy form, both matched). | upstream-blocked |
 
 The default is to work the problem. Only skip when the rule explicitly says so. This is an AFK loop — forward progress matters more than avoiding dead ends, because dead ends are cheap (findings are saved) and interactive input is expensive (user is absent).
 
@@ -393,7 +393,7 @@ The default is to work the problem. Only skip when the rule explicitly says so.
 
 - **user-answerable** — the user can answer directly (verification, naming, direction, pacing, scope). Step 2.5 surfaces these as questions (interactive) or in the Outstanding Design Questions table (non-interactive / AFK).
 - **architect-design** — requires architect judgment first; may escalate to a new ADR. Step 2.5 can optionally pre-trigger the architect agent in `--deep-stop` mode to produce a concrete user-answerable question. Otherwise noted as "pending architect review".
-- **upstream-blocked** — external dependency, Claude Code capability gap, or waiting on third-party fix. Truly terminal for this loop — no user question would change anything. Report the blocker (now via auto-invoke of `/wr-itil:report-upstream`, per ADR-024 2026-06-04 (P270) amendment) and move on. **Before skipping, run the manage-problem external-root-cause detection AFK fallback** (per P063 amended 2026-06-04): the fallback now invokes `/wr-itil:report-upstream` rather than only appending the marker. The report-upstream skill scores the drafted prose via `wr-risk-scorer:external-comms` (ADR-028); below-appetite branches send (public-issue Step 5 / comment Step 5c / security Step 6 per classification); above-appetite branches risk-reduce + re-score; if-still-above queue an `outstanding_questions` entry per P352 queue-and-continue (orchestrator does NOT halt). Existing tickets carrying `- **Upstream report pending** —` or `- **Reported Upstream:**` / a `## Reported Upstream` section are detected via the already-noted check; the marker shape is retained for backward compatibility and as the detection substrate. The outbound audit trail across AFK iterations now reflects ACTUAL filings (or queued-for-review drafts), not just deferred intents.
+- **upstream-blocked** — external dependency, Claude Code capability gap, or waiting on third-party fix. Truly terminal for this loop — no user question would change anything. Report the blocker (now via auto-invoke of `/wr-itil:report-upstream`, per ADR-024 2026-06-04 (P270) amendment) and move on. **Before skipping, run the manage-problem external-root-cause detection AFK fallback** (per P063 amended 2026-06-04): the fallback now invokes `/wr-itil:report-upstream` rather than only appending the marker. The report-upstream skill scores the drafted prose via `wr-risk-scorer:external-comms` (ADR-028); below-appetite branches send (public-issue Step 5 / comment Step 5c / security Step 6 per classification); above-appetite branches risk-reduce + re-score; if-still-above queue an `outstanding_questions` entry per P352 queue-and-continue (orchestrator does NOT halt). Existing tickets carrying `- **Upstream report pending** --` (canonical ASCII per P210), `- **Upstream report pending** —` (legacy em-dash), or `- **Reported Upstream:**` / a `## Reported Upstream` section are detected via the already-noted check; the marker shape is retained for backward compatibility and as the detection substrate. The outbound audit trail across AFK iterations now reflects ACTUAL filings (or queued-for-review drafts), not just deferred intents.
 
 Record the category alongside the skip reason in the iteration report so Step 2.5 can read the categories deterministically.
 
@@ -892,7 +892,7 @@ When `AskUserQuestion` is unavailable or the user is AFK, the skill (and the del
 | Halt-path final summary with accumulated user-answerable skips (CI failure / Rule 5 above-appetite / dirty-unknown / session-continuity / fetch failure) | Run Step 2.5b's surfacing routine before emitting the halt path's final AFK summary. Step 2.5b is gated on ≥1 accumulated user-answerable skip — empty-skip halts skip the routine. Step 2.5b surfaces *prior-iter accumulated user-answerable skips only*; it does NOT ask the user how to remediate the halt cause itself (CI failure / above-appetite state / dirty-unknown state remain halt-with-bug-signal). Per ADR-013 Rule 1 + ADR-032 + P126 (`halt-paths-must-route-design-questions-through-Step-2.5b`). |
 | Unexpected dirty state between iterations | Halt the loop. Report the `git status --porcelain` output, the last iteration's reported outcome, and the divergence — per P036 (Step 6.75). Run Step 2.5b before emitting the halt summary if ≥1 accumulated user-answerable skip from prior iters (P126). Do NOT attempt non-interactive recovery of the dirty state itself. |
 | Iter committed cleanly + claim contradicts on-disk ADR Confirmation state (P335) | Halt the loop with `outcome: halted-iter-over-claim`. Include the `wr-itil-verify-iter-summary` stdout (the `OVER-CLAIM: ADR-NNN has N unchecked Confirmation item(s)...` lines) as the divergence detail. Run Step 2.5b before emitting the halt summary if ≥1 accumulated user-answerable skip from prior iters. Do NOT auto-correct the iter's claim — the orchestrator cannot retroactively make a false claim true; the user adjudicates on return (re-dispatch / accept partial / amend). Per ADR-013 Rule 6 + ADR-032 subprocess-boundary trust contract + P335 (Step 6.75 verify-iter-claims sub-step). |
-| External root cause detected at Open → Known Error, or at park with `upstream-blocked` reason | **Auto-invoke `/wr-itil:report-upstream`** via the manage-problem Step 6 external-root-cause detection AFK fallback (per ADR-024 2026-06-04 (P270) amendment). The report-upstream skill composes the draft then scores the prose via `wr-risk-scorer:external-comms` (ADR-028); below-appetite → sends (public-issue Step 5 / comment Step 5c / security Step 6 per classification); above-appetite → risk-reduces (open-ended LLM judgement per leaf (a)) then re-scores → sends-or-queues to `## Queued Upstream Report` (leaf (c)). Security routing per leaf (b): upstream-with-`SECURITY.md` + below-appetite → files via declared channel; upstream-without-`SECURITY.md` → external-comms-gated impact assessment. Queue does NOT halt (P352). Tickets already carrying the stable `- **Upstream report pending** — external dependency identified; invoke /wr-itil:report-upstream when ready` marker from prior sessions are detected via the already-noted grep check and routed to the report-upstream invocation; the marker shape is retained as the detection substrate. Per P063 (amended 2026-06-04) + P270 + ADR-013 Rule 6. |
+| External root cause detected at Open → Known Error, or at park with `upstream-blocked` reason | **Auto-invoke `/wr-itil:report-upstream`** via the manage-problem Step 6 external-root-cause detection AFK fallback (per ADR-024 2026-06-04 (P270) amendment). The report-upstream skill composes the draft then scores the prose via `wr-risk-scorer:external-comms` (ADR-028); below-appetite → sends (public-issue Step 5 / comment Step 5c / security Step 6 per classification); above-appetite → risk-reduces (open-ended LLM judgement per leaf (a)) then re-scores → sends-or-queues to `## Queued Upstream Report` (leaf (c)). Security routing per leaf (b): upstream-with-`SECURITY.md` + below-appetite → files via declared channel; upstream-without-`SECURITY.md` → external-comms-gated impact assessment. Queue does NOT halt (P352). Tickets already carrying the stable `- **Upstream report pending** -- external dependency identified; invoke /wr-itil:report-upstream when ready` marker from prior sessions are detected via the already-noted grep check and routed to the report-upstream invocation; the marker shape is retained as the detection substrate (ASCII `--` per P210 — em-dash variant is the legacy form, still matched by the already-noted check for backward compatibility). Per P063 (amended 2026-06-04) + P270 + ADR-013 Rule 6. |
 | Mid-loop ask between iters in the orchestrator's main turn | Forbidden except at framework-prescribed user-interaction points (Step 0 session-continuity / fetch-failure halt; Step 2.5 / 2.5b loop-end emit; Step 6.5 above-appetite Rule 5 halt; Step 6.5 CI-failure / release:watch halt; Step 6.5 cohort-graduation halt-no-resolution halt; Step 6.5 cohort-graduation per-entry Rule 4 evidence-floor judgement (P308 — interactive only; AFK queues per P352); Step 6.75 dirty-for-unknown-reason halt). The loop's purpose is **progress + accumulation**; mechanical-stage transitions between iters are framework-resolved and MUST NOT prompt the user. Per ADR-044 framework-resolution boundary + ADR-013 Rule 1 (as amended by ADR-044) + P130. |
 
 ### Mid-loop ask discipline (orchestrator main turn) — P130