exp(codex): print dispatch tuples from SDD scripts — v2 chokepoint for PRI-2672

Run-2 dispatch-4 autopsy: after compaction, the codex-tools role table
fell out of context and the controller reasoned itself into an inherited
sol@max reviewer — the harness's own 'inherited parent model is preferred'
plus SKILL.md's 'most capable model' outvoted the compaction summary's
distilled 'terra/high' line. Its introspection named the only artifact it
actually consults at the moment of dispatch: the review-package output.

So the role tuple now rides the script output, reprinted fresh every
round, immune to compaction by construction:
- task-brief prints role=implementer terra/high fork_turns=none
- review-package prints per role via a new leading --role flag
  (task-review default | re-review | final-review), and SKILL.md call
  sites pass the flag at the re-review and final-review sites
- SKILL.md Model Selection now defers to platform role tables and the
  printed dispatch hints, closing the 'most capable model' loophole
- codex-tools.md tells the controller to copy the printed tuple verbatim

Harness detection considered and rejected: gating the print on CODEX_CI
risks a silent no-op in exactly the environment that needs it; the line
is labeled '(codex spawn_agent)' instead, and CC controllers — whose
templates carry their own model fields — can ignore it.

Experiment branch for PRI-2672 validation; not for merge without eval
evidence.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

skills/subagent-driven-development/SKILL.md

@@ -158,6 +158,12 @@ conflicts that only emerge from implementation.
 
 Use the least powerful model that can handle each role to conserve cost and increase speed.
 
+When your platform's reference file (using-superpowers → Platform
+Adaptation) defines a dispatch role table, that table IS this section's
+mapping for your harness. Follow it over the tier language below — including
+for the final review and fix-loop escalation — and follow the
+`dispatch:` hint lines the task-brief and review-package scripts print.
+
 **Mechanical implementation tasks** (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.
 
 **Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.
@@ -340,7 +346,7 @@ output; dispatch the re-review once all three are present. Name the
 covering test files in the fix message — a one-line fix does not need the
 whole suite.
 
-**The re-review is scoped.** Run `scripts/review-package PLAN_FILE FIX_BASE HEAD`
+**The re-review is scoped.** Run `scripts/review-package --role re-review PLAN_FILE FIX_BASE HEAD`
 where FIX_BASE is the head the previous review saw, and dispatch
 [re-review-prompt.md](re-review-prompt.md) with the findings list, the
 brief, the report file, and the printed diff path. The re-reviewer verdicts
@@ -391,7 +397,7 @@ parked-with-ruling at the cap.
 ## Final Review
 
 The final whole-branch review gets a package too: run
-`scripts/review-package PLAN_FILE MERGE_BASE HEAD` (MERGE_BASE = the commit the
+`scripts/review-package --role final-review PLAN_FILE MERGE_BASE HEAD` (MERGE_BASE = the commit the
 branch started from, e.g. `git merge-base main HEAD`) and include the
 printed path in the final review dispatch, so the final reviewer reads
 one file instead of re-deriving the branch diff with git commands. Dispatch
@@ -406,7 +412,7 @@ with the complete findings list — not one fixer per finding.
 Per-finding fixers each rebuild context and re-run suites; a real
 session's final-review fix wave cost more than all its tasks combined.
 Then run exactly one scoped re-review of the fix wave
-(`scripts/review-package PLAN_FILE FIX_BASE HEAD` over the fix range,
+(`scripts/review-package --role re-review PLAN_FILE FIX_BASE HEAD` over the fix range,
 [re-review-prompt.md](re-review-prompt.md)).
 Adjudicate any residual findings as in the task loop's breaker: park with
 rulings, or stop on load-bearing ones. There is no second fix wave —
@@ -494,7 +500,7 @@ Task reviewer: Spec ❌:
 Implementer: Added progress reporting, extracted PROGRESS_INTERVAL constant.
   Re-ran test/recovery.test.js — 10/10 passing. Fix report appended.
 
-[Run review-package PLAN_FILE FIX_BASE HEAD; dispatch scoped re-review]
+[Run review-package --role re-review PLAN_FILE FIX_BASE HEAD; dispatch scoped re-review]
 Re-reviewer: Missing progress reporting — ADDRESSED (src/recovery.js:41).
   Magic number — ADDRESSED (src/recovery.js:7). New breakage: none.
   Verdict: all findings addressed.
@@ -505,7 +511,7 @@ Re-reviewer: Missing progress reporting — ADDRESSED (src/recovery.js:41).
 ...
 
 [After all tasks]
-[Run review-package PLAN_FILE MERGE_BASE HEAD; dispatch final code-reviewer, most capable model]
+[Run review-package --role final-review PLAN_FILE MERGE_BASE HEAD; dispatch final code-reviewer, most capable model]
 Final reviewer: All requirements met. Deferred minors triaged: none block merge.
 
 [Delete this plan's workspace — the record now lives in git]

skills/subagent-driven-development/scripts/review-package

@@ -4,13 +4,31 @@
 # call. Using the recorded per-task BASE (not HEAD~1) keeps multi-commit
 # tasks intact.
 #
-# Usage: review-package PLAN_FILE BASE HEAD [OUTFILE]
+# Usage: review-package [--role task-review|re-review|final-review] PLAN_FILE BASE HEAD [OUTFILE]
 # Default OUTFILE: <repo-root>/.superpowers/sdd/<plan-basename>/review-<base7>..<head7>.diff
 # (named per range, so a re-review after fixes gets a distinct fresh file).
+#
+# The trailing dispatch hint rides this output because the controller reads it
+# immediately before spawning the reviewer; skill text loaded at session start
+# does not survive context compaction, but this line is reprinted every round.
 set -euo pipefail
 
+role=task-review
+if [ "${1:-}" = "--role" ]; then
+  [ $# -ge 2 ] || { echo "usage: review-package [--role task-review|re-review|final-review] PLAN_FILE BASE HEAD [OUTFILE]" >&2; exit 2; }
+  role=$2
+  shift 2
+fi
+
+case "$role" in
+  task-review)  hint_role=task-reviewer;      hint_effort=high ;;
+  re-review)    hint_role=scoped-re-reviewer; hint_effort=medium ;;
+  final-review) hint_role=final-reviewer;     hint_effort=high ;;
+  *) echo "bad --role: ${role} (task-review|re-review|final-review)" >&2; exit 2 ;;
+esac
+
 if [ $# -lt 3 ] || [ $# -gt 4 ]; then
-  echo "usage: review-package PLAN_FILE BASE HEAD [OUTFILE]" >&2
+  echo "usage: review-package [--role task-review|re-review|final-review] PLAN_FILE BASE HEAD [OUTFILE]" >&2
   exit 2
 fi
 
@@ -44,3 +62,4 @@ fi
 
 commits=$(git rev-list --count "${base}..${head}")
 echo "wrote ${out}: ${commits} commit(s), $(wc -c < "$out" | tr -d ' ') bytes"
+echo "dispatch (codex spawn_agent): role=${hint_role} fork_turns=none model=gpt-5.6-terra reasoning_effort=${hint_effort}"

skills/subagent-driven-development/scripts/task-brief

@@ -39,3 +39,7 @@ if [ ! -s "$out" ]; then
 fi
 
 echo "wrote ${out}: $(wc -l < "$out" | tr -d ' ') lines"
+# The dispatch hint rides this output because the controller reads it
+# immediately before spawning the implementer; skill text loaded at session
+# start does not survive context compaction, but this line reprints per task.
+echo "dispatch (codex spawn_agent): role=implementer fork_turns=none model=gpt-5.6-terra reasoning_effort=high"

skills/using-superpowers/references/codex-tools.md

@@ -32,6 +32,9 @@ Before Task 1, check your `spawn_agent` tool schema for `model` and
 
 On Codex this table IS the Model Selection mapping — including the final
 review, which stays on terra/high rather than "most capable available."
+The task-brief and review-package scripts reprint the applicable row as a
+`dispatch (codex spawn_agent):` line with their output — copy those values
+onto the spawn_agent call verbatim, every time, even late in a long session.
 Never give a subagent your session's model when you run a frontier config
 (sol at xhigh or max): reviewer tier never exceeds implementer tier, and
 a fix round never gets an effort bump. Rounds 4-5's "more capable model"