escalating-to-thinker

Capability: Escalating To Thinker

Render before asking. Before any AskUserQuestion, render the decision context as assistant chat text. Content that exists only in a Read result, a subagent/Agent return, or the question/option strings does not count as rendered (the UI shows a compact card) — restate it in chat first.

Dispatch a one-shot consult subagent on the project's think tier (models.think from config) when the orchestrating pipeline is stuck in a way the documented recovery paths don't cover. The consult returns a structured recommendation; the orchestrator executes it. The consult never mutates anything — it reads, reasons, and recommends.

Why this exists: the orchestrating session runs a mid-tier model tuned for stage-walking and dispatch, not for hard diagnosis. When the same fix fails twice or a gate hard-stops with no covered playbook, the cheap move is to buy one round of top-tier reasoning rather than burn iterations guessing. The per-sprint cap keeps this a scalpel, not a crutch.

When to invoke (the seven triggers — do NOT invoke outside these)

1. Repeated fix failure — the same task or gate has failed 2 consecutive fix iterations (*_fix_iter / redispatch exhausted, or two code_review_iter passes with an unchanged must-fix set).
2. Integration-gate hard stop — shipyard-data verify-wave-integrated exit 3 whose named branches/tasks don't match the documented remediation (rebase + ff-merge, anchor-commit) after one attempt.
3. Uncovered blocked task — a BLOCKED return whose escalation_code has no matching entry in the deviation rules / blocked-handling table.
4. Critic deadlock — review Stages 4.6/4.7 produce contradictory verdicts that a second pass does not reconcile.
5. Recovery-path ambiguity — the situation matches more than one documented recovery path, or matches one only partially, and picking between them (or adapting one to fit) requires judgment the shell isn't positioned to exercise. Since ship-execute now runs on Sonnet with a zero-thinking doctrine, this is the structural admission that "which documented path applies here" is itself sometimes a judgment call, not a lookup.
6. Uninterpreted gate failure — any CLI call exits 3 with a reason string that names a condition but no covered remediation exists for it in the skill body or references (distinct from trigger 2, which is specifically the integration gate; this covers any other gate — terminal-evidence, stale-cycle, task-state CLI refusals, etc.).
7. Deviation classification — a discrepancy between expected and actual state (a task's diff doesn't match its spec, a probe passes but the implementation looks wrong, a wave's evidence is technically complete but suspicious) needs a bug-vs-structural-deviation call: is this a defect to fix, or a legitimate divergence from the plan that the Deviation Rules should log and proceed past? The shell does not make this call itself.