## This is a live regression on `main`, not a conversion
`#2728` converted the retry **classifier** and left all three re-queue
**targets** on the literal `"todo"`. That pairing is **strictly worse
than the bug it fixed**:
- **Before:** `fn task retry` silently did nothing on a renamed board.
- **After (main today):** it correctly decides to retry, then throws.
```
TransitionRejectionError: Invalid transition: 'checking' → 'todo'. Unknown column for this workflow.
```
`todo` is not a column that board declares. Reproduced against main's
exact code — reverting this fix fails **2 of 4** cases with that error.
I flagged this on #2728 before it landed; posting it as a fix rather
than a comment now that it is merged.
## Why the census did not catch it
The census counts **comparisons**. A move **target** contains no
comparison, so all three sites are invisible to it —
`packages/cli/src/commands/task.ts` reads **0 guards** on main while the
crash is live.
That is the clearest case in this program so far that **the census
measures conversion progress, not correctness**. A classifier and the
target it feeds have to move together, and no automated signal will say
so.
## The fix
The target resolves from the task's own workflow:
```ts
const retryHoldColumn = (await resolveTaskLifecycleColumns(context.store, id))?.hold ?? "todo";
```
Failing soft to `"todo"` when the workflow cannot be resolved, matching
every other fallback in this file. Three call sites, all three
converted.
## Revert proof
| state | result |
|---|---|
| main today (classifier converted, target literal) | **2 failed** / 2
passed — `Invalid transition: 'checking' → 'todo'` |
| with this fix | **4 passed** |
## The fixture is derived, not hand-built
The renamed workflow is `BUILTIN_CODING_WORKFLOW_IR` with **only its
column ids renamed**, so the sole difference between the two runs is
vocabulary. Hand-building a graph tested the fixture's shape as much as
the code — the IR validator rejects an undeclared back-edge, and once
declared as `kind: "rework"` the transition table still did not match
the default board's. The suite also asserts the rename landed
(`checking` present, `in-review` absent), so a surviving literal cannot
pass by accident.
Real store, real persisted workflow, driven through the real
`runTaskRetry` — not the predicate. A unit test of the classifier goes
green on the half-fix; only driving the whole command surfaces the
crash.
## Relationship to #2736
This replaces it. #2736's other contents (active-task count,
near-duplicate filter, archived-lineage label, node-override guards, the
missing-worktree classifier) are now redundant with #2728, so they are
dropped rather than re-litigated. What survives is this fix, its test,
and the **changeset for the published CLI** that #2728 did not include.
I will close#2736 once this is reviewed.
## Verification
- new PG suite **4 passed** · `task-retry.test.ts` **7 passed** across 2
files
- `pnpm test:gate` — **10 / 158 / 487 / 71** · `pnpm lint` clean · CLI
`tsc --noEmit` clean · `check:changesets` passes · `--strict` exits 0
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
dc363543a2