|
237 | 237 | payload to carry it. Every agent-mode error line from those three commands |
238 | 238 | now carries the same envelope its `--json` payload would, projected from the |
239 | 239 | same selected route as `next_action` and `next_actions[]`, so the three |
240 | | - cannot disagree. A failure envelope is fail-closed by construction: |
241 | | - `execution: "failed"`, `decision: "setup_incomplete"`, and every field of |
242 | | - `permissions` false. Two lines still carry none, by design and by |
| 240 | + cannot disagree. What every setup error line guarantees is what the schema |
| 241 | + enforces for any setup envelope: `decision_source: "setup"`, a decision from |
| 242 | + the setup vocabulary, every field of `permissions` false, and never |
| 243 | + `control_state: "complete"` — the `execution` split is described below. Two |
| 244 | + lines still carry none, by design and by |
243 | 245 | documentation: the shared `--workspace` refusal fires before a workspace |
244 | 246 | exists, and `environment_error` is emitted before Agents Shipgate is running. |
245 | 247 | Runtime contract 26 → 27; both the `AgentControl` union and the envelope |
|
274 | 276 | `--minimal` and following it wrote a detected manifest where a legacy |
275 | 277 | template was asked for. |
276 | 278 |
|
| 279 | + **A pack change an agent asked for is not a pack change a human approved.** |
| 280 | + The reconciliation route above was published as a coding-agent `edit` because |
| 281 | + the value came from the command line rather than from inference. A *governed* |
| 282 | + coding agent composes its own argv, so that is not authenticated human |
| 283 | + provenance: `init --write --control-pack read-only-agent` over a |
| 284 | + `financial-strict` manifest drops `write` and `production_operation` |
| 285 | + obligations, and an agent could have requested it for itself. The direction |
| 286 | + decides the owner now — a transition that keeps every obligation the manifest |
| 287 | + has today is an agent edit, one that drops any obligation (or names a pack |
| 288 | + this build cannot resolve) is a human review naming what it would remove. The |
| 289 | + comparison is `weakened_pack_obligations`, moved beside the packs it compares |
| 290 | + and shared with the `control_pack_weakened` check rather than restated. |
| 291 | + |
| 292 | + "Asked for" is read from the argument parser, not inferred by comparing |
| 293 | + against the default: an explicit `--control-pack default` over a |
| 294 | + `financial-strict` manifest is a request, and the only one that can *only* |
| 295 | + weaken. |
| 296 | + |
| 297 | + **Scoped routing owed the same two things.** The capped retry is the one |
| 298 | + scope route that reruns the *same* workspace, and it was built from the list a |
| 299 | + rerun in a different one may repeat — so it dropped |
| 300 | + `--allow-unresolved-scope` and returned the refusal it was issued to resolve. |
| 301 | + Candidate commands dropped a raised `--max-python-files`, which bounds how |
| 302 | + much is read rather than which directory, so a candidate inherited the root's |
| 303 | + truncation and refused again while its `expects` promised a manifest. And an |
| 304 | + adopted candidate whose manifest selects a different pack went to `doctor`, |
| 305 | + losing the request one directory down. There are now two lists with one |
| 306 | + derivation — what transfers to another workspace, and that plus the two that |
| 307 | + only make sense in this one. |
| 308 | + |
277 | 309 | **`execution` is not a marker for "this line is an error".** The `error` |
278 | 310 | field is. `execution` says whether the command reached an answer about the |
279 | 311 | workspace, and both values occur on error lines: `"failed"` where it could |
|
0 commit comments