mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-21 07:33:14 +01:00
fix(autoplan): bind rec_hash to its run and plan; keep legacy gates answerable (GST-1819) (#4137)
* fix(autoplan): bind rec_hash to its run and plan; keep legacy gates answerable (GST-1819) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(autoplan): legacy rec_hash is not run-bound; re-render pending pre-change gates (GST-1819) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
This commit is contained in:
1 parent
ddbf1c9a47
commit
1a29fbc344
8 files changed
+70
-9
No files matched your search
@@ -4967,6 +4967,16 @@ recommended `b` pending, and `all` now takes them.
|
||||
and answer with `--rec-hash <h>` from that render. Explicit `<id><option>`
|
||||
tokens are never refused.
|
||||
|
||||
Since GST-1819 the hash also names the run, its reviewed plan's sha256 and each
|
||||
item's title and option keys, so a `--rec-hash` from another run's gate with
|
||||
the same decision shape is refused too: answer each run with the hash its own
|
||||
render printed. A gate written before that (its `gate.json` has no
|
||||
`rec_hash_v`) still accepts the hash it printed then, and the answer records
|
||||
that hash. That old hash is not bound to its run, so two such gates with the
|
||||
same decision shape still accept each other's: re-render a pending one and
|
||||
answer with the new hash its render prints. A `recommend` on it moves it to the
|
||||
new hash.
|
||||
|
||||
<a id="checkpoint-invalid"></a>
|
||||
### `CHECKPOINT_INVALID`
|
||||
|
||||
|
||||
+1
-1
@@ -283,7 +283,7 @@ tree no review saw, so /ship runs again;
|
||||
| File | Schema | Contents |
|
||||
|------|--------|----------|
|
||||
| `run.json` | `run` v1 | The manifest: `run` id, `status`, `required_phases`, each phase's `native` and `outside` outcome (`status`, `model`, `provider`), input `snapshot` hashes, `counts`, every artifact's `path` (relative to the run directory) and `sha256`, `session_kind`, `gate_rev`, `deviations`, `consumed_by`. |
|
||||
| `decisions.jsonl` | `decisions` v1 | One row per decision: `id` (`<run>-<label>` at gate revision 1, `<run>-r<rev>-<label>` after a reopen, since labels restart at each gate), `title`, `options`, `recommended`, `kind` (`auto`, `approval`, `user_challenge`), `status` (`pending`, `approved`, `overridden`, `rejected`, or `auto_kept` in a [CEO-only run](#ceo-only-runs)), `gate_rev`, and once answered `chosen`, `answered_at`, `reply`, plus how the owner answered: `owner_mode` (`rec`, `rec_except`, `tokens`, `as_is` or `unparsed`, parsed from the owner's own words), `owner_named` (his words named this item), `rec_hash` (the recommendations answered against) and `answered_role` (`human`, or `agent` relaying his words); an agent-relayed answer adds `owner_reply`, his verbatim words, which never leave in a [public copy](#the-public-copy). |
|
||||
| `decisions.jsonl` | `decisions` v1 | One row per decision: `id` (`<run>-<label>` at gate revision 1, `<run>-r<rev>-<label>` after a reopen, since labels restart at each gate), `title`, `options`, `recommended`, `kind` (`auto`, `approval`, `user_challenge`), `status` (`pending`, `approved`, `overridden`, `rejected`, or `auto_kept` in a [CEO-only run](#ceo-only-runs)), `gate_rev`, and once answered `chosen`, `answered_at`, `reply`, plus how the owner answered: `owner_mode` (`rec`, `rec_except`, `tokens`, `as_is` or `unparsed`, parsed from the owner's own words), `owner_named` (his words named this item), `rec_hash` (the recommendations answered against, bound to the run and its reviewed plan) and `answered_role` (`human`, or `agent` relaying his words); an agent-relayed answer adds `owner_reply`, his verbatim words, which never leave in a [public copy](#the-public-copy). |
|
||||
| `shadow/` | private, not an artifact | [Shadow mode](#shadow-mode) only: `ceo-only.r<rev>.jsonl` (one hidden prediction per gate item, written before the answer), `r<rev>.prompt.md` and one `<call>.reply.txt` per model call, the audit `salt`, and `r<rev>.pending` while a call is in flight. Never in `export --public`, the gate render or the owner brief. |
|
||||
| `findings.jsonl` | `findings` v1 | One row per reviewer finding: `id`, `phase`, `voice` (`native`/`outside`), `model`, `severity`, `title`, `disposition`, `plan_items`, `native_counterpart` (string or null), `source`. Rows share the review-log row shape, so `gstack-review-log --findings` derives review status from this file. |
|
||||
| `tasks.jsonl` | `tasks` v2 | Implementation tasks with `id`, `title`, `status`, `depends_on`, `findings` (ids in `findings.jsonl`), `blocked_by`, `acceptance`, optional `pr`/`item`/`tier`. |
|
||||
|
||||
Reference in new issue
Block a user