@junghanacs/entwurf 0.36.1 → 0.37.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/AGENTS.md CHANGED
@@ -91,10 +91,10 @@ implement → affected focused gates → independent review → one amendment bu
91
91
  → affected qualification PARTIAL once if gate/mutant/matrix changed → full floor once on frozen candidate → commit
92
92
  ```
93
93
 
94
- - GLG-requested branch checkpoint commits keep completed subject/proof bundles small: scoped review, affected focused checks and normal hooks/shared scanner before each checkpoint, with known RED/unmeasured boundaries recorded. A checkpoint is not frozen-candidate acceptance. The sequence above owns final candidate acceptance: the affected qualification PARTIAL, frozen FULL and native/LIVE/release floors remain mandatory before landing, and the prepared SHA's CI qualification body before shipment, never inherited from an interim commit.
94
+ - GLG-requested branch checkpoint commits keep completed subject/proof bundles small: scoped review, affected focused checks and normal hooks/shared scanner before each checkpoint, with known RED/unmeasured boundaries recorded. A checkpoint is not frozen-candidate acceptance. The sequence above owns final candidate acceptance: the affected qualification PARTIAL, frozen FULL and native/LIVE/release floors remain mandatory before landing, and the prepared SHA's exact-SHA CI push run (its four required jobs; the qualification body is no longer a release axis, #144) before shipment, never inherited from an interim commit.
95
95
  - Inner loop runs only affected gates; review and its corrections finish before the full floor.
96
96
  - A changed contract names a production subject and independent oracle; its focused assertion has a stable QK and exact-once mutant. Matrices change by their declared axes/cells, not appended anecdotes.
97
- - Development never runs the whole qualification body. A changed gate/mutant/matrix runs its affected exact-argv groups once, after review and amendment, as PARTIAL receipts (`./run.sh check-gate-qualification --group '<argv JSON>' --receipt <absolute path outside the repo>`); the manifest head stays in the deterministic floor. The whole body runs once per cut, in the prepared SHA's CI: a prepared state awaits it and is never presumed PASS, and a release requires the exact-SHA evidence VERIFY names, never a nearby green run or a PARTIAL.
97
+ - Development never runs the whole qualification body. A changed gate/mutant/matrix runs its affected exact-argv groups once, after review and amendment, as PARTIAL receipts (`./run.sh check-gate-qualification --group '<argv JSON>' --receipt <absolute path outside the repo>`); the manifest head stays in the deterministic floor. Since #144 (GLG, 2026-10-16) the whole body is not a release axis: it runs only on the weekly schedule or a manual `qualify=true` dispatch, as a drift diagnostic no cut waits for, and no cut owes a local whole body either. A release states that kill-power was not re-measured at its SHA and lists any earlier-candidate PARTIAL with its own candidate; a PARTIAL never stands for the release, and the release still requires the exact-SHA evidence VERIFY names, never a nearby green run.
98
98
  - Freeze the candidate while the full floor runs; any worktree/index movement voids that receipt. Pre-commit is not the full floor.
99
99
  - LIVE/release floors are not lowered by a shorter inner loop. Failed gate or evidence downgrade blocks the relevant commit/release decision.
100
100
 
package/CHANGELOG.md CHANGED
@@ -4,6 +4,307 @@ All notable changes to this project will be documented here. Format follows [Kee
4
4
 
5
5
  ## Unreleased
6
6
 
7
+ ## 0.37.1 - 2026-10-16
8
+
9
+ ### Verification
10
+
11
+ - **The native-module ingress claims get their own mutant coordinate (#144).** The 13
12
+ `PI-DURABLE-MODULE-*` claims carry their QKs only in `pi-durable-native-module.test.ts`, and a
13
+ kill is attributed from the mutant's own QK, yet each of them re-ran all six pi-durable beside
14
+ tests. `./run.sh check-pi-durable-native-module` runs that one file and is now their gate argv;
15
+ `check-pi-durable-beside` no longer runs it. No claim, find/replace, signature or build changes.
16
+ - **The carrier claims get their own mutant coordinate too (#144).** The 30 claims whose QKs live
17
+ only in `pi-durable-carrier.test.ts` move to `./run.sh check-pi-durable-carrier`, which runs that
18
+ file alone; `check-pi-durable-beside` keeps the adapter, verifier, preflight and owner-join files
19
+ and their 39 claims. All three coordinates stay in `check:contracts`, and every claim keeps its
20
+ subject, find/replace, signature and bridge build (the carrier test reaches the bridge through the
21
+ bootstrap). Measured once on one host, on an isolated copy of `5e1e629` (M1, a composition
22
+ measurement, not a kill run): the six files together took 24.5s, the carrier file alone 17.6s and
23
+ the native-module file alone 1.7s, so before the split every mutant of the former six-file
24
+ `check-pi-durable-beside` group (82; the two `check-node-floor-coherence` claims were never in it)
25
+ paid the carrier's time. Those seconds are local, not CI timing. A moved mutant no longer runs beside the other
26
+ files; that was incidental exposure, never the ground of a kill, which is attributed only from the
27
+ mutant's own QK.
28
+ - **The whole qualification body is no longer a release axis (#144).** By GLG's decision of
29
+ 2026-10-16 (split local gates from CI; a named loss of verification is accepted to stop paying for
30
+ the same proof twice), no push runs the body any more and no cut waits for it. Measured from the
31
+ GitHub API over one cut window (v0.36.1 push `cab1b9f` through the Herdr 0.37.0 snapshot `5e1e629`,
32
+ six `ci.yml` runs): the body ran five times on five SHAs for 506.3 minutes of `check`-step time,
33
+ once as a dispatch that re-bought it for a SHA whose push had skipped it, while a push run without
34
+ it took 10.9 minutes wall. That is the cost before this change, not a measured saving. The body now
35
+ runs only on the weekly schedule or a manual `qualify=true` dispatch, as a drift diagnostic. The
36
+ push-range filter that decided when it ran (`scripts/ci-qualify-decide.sh`, its replay fixture, and
37
+ the five `QUALIFY-FILTER-*` claims) is retired with it, and the release skill no longer dispatches
38
+ the body.
39
+ - **The release oracle takes the push run as its only witness, and no longer reads the body
40
+ (#144).** `verify-exact-ci.sh` asks for push runs of the exact SHA (`--event push`, and a jq that
41
+ keeps only push runs) and judges the four required jobs. Its fourth axis, the body step, is
42
+ removed with `RELEASE-SHA-QUALIFIED-IN-CI`, and its PASS prints that the body is not a release
43
+ axis instead of a body success line. `check-release-gate-outcomes` drives the shipped script
44
+ through a fake `gh`: `RELEASE-WITNESS-IS-PUSH-RUN` pins the one `run list` call it sends (the
45
+ fake evaluates no jq, and GitHub's own filtering is not observed), `RELEASE-ORACLE-REFUSES-NON-SUCCESS-JOB`
46
+ refuses each required job that is absent, failed, skipped, cancelled or unconcluded, and
47
+ `RELEASE-ORACLE-CLAIMS-NO-BODY` passes the four jobs whether the body step is skipped, absent or
48
+ green without ever naming it. The `release-gate` lane is 21 claims.
49
+ - **Named loss.** A release no longer re-measures the kill-power of the committed claims at its SHA.
50
+ Its section says so (`Kill-power re-measured at this shipped SHA: none`), and lists a PARTIAL
51
+ receipt only with its own candidate, never summed into a count for the release. The weekly run is
52
+ a drift window, not a guarantee for any commit.
53
+ - **The mux lifecycle LIVE runs on a different native model, and before the ACP tier.** In 0.37.0's
54
+ first LIVE run and in this cut's first one, `smoke-mux-lifecycle-live` went red the same way: its
55
+ pi-native sibling (`openai-codex/gpt-6-luna`) was alive, ran shell no-ops, answered "ACK" and never
56
+ called the callback tool within 300 s. The cause is not determined; one instrumented diagnostic run
57
+ saw the callback declared in the first request and called back in about 4 s, so the failure did
58
+ not reproduce. The test's native model is now `openai-codex/gpt-6.1-sol:low` (`VERIFY.md` names it), and
59
+ `release-gate` runs this step right after the v2 matrix, before the ACP tier, so a red answer comes
60
+ before the ACP turns are spent. This is a test-model and order change, not a fix: the `gpt-6-luna`
61
+ cause stays undetermined. In this cut's second and third LIVE runs the step passed on the new
62
+ model and order; those are two observations, and neither proves the earlier cause.
63
+ - **The Codex first-admission LIVE now says the id prefixes are part of the ids.** In this cut's
64
+ second LIVE run the moved mux step passed, and `smoke-codex-fresh-live` failed on its last check:
65
+ the Codex sibling's final `entwurf_v2` arguments carried `PI_SESSION_ID=485` and
66
+ `PI_WINDOW_ID=1130` where the launch receipt printed `$485` and `@1130`, with every other field
67
+ exact. Its instruction named the `$` and `@` only inside the placeholder text; it now tells the
68
+ sibling to copy both ids byte for byte from the receipt's `window:` line, keeping each leading
69
+ prefix. The exact-argument comparison is unchanged and nothing is stripped. That the wording
70
+ invited the drop is a hypothesis: the same code and model passed in 0.37.0. In this cut's third
71
+ LIVE run the step passed with both prefixes exact (`$488`, `@1136`); that is one run, and it does
72
+ not prove that the wording caused the earlier drop or rule out model variation.
73
+
74
+
75
+ ### Release boundary and verification
76
+
77
+ - **Scope.** A core patch over `v0.37.0` for #144: `1df7926` (the pi-durable native-module and
78
+ carrier mutant coordinates, and the release oracle's job refusal driven through a fake `gh`) and
79
+ `c208d37` (the whole qualification body retired as a release axis). The Herdr plugin snapshot
80
+ `v2026.10.15-herdr.0.37.0` at `5e1e629` is unchanged; pi 1.3.0 (#145) is not in this cut.
81
+ - **Kill-power re-measured at this shipped SHA: none (all 979 committed claims not re-proved,
82
+ #144).**
83
+ - Earlier-candidate PARTIAL (operator-attested, not this SHA): head 5e1e629a5826 surface
84
+ e907429b9c00 -- `check-pi-durable-native-module` 13/13 receipt e0f96c3374de
85
+ - Earlier-candidate PARTIAL (operator-attested, not this SHA): head 5e1e629a5826 surface
86
+ e907429b9c00 -- `check-pi-durable-beside` 69/69 receipt 36e46bdd4cf0
87
+ - Earlier-candidate PARTIAL (operator-attested, not this SHA): head 5e1e629a5826 surface
88
+ ea26d369b1af -- `check-pi-durable-carrier` 30/30 receipt 01f9096a8eb5
89
+ - Earlier-candidate PARTIAL (operator-attested, not this SHA): head 5e1e629a5826 surface
90
+ ea26d369b1af -- `check-pi-durable-beside` 39/39 receipt 93d9f5cdf699
91
+ - Earlier-candidate PARTIAL (operator-attested, not this SHA): head 5e1e629a5826 surface
92
+ 980384f2532f -- `check-release-gate-outcomes` 25/25 receipt eedfb075bf07
93
+ - Earlier-candidate PARTIAL (operator-attested, not this SHA): head 5e1e629a5826 surface
94
+ 980384f2532f -- `check-gate-manifests` 52/52 receipt 8a976415c566
95
+ - Earlier-candidate PARTIAL (operator-attested, not this SHA): head 5e1e629a5826 surface
96
+ 980384f2532f -- `check-gate-qualification.ts --attribution-self-test` 1/1 receipt 3edfa0af9d3a
97
+ - Earlier-candidate PARTIAL (operator-attested, not this SHA): head 1df7926257a9 surface
98
+ 106c59c5cb99 -- `check-release-gate-outcomes` 21/21 receipt c869965b8dbc
99
+ - Earlier-candidate PARTIAL (operator-attested, not this SHA): head 1df7926257a9 surface
100
+ 106c59c5cb99 -- `check-gate-manifests` 52/52 receipt 08eae97d65b0
101
+ - Earlier-candidate PARTIAL (operator-attested, not this SHA): head 1df7926257a9 surface
102
+ 106c59c5cb99 -- `check-gate-qualification.ts --attribution-self-test` 1/1 receipt 276118d0ba9b
103
+ - Earlier-candidate PARTIAL (operator-attested, not this SHA): head c208d37f1442 surface
104
+ d941509e2e9e -- `check-release-gate-outcomes` 21/21 receipt cd0a59e12569 (taken after the
105
+ mux model/order change and before the Codex id-prefix sentence; kept locally under
106
+ `.tmp-verify/release-0.37.1/fix-mux-first/partial-evidence/`)
107
+ - **Not re-measured for the Codex id-prefix sentence.** The five mutants whose subject is
108
+ `scripts/lib/codex-fresh-live-protocol.ts` were reviewed as lying outside the changed bytes, and
109
+ their `check-mux-fresh-call` group (150 mutants over 18 subjects) was not run, so those five
110
+ kills are not re-measured on the new bytes. The new sentence has no deterministic assertion of
111
+ its own: deleting it would leave the deterministic suite green, and only a LIVE run would see it.
112
+ - **Where those receipts are published.** Each receipt above except the newest (`cd0a59e12569`) is
113
+ listed with its candidate in a #144 checkpoint comment, so another host can trace it without this
114
+ operator's paths; the newest is local and operator-attested only, in no #144 comment. A′
115
+ ([#144 comment 6195663856](https://github.com/junghan0611/entwurf/issues/144#issuecomment-6195663856)),
116
+ B ([6196318282](https://github.com/junghan0611/entwurf/issues/144#issuecomment-6196318282)),
117
+ RO-1 ([6200017214](https://github.com/junghan0611/entwurf/issues/144#issuecomment-6200017214)) and
118
+ P1 ([6202638853](https://github.com/junghan0611/entwurf/issues/144#issuecomment-6202638853)).
119
+ The links add location only; they prove nothing new.
120
+ - **Branch CI, not this SHA.** The pushed branch head `c208d37` ran the new policy's first push CI
121
+ (run 38811304369): the four required jobs green, the body step skipped, created to last required
122
+ job 645 s. That run is evidence for `c208d37`; the prepared SHA owes its own.
123
+ - **Unpublished candidate carrier.** As in 0.37.0, `plugins/herdr/runtime-lock.json` names the
124
+ closed `herdr-checkout` source, because 0.37.1 has no published integrity yet and the runtime
125
+ refuses an npm lock whose version is not the checkout's (`scripts/herdr-runtime.mjs:355-358`).
126
+ The npm 0.37.0 bytes and every existing tag are unchanged; re-pinning registry bytes is a later,
127
+ separate Herdr snapshot.
128
+ - **No local static floor; it is the exact CI's.** `check:hermetic` carries
129
+ `check-herdr-plugin-build` and `check-herdr-sandbox`, which must not run on the operator host,
130
+ and `release-gate`'s first MUST step is `pnpm run check:full`. By GLG's decision of 2026-10-16
131
+ for this cut (a new approval, not inherited from 0.37.0), `check:full` is not run locally at P4,
132
+ at P5's first step or at M0, and is owed whole to the prepared SHA's CI.
133
+ - **LIVE, taken step by step, not as `release-gate --cut`.** The gate's 23 non-static MUST steps
134
+ and its BEHAVIOR step ran in the gate's own order, command, environment and working directory,
135
+ stopping at the first red, with each run's candidate fingerprint the same at freeze, before and
136
+ after. The first run (`c208d37` with this preparation's first edits) passed 18 MUST steps and
137
+ failed `smoke-mux-lifecycle-live` at its old position; the second (with the model and order
138
+ change) passed 21 and failed `smoke-codex-fresh-live` on the dropped id prefixes. Both red
139
+ receipts are kept. The third ran on the tested bytes, `c208d37` with this cut's source and package
140
+ edits; after it only `CHANGELOG.md` and `NEXT.md` changed, to record these results. It ran every
141
+ step itself, none reused: **MUST 23/23 PASS, FAIL 0, SKIP 0;
142
+ BEHAVIOR 1/1 PASS.** `smoke-mux-lifecycle-live` passed 81 checks as step 5,
143
+ `smoke-codex-fresh-live` 66 assertions against one owned app-server in its own tmux session
144
+ (named pane pid with its recorded start time, `gpt-5.6-luna` and `openai-codex/gpt-5.6-luna`,
145
+ stopped by one TERM after the run with its subtree, listener and control alias gone), and
146
+ `smoke-pi-durable-fresh-live` 36 assertions. Receipts on the operator host, under
147
+ `.tmp-verify/release-0.37.1/`: the third run's freeze fingerprint `3a90e3f1f2a2`, gate log
148
+ `94d14b3d42af` and step-log manifest `ded0d693c3ff` (24 logs); the red runs' gate logs
149
+ `3e16e8964f9e` and `da9622fb5312`. This is local LIVE evidence, not a release-gate verdict, and
150
+ no static CI result is claimed by it.
151
+ - **Publication boundary.** The LIVE and PARTIAL lines above are local preparation evidence.
152
+ Shipping this version separately requires the prepared SHA's exact CI (the four required jobs), a
153
+ preserved accepted candidate made from that SHA, and the tag and GitHub Release cut from it; npm
154
+ publication is the operator's.
155
+
156
+ ## v2026.10.15-herdr.0.37.0 — Herdr Entwurf plugin 0.37.0
157
+
158
+ A separate Herdr plugin snapshot, not another core release: core package 0.37.0 and
159
+ its `v0.37.0` tag remain unchanged. The operator has published the core to npm.
160
+
161
+ ### Herdr plugin
162
+
163
+ - **Re-pin the published core 0.37.0 and close the checkout window.**
164
+ `plugins/herdr/runtime-lock.json` returns from the `herdr-checkout` carrier that 0.36.1 and
165
+ 0.37.0 rode to production npm source `@junghanacs/entwurf@0.37.0` with the registry's
166
+ measured sha512 (`sha512-ETVgzMWf…7964A==`). The plugin manifest moves 0.36.0 → 0.37.0;
167
+ admission remains Herdr >= 0.9.0 and the one-build/one-pane/Linux shape is unchanged.
168
+ - **The same core capability through Herdr.** The runtime this snapshot acquires carries core
169
+ 0.36.1 and 0.37.0: the Claude ACP driver on 0.90.0, Codex app-server socket ownership read
170
+ from the kernel, the durable app's transport and compaction tuning (#143) and its project
171
+ skill list (`4968ffd`). The measured Herdr is the 0.9.5 pin that landed in core 0.37.0
172
+ (`d8cd8f3`). This snapshot changes no rail, gate or mutant, and Pi's accepted range is the
173
+ same as 0.36.0's.
174
+ - **Upgrade by acquisition source, not just version.** A settled npm-source 0.36.0 installation
175
+ can rebind under the plugin README's ownership conditions. A host that installed an
176
+ intervening `herdr-checkout` candidate must explicitly deactivate by its own absolute runtime
177
+ path before reinstalling the npm-source snapshot. No operator installation or active session
178
+ is rewired by this release work.
179
+
180
+ ### Source-specific verification
181
+
182
+ - Registry metadata reports version/latest 0.37.0, repair 0.12.8-repair.1. The downloaded
183
+ tarball is 11144951 bytes, SHA256
184
+ `d127a927e6a9f9c6561f86975dc30697aebaa5eeb2de463e8f0d765ff12035ee`, byte-identical to the
185
+ preserved accepted core candidate; independently computed sha512 equals `dist.integrity`, and
186
+ the registry-shipped runtime helper is byte-equal to this checkout's.
187
+ - The exact registry tarball passed the required Docker consumer without repacking
188
+ (`node:24-bookworm`, repoDigest `node@sha256:6dac556d…`).
189
+ - **The npm runtime swap against the real registry**, by the registry-shipped helper in sandboxed
190
+ user roots, 20/20 checks. The 0.36.0 runtime was seeded from its own committed lock; the swap
191
+ to 0.37.0 took one acquisition, the cached tarball's sha512 equals the lock and its sha256
192
+ equals the ready journal's observed digest and the accepted candidate. The `installing`
193
+ journal carried the 0.36.0 identity as `previousRuntime` and the `runtime-ready` journal
194
+ carries `null`; when acquisition began the 0.36.0 tree was still at the active address. A
195
+ manually seeded torn swap (the active tree moved to the backup address with a half candidate
196
+ in staging; not a killed process) was restored before acquisition and reported
197
+ `recovered: torn-swap-with-candidate`. An exact re-request acquired nothing and left journal
198
+ and tree byte-identical, and the owned removal reclaimed cache, runtime and journal. Not
199
+ certified by these cells: Herdr's install/update relocation, harness wiring, the installed
200
+ CLI's deactivate path, a model turn, or recovery from a real kill.
201
+ - **Focused gates on the branch**, with HEAD, index and work surface unchanged across them:
202
+ `check-herdr-supply` (11 assertions), `check-herdr-plugin` (49),
203
+ `check-herdr-plugin-profile` (14), `check-herdr-runtime-bootstrap` (31),
204
+ `check-herdr-activation` (33), `check-herdr-placement` (25), `check-herdr-fresh-call` (45)
205
+ and `check-gate-manifests` (982 committed mutants across 72 lanes validated, none executed).
206
+ `check-herdr-plugin-build` and `check-herdr-sandbox` were not run locally because they run
207
+ the operator's own herdr; they ride the pushed SHA's FULL floor in CI.
208
+ - Pending, and not claimed here: the pushed SHA's four-job CI with the qualification body, and
209
+ the public-ref install/use/deactivate journey on Herdr 0.9.5. Earlier npm or checkout-carrier
210
+ receipts cannot certify these source-specific axes.
211
+
212
+ ## 0.37.0 - 2026-10-15
213
+
214
+ ### pi-durable
215
+
216
+ - **The durable app forwards pi's transport and stops compacting beside a running turn (#143).**
217
+ The owned Harness settings now carry `SettingsManager.getTransport()` (pi's default `auto`)
218
+ into every request; the reference app had left the field out, so the SDK chose per connection.
219
+ `auto` permits a cached WebSocket continuation only when the provider's own body and prefix
220
+ conditions hold; it does not make every request a delta. Background compaction is off
221
+ (`backgroundTokens: 0`): a turn past the blocking threshold waits for the SDK's summary instead
222
+ of one being written beside it. Threshold, manual and overflow compaction stay the SDK's, on
223
+ pi's own compaction settings. The SDK engine, models, auth and storage are unchanged, and this
224
+ claims neither lower vendor overload nor better memory.
225
+ - **`entwurf pi-durable --resume` reopens a chosen session (#143).** It lists the current
226
+ directory's durable sessions from their files and the record store only (creation time, garden
227
+ id, last write, open elsewhere), most recently written first, and opens the chosen one as it
228
+ was saved, under its own garden id. Cancelling opens nothing. No session, a non-terminal, a
229
+ session open elsewhere, or a new session's argument beside it refuse by name, with no fallback.
230
+ `--continue` still opens the newest-created session.
231
+ - **The durable app lists a project's skills again.** The owned prompt handed pi's `skills`
232
+ setting to the skill loader as written, so a relative entry was read against the session
233
+ directory: a project's `.pi/settings.json` entry `../.claude/skills` named a `.claude/skills`
234
+ beside the project, in its parent, and the project's own skills were silently not listed.
235
+ Relative path entries are now read as pi reads them, the project's against its `.pi` and the
236
+ global ones against the agent directory. Both scopes are kept, the project's first, so a project
237
+ skill wins over a global one of the same name. Absolute and `~` entries are unchanged.
238
+ Patterns, package skills, `.agents/skills` and skill diagnostics are not supported by this
239
+ change. No project trust check is added: the durable app reads a project's settings without a
240
+ trust decision, as it did before.
241
+
242
+ ### Herdr plugin
243
+
244
+ - **The measured Herdr moves to 0.9.5, the hotfix of 0.9.4.** `scripts/fixtures/herdr-supply.json`
245
+ pins v0.9.5 (`2ecf19a9`), protocol 22, with both Linux asset digests taken from the immutable
246
+ release and named by its attestation. On aarch64 the pin rests on a private CLI baseline:
247
+ version, protocol 22, 18 `integration status` rows unchanged from 0.9.4, and a residue-free
248
+ `server stop`. The full `check-herdr-sandbox` then passed at this pin on x86_64 in the CI run of
249
+ the SHA that introduced it (run 38667564413 at `d8cd8f3`, 12 assertions on private Herdr 0.9.5),
250
+ and the x86_64 asset is recorded as executed with that receipt; it has not run on aarch64. The
251
+ supply receipt mutant now removes the x86_64 receipt instead of flipping an unexecuted flag,
252
+ because no asset at this pin is unexecuted. Plugin admission (Herdr >= 0.9.0), the plugin
253
+ version and the runtime lock are unchanged.
254
+ - **A host that uses the Claude integration needs `herdr integration install claude` again
255
+ after upgrading to Herdr 0.9.5.** 0.9.5 raises its claude integration from v10 to v11 and leaves pi at v9. Over integrations seeded by
256
+ 0.9.4 it reads claude as `outdated (v10 < v11)`, which the plugin's activation profile files as
257
+ `herdr-integration-outdated`, so the build and pane block [1] refuse by name until the
258
+ reinstall. In the measured 0.9.4-seeded private sandbox, the reinstall changed only the hook's
259
+ version line; the pi extension and the Claude settings stayed byte-identical. The plugin README
260
+ and the launch-rail document say so.
261
+
262
+ ### Release boundary and verification
263
+
264
+ - **Scope.** A core minor over `v0.36.1`: #143 at `3a65c8d`, the Herdr 0.9.5 pin at `d8cd8f3`
265
+ and its CI record at `dbb8a32`, and the skill fix at `4968ffd`. Not in it: #142 (the ACP
266
+ thinking option), and the default thinking level of a new durable session named by a model
267
+ without `:<level>`, which starts at `off` where pi starts at its configured default; that is
268
+ recorded on #142 and not changed here. The Herdr manifest stays 0.36.0; plugin 0.37.0 is a
269
+ separate cut after the core is published.
270
+ - **Local evidence before this preparation is focused, not a whole pass.** Each affected
271
+ qualification group (PARTIAL) measured its own change with a green control, and none is
272
+ carried to another. #143 killed 81/81 in the `check-pi-durable-beside` group. The supply
273
+ receipt mutant re-aimed at `dbb8a32` killed with its whole `check-herdr-supply` group, 11/11;
274
+ that commit skipped CI, so the re-aimed mutant has no CI run yet. The skill fix killed 82/82 in
275
+ the `check-pi-durable-beside` group (receipt `d934e43c4dad5dc28b49a3a85c5a133d126df9558f2bc260087c1b34cf7422f9`),
276
+ with 900 of the 982 committed claims not run. The qualification body has not run on any of them.
277
+ - **Unpublished candidate carrier.** As in 0.36.1, `plugins/herdr/runtime-lock.json` names the
278
+ closed `herdr-checkout` source, because 0.37.0 has no published integrity yet. The npm 0.36.1
279
+ bytes and every existing tag are unchanged. Re-pinning registry bytes is the separate Herdr
280
+ 0.37.0 cut, after the operator publishes core 0.37.0.
281
+ - **No local static floor; it is the exact CI's.** `check:hermetic` carries
282
+ `check-herdr-plugin-build` and `check-herdr-sandbox`, which must not run on the operator host,
283
+ and `release-gate`'s first MUST step is `pnpm run check:full`. By the operator's decision for
284
+ this cut only, `check:full` was not run locally and is owed whole to the prepared SHA's CI.
285
+ The decision is not inherited by a later cut.
286
+ - **LIVE, taken step by step, not as `release-gate --cut`.** The gate's 23 non-static MUST steps
287
+ and its BEHAVIOR step ran in the gate's own order, command, environment and working directory,
288
+ stopping at the first red, on the frozen candidate (`4968ffd` with this preparation's edits),
289
+ with the candidate fingerprint the same before and after each run. The first run passed steps
290
+ 1-18 and failed `smoke-mux-lifecycle-live`: its pi-native sibling (`openai-codex/gpt-6-luna`)
291
+ was alive and answered with a shell call and "ACK" but never called the callback tool within
292
+ 300 s. No input of that step changed in this cut, and the cause was not measured. By the
293
+ operator's choice it was run again once, unchanged, with steps 1-18 reused: steps 19-23 and the
294
+ BEHAVIOR step then passed. **MUST 23/23 PASS (18 + 5 on the second run), SKIP 0; BEHAVIOR 1/1
295
+ PASS.** `smoke-mux-lifecycle-live` passed 81 checks, `smoke-codex-fresh-live` 66 assertions
296
+ against an app-server started for each run in its own tmux session (named pane pid, a child
297
+ holding the kernel LISTEN inode, `gpt-5.6-luna` and `openai-codex/gpt-5.6-luna`, stopped by one
298
+ TERM after the run), and `smoke-pi-durable-fresh-live` 36 assertions. The gate sessions held no
299
+ ambient identity carrier. This is local LIVE evidence, not a release-gate verdict and not the
300
+ exact CI.
301
+ - **Exact CI owes the whole floor.** The prepared SHA's exact CI (the four required jobs, the
302
+ whole qualification body over the 982 committed claims, the re-aimed supply mutant included,
303
+ and `check-herdr-sandbox` on pinned Herdr 0.9.5) is the next checkpoint and is not presumed
304
+ PASS.
305
+ - **Publication boundary.** No make artifact, core tag, GitHub Release or npm publication is
306
+ claimed; they wait for the exact CI, the make decision and the operator.
307
+
7
308
  ## 0.36.1 - 2026-10-14
8
309
 
9
310
  ### ACP
package/CONTRIBUTING.md CHANGED
@@ -30,7 +30,7 @@ pnpm check # everyday core (prints wall time; <=60s on the referenc
30
30
  pnpm run check:full # full deterministic floor — the required PR gate
31
31
  ```
32
32
 
33
- The deterministic floor is tiered (#70). `pnpm check` is the everyday core (biome, tsc, the vitest lanes, and the fast contract gates); `pnpm run check:full` adds the hermetic-integration and package/install tiers — including `check-gate-manifests`, the qualification HEAD (runner self-test, manifest-set validation, declared lane inventory; zero COMMITTED mutants executed — the self-test runs only its synthetic fixture mutants in tmp fixture repos — ~20s), but not the separately scheduled mutant-EXECUTING body `check-gate-qualification`, which CI runs on a branch push whose diff touched the qualification surface (and unconditionally on dispatch or the weekly schedule). Development never runs that whole body: a gate, mutant or matrix change runs only its affected exact-argv groups once, as PARTIAL receipts (`./run.sh check-gate-qualification --group '<argv JSON>' --receipt <absolute path outside the repo>`), and the whole body runs once per cut, in the prepared SHA's CI. Exact membership is the named `check:*` scripts in `package.json`. Run `check:full` once on your frozen commit candidate — the pre-commit hook (`.husky/pre-commit`) carries only fast static checks (whitespace, lint, typecheck), not the full floor, so a green `pnpm run check:full` before commit is the evidence that your change holds (scheduling contract: AGENTS.md "Verification scheduling"). No install or build lifecycle script installs git hooks: a global `core.hooksPath` guard that chains to repository-local hooks runs its own checks, then delegates — to `.husky/pre-commit` here, unless an executable `.git/hooks/pre-commit` takes precedence.
33
+ The deterministic floor is tiered (#70). `pnpm check` is the everyday core (biome, tsc, the vitest lanes, and the fast contract gates); `pnpm run check:full` adds the hermetic-integration and package/install tiers — including `check-gate-manifests`, the qualification HEAD (runner self-test, manifest-set validation, declared lane inventory; zero COMMITTED mutants executed — the self-test runs only its synthetic fixture mutants in tmp fixture repos — ~20s), but not the separately scheduled mutant-EXECUTING body `check-gate-qualification`, which CI runs only on the weekly schedule or a manual `qualify=true` dispatch, as a drift diagnostic outside release acceptance (#144). Development never runs that whole body: a gate, mutant or matrix change runs only its affected exact-argv groups once, as PARTIAL receipts (`./run.sh check-gate-qualification --group '<argv JSON>' --receipt <absolute path outside the repo>`), and no cut waits for the whole body. Exact membership is the named `check:*` scripts in `package.json`. Run `check:full` once on your frozen commit candidate — the pre-commit hook (`.husky/pre-commit`) carries only fast static checks (whitespace, lint, typecheck), not the full floor, so a green `pnpm run check:full` before commit is the evidence that your change holds (scheduling contract: AGENTS.md "Verification scheduling"). No install or build lifecycle script installs git hooks: a global `core.hooksPath` guard that chains to repository-local hooks runs its own checks, then delegates — to `.husky/pre-commit` here, unless an executable `.git/hooks/pre-commit` takes precedence.
34
34
 
35
35
  For changes that touch backend launch, session lifecycle, or `_meta` shape, also run
36
36
  the live ACP smokes that cover the touched rail — at minimum:
package/README.md CHANGED
@@ -91,8 +91,13 @@ incomplete, drifted or mixed supply refuses by name.
91
91
  ```bash
92
92
  entwurf pi-durable --provider <provider> --model <model-id> --width task-wide
93
93
  entwurf pi-durable --continue
94
+ entwurf pi-durable --resume
94
95
  ```
95
96
 
97
+ `--continue` opens this directory's newest durable session. `--resume` lists its
98
+ sessions, most recently written first, by creation time, garden id and last write, and
99
+ reopens the one you choose as it was saved; a cancelled choice opens nothing.
100
+
96
101
  The contact adds garden identity and two-way mailbox communication. Entwurf owns the
97
102
  thin app/TUI composition (shipped as an emitted JS carrier); execution, models/auth, queues,
98
103
  SQLite, transcripts and recovery remain the upstream SDK's:
package/VERIFY.md CHANGED
@@ -95,8 +95,7 @@ that moved out of `scripts/` and into a file beside its subject would otherwise
95
95
  ### The canonical floor — two entry points
96
96
 
97
97
  - **Deterministic floor — two tiers (#70):** `pnpm check` is the everyday CORE — toolchain (lint + typecheck), the vitest lanes, and the pure-unit / behavioral-contract / source-topology gates plus the cheap static coherence checks. It prints its own total wall time; acceptance is ≤60s on the reference host `oracle` (an operator measurement, never a hard wall-clock gate on arbitrary hosts). `pnpm run check:full` is the FULL deterministic floor — the core plus the hermetic-integration and package/install tiers — and is what the frozen-candidate protocol, push CI, release-gate, and `prepublishOnly` run. Exact membership is the named `check:*` group scripts in `package.json` (the executable SSOT — this document records meaning and principles, not the command list); a gate changes tier by semantic-class decision, never by getting faster or slower. One core member assumes a build output: the beside test `pi-extensions/entwurf-control.test.ts` (reached through `check-tests-beside-behavior`) registers the COMPILED bridge and refuses by name when it is absent. `prepare` normally builds it at install; after an `--ignore-scripts` install or a bridge source change, run `pnpm run build-bridge` (in the sandbox candidate when verifying one) before the core. The FULL tier carries the qualification HEAD (`check-gate-manifests`, through `check:hermetic`); the everyday core does not, and neither tier carries the separately scheduled mutant-executing body (`check-gate-qualification`).
98
- - **Discriminating power of that floor:** `./run.sh check-gate-qualification` (scheduled, not ambient: the whole body runs only as the bare call — in the CI `check` job on a branch push that touched the qualification surface, and — for a cut — at the prepared SHA, where the exact-SHA release oracle requires that CI step once and the prepared state awaits it, never presumed PASS; a cut therefore batches its commits into that one prepared push (#132 took the cut's body off the local `release-gate`). Development runs no whole body (#133): a lane that changes a gate/mutant/matrix runs its affected exact-argv groups once, after review, as PARTIAL receipts — `./run.sh check-gate-qualification --group '<argv JSON>' --receipt <absolute path outside the repo>`, whose arguments reach the runner's parser unchanged and are refused there by name, before any body or snapshot, when malformed, missing or repeated. A receipt is a measurement of one group, never a qualification pass. Neither form is inside the default check chains; a semver TAG push triggers no CI at all, and the exact-SHA evidence a release quotes is whichever run at that commit CARRIES the body — the branch run when the push touched the qualification surface, else a dispatch run; a push that touched none of the qualification surface skips the body, and `workflow_dispatch -f qualify=true` plus a weekly `schedule` run it unconditionally — the exact-SHA release oracle refuses a SHA whose body step did not conclude success) re-plants committed defect mutants (`scripts/mutants/*.json`, one per closed defect class) in an isolated snapshot repo and requires each to turn its gate red **bounded and at its claimed `[QK:<claim>]` signature** — a wrong-reason red fails, a baseline-red control voids the whole group, and the runner is negative-controlled on every run (zero-match/multi-match/survived/wrong-reason/hang/control-red/impurity). This measures whether the deterministic gates still *block* what they claim to block; it is **not a new evidence level** (L0–L5 are untouched) and never substitutes for LIVE evidence. Per-cut records cite claim IDs + killed mutant IDs — "N checks passed" alone is not evidence. `check-agy-permission-matrix` complements it with the enumerated permission contract space (literal cells + stated exclusion rules, oracle independent of the SUT). The gate's HEAD is separable and IS in the floor: `check-gate-manifests` runs the runner self-test, validates the committed manifest set against the origin index, and asserts the declared lane inventory, while executing zero COMMITTED mutants (the self-test runs only its synthetic fixture mutants, in tmp fixture repos) and never snapshotting the repo — three of the five reds qualification has ever produced in CI died in that head, in under five seconds.
99
- - **Push matching is conservative and hunk-aware (#137).** Git ranges read mutant manifests from the named HEAD commit, not a later working tree. Signature sources and the existing deciding machinery always match at file level, including paths that are also subjects. Only TOML subjects (`.toml`) may skip, and only when every mutant's joined `find` span occurs exactly once on both blobs, stays on the same lines, and intersects no zero-context diff hunk. Markdown, JSON, code and unknown subject types remain file-level. An outside-find early return/import/caller change can weaken a code mutant without editing its literal find. A presence/`includes` oracle whose required literal is shorter than the find can be re-satisfied by an out-of-span restatement; a scratch-repo probe measured exactly that false SKIP for `ADMISSION-LEGACY-DOCUMENTED` in `DELIVERY.md`. A later duplicate JSON key wins under `JSON.parse`, which every current JSON data oracle uses. TOML refuses a redefined key, and the current TOML oracles are exact-count/absence checks; a future TOML subject with a presence oracle reopens this boundary. `QUALIFY-FILTER-TOML-ONLY-REFINEMENT` pins Markdown/JSON at file level. Moved, absent, ambiguous, binary or unreadable spans/diffs/manifests run the body with a named reason; renames are compared as delete/add. `--files-from` has no hunk evidence and retains path identity. There is no Herdr filename or release-shape exemption. Span matching is not proof of unchanged kill-power. The rule narrows per-push qualification to those declared TOML spans; forced/scheduled and exact-SHA release qualification remain the backstop. This narrows redundant data-only pushes, never the FULL floor or exact-SHA release body's obligation; a body-less plugin SHA cannot supply the core SHA's evidence.
98
+ - **Discriminating power of that floor:** `./run.sh check-gate-qualification` (scheduled, not ambient: the whole body runs only as the bare call — in the CI `check` job on the weekly `schedule` or a `workflow_dispatch -f qualify=true`, never on a push. It is a drift diagnostic, not a release axis (#144): no cut waits for it and the exact-SHA release oracle reads only the push run's four required jobs. Development runs no whole body (#133): a lane that changes a gate/mutant/matrix runs its affected exact-argv groups once, after review, as PARTIAL receipts — `./run.sh check-gate-qualification --group '<argv JSON>' --receipt <absolute path outside the repo>`, whose arguments reach the runner's parser unchanged and are refused there by name, before any body or snapshot, when malformed, missing or repeated. A receipt is a measurement of one group on its own candidate, never a qualification pass and never coverage of a release. Neither form is inside the default check chains; a semver TAG push triggers no CI at all) re-plants committed defect mutants (`scripts/mutants/*.json`, one per closed defect class) in an isolated snapshot repo and requires each to turn its gate red **bounded and at its claimed `[QK:<claim>]` signature** — a wrong-reason red fails, a baseline-red control voids the whole group, and the runner is negative-controlled on every run (zero-match/multi-match/survived/wrong-reason/hang/control-red/impurity). This measures whether the deterministic gates still *block* what they claim to block; it is **not a new evidence level** (L0–L5 are untouched) and never substitutes for LIVE evidence. Per-cut records cite claim IDs + killed mutant IDs — "N checks passed" alone is not evidence. `check-agy-permission-matrix` complements it with the enumerated permission contract space (literal cells + stated exclusion rules, oracle independent of the SUT). The gate's HEAD is separable and IS in the floor: `check-gate-manifests` runs the runner self-test, validates the committed manifest set against the origin index, and asserts the declared lane inventory, while executing zero COMMITTED mutants (the self-test runs only its synthetic fixture mutants, in tmp fixture repos) and never snapshotting the repo — three of the five reds qualification has ever produced in CI died in that head, in under five seconds.
100
99
  - **The snapshot is source-only (#125).** It replicates the git work surface and never copies an ignored artifact from the checkout. A gate that consumes an ignored build output — the compiled `entwurf-bridge` a pi citizen registers — declares it on each of its mutants (`"build": {"argv": [...], "output": "<dir>"}`, one declaration per gate group). For that group only, the runner builds the output from the snapshot's own bytes before the control, rebuilds it after every mutation and from the restored bytes before the post-control (which must reproduce the baseline digest), never counts a build red as a kill, voids a run whose gate writes into the output, and removes the output when the group ends. The runner self-test owns this as `[QK:QUALIFY-BUILD-*]`.
101
100
  - **Live floor:** `LIVE=1 ./run.sh release-gate <scratch-project-dir> --cut` — `pnpm run check:full` + the v2-native live gates + the ACP plugin acceptance floor. It reports a **two-tier summary**:
102
101
  - **MUST tier** (release-blocking — owns the exit code; "green" applies only here): `pnpm run check:full`, `smoke-entwurf-v2-matrix-live`, `check-bridge`, `doctor-pi-provider` (#81 — `check-bridge` proves the launcher this checkout SHIPS; this proves the invocation the operator's pi provider actually EXECS, by booting it and requiring the entwurf verb set back, because `command -v` answers yes for a command that exits 127; wired as a step on 2026-08-19 after a relocated pnpm cmd-shim cost a cut sixteen LIVE steps before the same fact surfaced at `smoke-acp-bundled-mcp-live`), the resident-garden-guard zero-token half (record birth / record-keyed socket / attach-on-reopen), the `smoke-acp-*-live` ACP plugin smokes (socket-citizen / raw-turn / overlay / provider / session-reuse / carrier-augment / memory-containment / rgg / mcp / skill / bundled-mcp / v2-send), the axis wired in on 2026-07-31 that the aggregate had simply never listed (`smoke-claude-native-resume-live`), `smoke-entwurf-chain-live` — the cross-harness delivery chain (native Claude Code → pi GPT → pi ACP Sonnet → mailbox terminus) proving sender identity and replyability at every hop plus a real read receipt at the end — the integrated `smoke-mux-lifecycle-live` (its own note below), and the two OMP steps 0.16.0 wired: `smoke-omp-receive-live` (the addressed roundtrip into a live omp citizen; it reads the capability registry and decides its own outcome rather than passing by default) and `smoke-omp-fresh-live` (the clause 7 receipt the release stop now requires). (`smoke-session-id-name` is gone — #50 C3: its `--session-id`/`--name` substrate has no entwurf consumer anymore.)
@@ -116,7 +115,7 @@ that moved out of `scripts/` and into a file beside its subject would otherwise
116
115
  >
117
116
  > A cut that touches the prompt-lifecycle contract (no wall clock on a running turn) owes one long-turn acceptance the aggregate floor is too short to carry: `LIVE=1 ./run.sh smoke-acp-long-turn-live` drives a real turn whose tool work outlasts the retired 600s cutoff and requires exactly one cold ACP bootstrap in the transcript. It takes >12 minutes by construction and is on-demand, not part of `release-gate`.
118
117
  >
119
- > **The integrated mux lifecycle IS a release-gate MUST.** `LIVE=1 ./run.sh smoke-mux-lifecycle-live` enters through a real MCP `tools/call` on the shipped bridge launcher and follows one citizen the whole way: fresh-call launch receipt, the sibling's own nonce callback whose SENDER ENVELOPE is the address, an `entwurf_v2` control-socket send that lands in the sibling's own transcript, `entwurf_resume_call` REFUSED while that citizen is live, a stable-handle close proving pane and socket gone with the record preserved, delivery to the dormant citizen refused honestly, then the public `entwurf_resume_call` — whose LAUNCH and OBSERVATION receipts stay apart — and finally an `entwurf_v2` send the resumed session answers with a fact it was told BEFORE the window closed. That last step is the point: a socket answering under the same garden id proves a process stood up at that address, and only the recall proves the same conversation came back. Both pi provider shapes are driven to it (native `openai-codex/gpt-6-luna` and recorded-ACP `entwurf/claude-sonnet-5-5`, the only shape that re-injects a bridge extension), and the Claude Code cell ends where its capability ends: its resume is refused as `target-not-pi` with no window opened and no lock residue (the per-gid coordination lock is released).
118
+ > **The integrated mux lifecycle IS a release-gate MUST.** `LIVE=1 ./run.sh smoke-mux-lifecycle-live` enters through a real MCP `tools/call` on the shipped bridge launcher and follows one citizen the whole way: fresh-call launch receipt, the sibling's own nonce callback whose SENDER ENVELOPE is the address, an `entwurf_v2` control-socket send that lands in the sibling's own transcript, `entwurf_resume_call` REFUSED while that citizen is live, a stable-handle close proving pane and socket gone with the record preserved, delivery to the dormant citizen refused honestly, then the public `entwurf_resume_call` — whose LAUNCH and OBSERVATION receipts stay apart — and finally an `entwurf_v2` send the resumed session answers with a fact it was told BEFORE the window closed. That last step is the point: a socket answering under the same garden id proves a process stood up at that address, and only the recall proves the same conversation came back. Both pi provider shapes are driven to it (native `openai-codex/gpt-6.1-sol:low` and recorded-ACP `entwurf/claude-sonnet-5-5`, the only shape that re-injects a bridge extension), and the Claude Code cell ends where its capability ends: its resume is refused as `target-not-pi` with no window opened and no lock residue (the per-gid coordination lock is released).
120
119
  >
121
120
  > One cell cannot be fully fenced, and that is recorded rather than glossed: the recorded-ACP pi cell runs under the operator's REAL home, because its provider spawns `claude` as a child that authenticates from there — measured, a fenced HOME kills that turn with `Authentication required` before the model is ever reached, and `CLAUDE_CONFIG_DIR` alone does not fix it. That is the same trade `smoke-acp-bundled-mcp-live` already makes. While that cell runs, its citizen's control socket and per-gid lock exist under the operator's own `~/.pi/entwurf-control` and `~/.pi/entwurf-v2-locks`; its meta store stays fixture, so no garden record is minted outside the fixture, and the run ends by proving all six real roots hold the entry sets they started with, with no fixture garden id and no leftover lock.
122
121
  >
@@ -210,16 +209,19 @@ that moved out of `scripts/` and into a file beside its subject would otherwise
210
209
 
211
210
  Do not collapse source, package, fixture, and native-host evidence into one “green.”
212
211
 
213
- **Native durable contact (#129, #130 carrier).** `check-pi-durable-beside` is the deterministic
214
- beside-test/mutant coordinate in `check:contracts`: the adapter, the installed carrier/SDK-set
215
- verifier, the preflight, the owner join, the carrier's relocation grammar, resolver and
216
- maintainer emitter (its `--check` reads only the owned in-repo source, #141; the overlay patch is
217
- retired, and `--origin <clone>` checks provenance only), and the bootstrap's explicit `--native-module` ingress
218
- (#130 P2) with its paired `--native-module-dir` (#134), driven through the packaged `main`'s own
212
+ **Native durable contact (#129, #130 carrier).** Three deterministic beside-test/mutant
213
+ coordinates in `check:contracts` split the durable contact by the file that carries each claim's QK
214
+ (#144): a carrier or native-module mutant runs its one file, the rest run four. `check-pi-durable-beside` holds the adapter, the installed
215
+ carrier/SDK-set verifier, the preflight and the owner join. `check-pi-durable-carrier` holds the
216
+ carrier's relocation grammar, resolver and maintainer emitter (its `--check` reads only the owned
217
+ in-repo source, #141; the overlay patch is retired, and `--origin <clone>` checks provenance only)
218
+ and the task footer and sandboxed children described below. `check-pi-durable-native-module` is the coordinate of
219
+ the bootstrap's explicit `--native-module` ingress
220
+ (#130 P2) with its paired `--native-module-dir` (#134). That ingress is driven through the packaged `main`'s own
219
221
  seams: initialization before the TUI and the open, named refusals, the identity and directory
220
222
  guards, the top-level `*.extension.mjs` filter and byte-wise order, cross-module name refusals, the
221
- contact-first order by reference, and the bridge spawn *spec* (not the child's inheritance). The
222
- carrier's task footer (#134) is observed in ONE sandboxed child that loads the committed carrier
223
+ contact-first order by reference, and the bridge spawn *spec* (not the child's inheritance). In
224
+ `check-pi-durable-carrier`, the carrier's task footer (#134) is observed in ONE sandboxed child that loads the committed carrier
223
225
  through its own resolver: the real carrier runtime opened and closed with no model (graph observed
224
226
  for the session, `/tasks` toggling only the panel), then continued after one native background task
225
227
  was committed into that session through the SDK's public `Conversation.commit` (the carrier's graph
@@ -227,8 +229,15 @@ holds that node and the badge counts it, `pending` while recovered), and the car
227
229
  `durableLayout` drawn by the published pi-tui renderer on a fake terminal across rows 1–8 × cols
228
230
  1–12, count changes and resizes, against the pinned upstream screen for the zero-task case. Its
229
231
  editor is a fixed stand-in: the real `CustomEditor`, overlays, emoji width and a consumer's own task
230
- are the visible-terminal and consumer subjects. `check-pi-runtime-version` asks the
231
- same verifier whether this checkout resolves exactly the pinned SDK set (the native set; the PATH
232
+ are the visible-terminal and consumer subjects. The 1.2 bootstrap child also observes `--resume`
233
+ reopening the chosen session and cancelling to nothing (#143). Two more sandboxed children reach the
234
+ reference app's settings and prompt mapping: one drives the real bootstrap against a loopback
235
+ WebSocket Responses endpoint, whose received frames decide the forwarded transport and its
236
+ continuation and the reference compaction policy (no background summary; blocking and overflow
237
+ kept, #143); the other renders the carrier prompt's skills section with no model, against a fixture
238
+ of both settings scopes, an absolute entry, a same-name pair and a wrong-base decoy.
239
+ `check-pi-runtime-version` asks the
240
+ same installed verifier (`check-pi-durable-beside`) whether this checkout resolves exactly the pinned SDK set (the native set; the PATH
232
241
  host is setup's subject), and `check-pi-import-surface` asserts the carrier fence. The separate
233
242
  `check-pi-durable-contact`, `check-pi-durable-send` and `check-pi-durable-receive` are
234
243
  CHECKOUT-ONLY SDK/contact gates: they run the checkout's own carrier — verified first, refused by
@@ -253,7 +262,7 @@ initializing only its top-level `*.extension.mjs` (#134) and a directory without
253
262
  before anything opens — and the HOST kept a separate subject — a real pi 1.1.0
254
263
  binary (the previous generation) beside the pinned native set is a named pi FAIL with zero Pi wiring while pi-durable still
255
264
  PASSes — not native admission. The carrier's rebuild
256
- equality is the owned source's emission (#141): the beside claim `PI-DURABLE-CARRIER-EMIT-SOURCE-EQUAL`
265
+ equality is the owned source's emission (#141): the carrier claim `PI-DURABLE-CARRIER-EMIT-SOURCE-EQUAL`
257
266
  on every floor, `emit-pi-durable-carrier --check` as its CLI. The emitter's exact Node is red in the CI
258
267
  `check` job (`ENTWURF_REQUIRE_EMITTER_NODE=1`) and a named SKIP on a host running another Node, not
259
268
  acceptance there. First-release visible fresh/callback and native
@@ -262,10 +271,10 @@ caller/target/cross-harness LIVE are owed by `smoke-pi-durable-fresh-live`, a re
262
271
 
263
272
  | Axis | Required proof | Limit |
264
273
  |---|---|---|
265
- | Source | `pnpm run check:full` + the prepared SHA's CI `./run.sh check-gate-qualification` step | Does not prove an installed consumer. |
274
+ | Source | `pnpm run check:full` in the prepared SHA's CI `check` job | Does not prove an installed consumer. Kill-power of the committed claims is not re-measured per release (#144); the release record says so and lists any earlier-candidate PARTIAL separately. |
266
275
  | Packed install | `check-pack-install` | Real tarball, but checkout-visible. |
267
276
  | Linux artifact consumer | required `check-install-container` CI job against one preserved candidate | Fixtures prove package/oracle shape, not a real Claude lifecycle. |
268
- | Exact release commit | all required CI jobs green, and the `check` job's qualification body step concluded success, at the exact SHA | A different green SHA is not transferable evidence. |
277
+ | Exact release commit | the exact SHA's push run: all four required CI jobs green (the qualification body is not read, #144) | A different green SHA is not transferable evidence. |
269
278
  | macOS Entwurf-only install | required `macos-install-surface` CI job at the exact release SHA | Shape-only, CERTIFIED (CI): certifies the Entwurf-only install path on macOS only — never Claude/Copilot/OMP/agy wiring, the pi rail, ACP or mux. Promoted from non-voting (`continue-on-error`) to required in 0.20.0 after its first CERTIFIED (CI) green on a GitHub Actions `macos-latest` runner (not a physical host): run 34303884286 @ `70eda03` (2026-09-09), 65s, all 10 steps success — the packed candidate installed clean, `entwurf --help` and `entwurf check-bridge` ran (the latter listing the seven current `entwurf-bridge` MCP tools), an all-harness-absent `entwurf setup` reached `result: green` across the five documented SKIP probes (`pi`/`claude`/`agy`/`copilot`/`omp`), and five checked paths (`.pi`, `settings.json`, `.gemini`, `.copilot`, `auth.json.bak`) plus a byte-identical `auth.json` proved zero harness/credential writes. A macOS runner failure now blocks every release cut, the same as any other required job. |
270
279
  | LIVE runtime | `LIVE=1 ./run.sh release-gate <scratch> --cut` plus any shipped on-demand backend axis | `--cut` enforces `SKIP=0`; a red wired gate blocks the cut. |
271
280
  | Native Claude host | installed strict doctor against a new real session | Missing live join is `NOT CERTIFIED`, not a fixture PASS. |
@@ -508,7 +517,7 @@ Pass: user/assistant turns accumulate normally; the transcript is not broken/emp
508
517
 
509
518
  The minimum passing bar:
510
519
 
511
- 1. **Deterministic floor green:** `pnpm run check:full` passes (the core tier plus the hermetic-integration and package/install tiers, incl. `check-pack`), plus the `./run.sh check-gate-qualification` step green in the exact-SHA CI run of the same prepared candidate (criterion 2's run).
520
+ 1. **Deterministic floor green:** `pnpm run check:full` passes (the core tier plus the hermetic-integration and package/install tiers, incl. `check-pack`), in the exact-SHA CI push run of the same prepared candidate (criterion 2's run). The qualification body is not a criterion (#144).
512
521
  2. **All four required CI jobs green on the exact release commit:** `check`, `install-surface`, the required Linux `artifact-consumer`, and `macos-install-surface` — promoted from non-voting to required in 0.20.0 (see the release acceptance axes table above for what its green run does and does not certify); preserve the Linux artifact-consumer's tarball digest and image identity. A macOS runner failure now blocks the cut like any other required job.
513
522
  3. **Live floor MUST green:** `LIVE=1 ./run.sh release-gate <dir> --cut` exits 0 reporting `MUST PASS=N FAIL=0 SKIP=0`; with `--cut` a single SKIP is red, so the exit code itself now carries this condition. A BEHAVIOR FAIL is advisory, not blocking.
514
523
  4. **Native-host doctor green where the Claude meta-bridge is claimed:** a new post-install Claude session exists, live evidence is present, and the installed `doctor-meta-bridge` exits 0. `NOT CERTIFIED` is a release failure for that host, not a skip.
@@ -358,6 +358,7 @@ tree (for example an override that binds pi-durable's `pi-ai` to an older publis
358
358
  ```bash
359
359
  entwurf pi-durable --provider <provider> --model <exact catalog id> --width task-wide
360
360
  entwurf pi-durable --continue # this directory's newest durable session
361
+ entwurf pi-durable --resume # choose one of this directory's durable sessions
361
362
  ```
362
363
 
363
364
  The bootstrap imports only the compiled closure shipped beside it
@@ -107,9 +107,24 @@ import * as fs from "node:fs";
107
107
  import * as path from "node:path";
108
108
  import { Client } from "@modelcontextprotocol/sdk/client/index.js";
109
109
  import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
110
- import { defaultMetaMailboxDir, defaultMetaReceiversDir, defaultMetaSendersDir, defaultMetaSessionsDir, readAddressableMetaIdentity, readMetaReceiverMarker, readMetaSenderMarker, requireGardenId, upsertMetaSession, writeMetaReceiverMarker, writeMetaSenderMarker, } from "./lib/meta-session.js";
110
+ import { defaultMetaMailboxDir, defaultMetaReceiversDir, defaultMetaSendersDir, defaultMetaSessionsDir, listAllMetaIdentitiesDir, readAddressableMetaIdentity, readMetaReceiverMarker, readMetaSenderMarker, requireGardenId, upsertMetaSession, writeMetaReceiverMarker, writeMetaSenderMarker, } from "./lib/meta-session.js";
111
111
  /** The backend id this contact mints under. */
112
112
  export const PI_DURABLE_BACKEND = "pi-durable";
113
+ /**
114
+ * The garden ids the record store holds for these durable sessions (#143 `--resume`), read only: a session no record
115
+ * names is absent, and an unreadable record is counted, never guessed.
116
+ */
117
+ export function piDurableGardenIds(nativeSessionIds, sessionsDir = defaultMetaSessionsDir()) {
118
+ const wanted = new Set(nativeSessionIds);
119
+ const { identities, errors } = listAllMetaIdentitiesDir(sessionsDir);
120
+ const gardens = new Map();
121
+ for (const identity of identities) {
122
+ if (identity.backend === PI_DURABLE_BACKEND && wanted.has(identity.nativeSessionId)) {
123
+ gardens.set(identity.nativeSessionId, identity.gardenId);
124
+ }
125
+ }
126
+ return { gardens, unreadable: errors.length };
127
+ }
113
128
  /** The durable Extension's name, owned exactly. */
114
129
  export const PI_DURABLE_EXTENSION_NAME = "entwurf";
115
130
  /** Every bridge tool this contact exposes. A tool outside this list is not callable here. */
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@junghanacs/entwurf",
3
- "version": "0.36.1",
3
+ "version": "0.37.1",
4
4
  "description": "Visible sibling sessions across independent agent harnesses: launch in Herdr or tmux, reopen pi in tmux, and deliver messages by garden id; native bridges and Claude/Cortex ACP adapters.",
5
5
  "license": "MIT",
6
6
  "author": {
@@ -123,7 +123,8 @@
123
123
  "husky": "^9.1.7",
124
124
  "rregex": "1.13.1",
125
125
  "typescript": "^6.0.2",
126
- "vitest": "4.1.9"
126
+ "vitest": "4.1.9",
127
+ "ws": "8.21.3"
127
128
  },
128
129
  "scripts": {
129
130
  "prepare": "npm run --silent build-bridge 1>&2",
@@ -193,7 +194,7 @@
193
194
  "check:core": "pnpm run check:toolchain && pnpm run check:vitest && pnpm run check:contracts",
194
195
  "check:toolchain": "pnpm lint && pnpm typecheck",
195
196
  "check:vitest": "./run.sh check-mux-fresh-call && ./run.sh check-acp-sdk-surface && ./run.sh check-pi-queue-oracle && ./run.sh check-tests-beside-behavior",
196
- "check:contracts": "./run.sh check-demo-reproducibility && ./run.sh check-shell-quote && ./run.sh check-entwurf-session-identity && ./run.sh check-meta-session && ./run.sh check-meta-v3-record && ./run.sh check-mailbox-receipt-state && ./run.sh check-entwurf-capabilities && ./run.sh check-harness-admission-parity && ./run.sh check-capability-bundle-reach && ./run.sh check-meta-mailbox-state-write && ./run.sh check-meta-receiver-marker && ./run.sh check-meta-capability-source && ./run.sh check-model-lock && ./run.sh check-dep-versions && ./run.sh check-node-floor-coherence && ./run.sh check-claude-floor-coherence && ./run.sh check-copilot-statusline && ./run.sh check-pi-import-surface && ./run.sh check-env-namespace && ./run.sh check-pi-runtime-version && ./run.sh check-pi-preflight && ./run.sh check-project-trust-handler && ./run.sh check-entwurf-v2-contract && ./run.sh check-entwurf-v2-send && ./run.sh check-entwurf-v2-runner && ./run.sh check-control-send-receipt && ./run.sh check-compaction-send-guard && ./run.sh check-entwurf-resume-args && ./run.sh check-entwurf-v2-native-push && ./run.sh check-entwurf-v2-production && ./run.sh check-entwurf-v2-surface && ./run.sh check-entwurf-bridge-pi-free && ./run.sh check-resume-launch-identity && ./run.sh check-mux-placement && ./run.sh check-mux-launch && ./run.sh check-mux-resume-call && ./run.sh check-mux-parent-artifact && ./run.sh check-mux-launcher-fence && ./run.sh check-entwurf-v2-visible-resume && ./run.sh check-control-socket-path && ./run.sh check-meta-listing && ./run.sh check-entwurf-fact-provider && ./run.sh check-herdr-placement && ./run.sh check-herdr-fresh-call && ./run.sh check-herdr-supply && ./run.sh check-fresh-call-dispatch && ./run.sh check-entwurf-peers-surface && ./run.sh check-entwurf-self-address && ./run.sh check-entwurf-deliverability && ./run.sh check-native-push-adapter && ./run.sh check-native-push-register && ./run.sh check-auth-boundary && ./run.sh check-acp-overlay && ./run.sh check-acp-tool-surface && ./run.sh check-acp-event-mapper && ./run.sh check-acp-prompt-builder && ./run.sh check-acp-config && ./run.sh check-acp-session-store && ./run.sh check-acp-carrier-augment && ./run.sh check-acp-foreground-only && ./run.sh check-acp-set-model-readback && ./run.sh check-acp-vendor-rejection && ./run.sh check-codex-sender-identity && ./run.sh check-codex-native-push && ./run.sh check-pi-durable-beside",
197
+ "check:contracts": "./run.sh check-demo-reproducibility && ./run.sh check-shell-quote && ./run.sh check-entwurf-session-identity && ./run.sh check-meta-session && ./run.sh check-meta-v3-record && ./run.sh check-mailbox-receipt-state && ./run.sh check-entwurf-capabilities && ./run.sh check-harness-admission-parity && ./run.sh check-capability-bundle-reach && ./run.sh check-meta-mailbox-state-write && ./run.sh check-meta-receiver-marker && ./run.sh check-meta-capability-source && ./run.sh check-model-lock && ./run.sh check-dep-versions && ./run.sh check-node-floor-coherence && ./run.sh check-claude-floor-coherence && ./run.sh check-copilot-statusline && ./run.sh check-pi-import-surface && ./run.sh check-env-namespace && ./run.sh check-pi-runtime-version && ./run.sh check-pi-preflight && ./run.sh check-project-trust-handler && ./run.sh check-entwurf-v2-contract && ./run.sh check-entwurf-v2-send && ./run.sh check-entwurf-v2-runner && ./run.sh check-control-send-receipt && ./run.sh check-compaction-send-guard && ./run.sh check-entwurf-resume-args && ./run.sh check-entwurf-v2-native-push && ./run.sh check-entwurf-v2-production && ./run.sh check-entwurf-v2-surface && ./run.sh check-entwurf-bridge-pi-free && ./run.sh check-resume-launch-identity && ./run.sh check-mux-placement && ./run.sh check-mux-launch && ./run.sh check-mux-resume-call && ./run.sh check-mux-parent-artifact && ./run.sh check-mux-launcher-fence && ./run.sh check-entwurf-v2-visible-resume && ./run.sh check-control-socket-path && ./run.sh check-meta-listing && ./run.sh check-entwurf-fact-provider && ./run.sh check-herdr-placement && ./run.sh check-herdr-fresh-call && ./run.sh check-herdr-supply && ./run.sh check-fresh-call-dispatch && ./run.sh check-entwurf-peers-surface && ./run.sh check-entwurf-self-address && ./run.sh check-entwurf-deliverability && ./run.sh check-native-push-adapter && ./run.sh check-native-push-register && ./run.sh check-auth-boundary && ./run.sh check-acp-overlay && ./run.sh check-acp-tool-surface && ./run.sh check-acp-event-mapper && ./run.sh check-acp-prompt-builder && ./run.sh check-acp-config && ./run.sh check-acp-session-store && ./run.sh check-acp-carrier-augment && ./run.sh check-acp-foreground-only && ./run.sh check-acp-set-model-readback && ./run.sh check-acp-vendor-rejection && ./run.sh check-codex-sender-identity && ./run.sh check-codex-native-push && ./run.sh check-pi-durable-beside && ./run.sh check-pi-durable-carrier && ./run.sh check-pi-durable-native-module",
197
198
  "check:hermetic": "./run.sh check-bridge-delivery && ./run.sh smoke-pi-attach && ./run.sh check-fresh-cut-gate && ./run.sh check-hook-launch-topology && ./run.sh check-meta-hook-session-switch && ./run.sh check-copilot-birth-hook && ./run.sh check-copilot-receive-arm && ./run.sh check-copilot-launch && ./run.sh check-pi-launch && ./run.sh check-codex-app-server-launch && ./run.sh check-meta-identity-consumers && ./run.sh check-socket-probe && ./run.sh smoke-meta-honesty && ./run.sh check-meta-doctor-oracle && ./run.sh check-agy-permission-matrix && ./run.sh smoke-agy-statusline-state && ./run.sh smoke-copilot-statusline-state && ./run.sh smoke-copilot-mcp-state && ./run.sh smoke-omp-bridge-state && ./run.sh smoke-omp-mcp-state && ./run.sh smoke-omp-receive-state && ./run.sh check-omp-birth-hook && ./run.sh check-omp-receive-arm && ./run.sh check-omp-fresh-preflight && ./run.sh smoke-agy-hooks-state && ./run.sh smoke-pi-provider-state && ./run.sh smoke-user-scope-citizen && ./run.sh smoke-meta-prune && ./run.sh smoke-meta-keyset-guard && ./run.sh check-meta-manifest-schema && ./run.sh check-entwurf-control-rpc && ./run.sh check-entwurf-bridge-boot && ./run.sh check-probe-bridge-command && ./run.sh check-meta-facts && ./run.sh check-peer-facts && ./run.sh check-herdr-plugin && ./run.sh check-herdr-plugin-profile && ./run.sh check-herdr-plugin-build && ./run.sh check-herdr-runtime-bootstrap && ./run.sh check-herdr-activation && ./run.sh check-agy-sender-identity && ./run.sh check-acp-provider-surface && ./run.sh check-acp-stop-reason && ./run.sh check-acp-prompt-lifecycle && ./run.sh check-acp-usage-accounting && ./run.sh check-acp-launch-namespace && ./run.sh check-acp-stream-hooks && ./run.sh check-acp-backend-preflight && ./run.sh check-acp-session-reuse && ./run.sh check-typing-call-fence && ./run.sh check-gate-manifests && ./run.sh check-release-gate-outcomes && ./run.sh check-probe-ordering && ./run.sh check-probe-cli-shim && ./run.sh check-acp-cortex && ./run.sh check-codex-bridge-identity && ./run.sh check-pi-bridge-sender && ./run.sh check-pi-mcp-register && ./run.sh check-pi-mcp-bridge && ./run.sh check-codex-birth-hook && ./run.sh smoke-codex-config-state && ./run.sh smoke-codex-birth && ./run.sh check-herdr-sandbox",
198
199
  "check:package": "./run.sh check-install-surface && ./run.sh smoke-meta-install-state && ./run.sh smoke-agy-install-state && ./run.sh smoke-setup-verdict && ./run.sh check-pack-pin-matcher && ./run.sh check-pack-consumer-roots && ./run.sh check-package-source-routing && ./run.sh check-install-preflight && ./run.sh check-pack"
199
200
  },