Repair native install-plan acceptance after the hcom relaxation - #723

…Sol max (published v3.8.51 + #15167 + the cited affinity patch) (#744)

### Scope

- What this PR changes, in one or two sentences: records the decision that the NativeStack OmniRoute gateways keep true GPT-6.1 Sol max (published `v3.8.51` content plus upstream PR 15167 plus the cited local session-affinity patch) instead of switching to the published-only package, with the wire evidence, the affinity commit as a public patch file (sha256) and the build facts of the composition. Nothing running changes: the planned 15:00Z swap was cancelled before any unit changed. The second host's claim is scoped to what is observed: NativeStack 20128 delivers max; on 2604 the co-op's read-back of 16:50Z (relayed, private record) gave HTTP 200 on the `-max`, `-xhigh`, bare and `astra-max` routes and upstream `max` on `sol-max` for 21128; the 2604 plan rows, which since #713 select the published 3.8.51 with Sol at xhigh, are handed to the plan owner (the fixwave-defects lane holds the plan files through #723), not edited here. Standing constraint F1 is extended to 21128/21129.
- Base commit: `cb339488e`, merged with main `2d849ba1f` (head `08e749ec4`, after the repair rounds for 5f's read of `b5bf717d9`, its delta reads of `fb3d1ee40` and `3d65b80fa` and c5's read of `7200ee424`; main moved with #713, so the plan rows the record cites are the post-#713 ones)
- Lane: `lane:shared` (the gateway serves the foundation and trading lanes, as in #637); the trading lane's acknowledgement is requested before merge ([docs/lanes.md](../docs/lanes.md)).
- Owned paths touched: `docs/decisions/2026-10-05-omniroute-gateway-composition.md`, `evidence/artifacts/omniroute-wire-effort-20261005/` (new), one-clause F1 extensions in `docs/decisions/2026-09-30-omniroute-rebuild.md` and `docs/foundation-stack.md`, and the hot-file registry rows in `manifests/evidence.json` (last commit, hot-file protocol).

### SOTA sources

- OmniRoute upstream, https://github.com/diegosouzapw/OmniRoute: tag `v3.8.51` (commit `c1e30b7676975feb298b49eff6ff58923c04b89e`, tree `0f58d8df20c0c2ae4336b432b3f39837119b6eed`, equal to the tree of `release/v3.8.51` at `2f42a9ac19d1a247ec9ce5473b790843724b3061`); npm `[email protected]` (integrity `sha512-VwwSt+bP9lJiPJXFJMz0nNGGuoewPZU3nFe1SLuO11ADgdSwTegGCxhg8Ov75+31m/cocPxHiO63zygn1XQ0MQ==`).
- Upstream PR 15167 (head `0585aba5589d5a1f49243a13a8db249558e7c9e3`): `gpt-6.1-sol` in the Codex registry and alias sets; its re-pin trigger is the first official release that carries it. Upstream issue 8939 and PR 8940 (the affinity premise), open PR 13102, PR 13788 (commits `24bbadbad15eec0d598c908416e4b01be4e37671` and `6c7990058c4ce9677de79452c8cefb10b4bf1b3d`; optional, dropped at the next rebuild). The running builds carry PR 15167's earlier head `f5d8e150b` and local cherry-picks of PR 13788's two commits with the same patch-ids.
- Upstream code read for the wire behavior: `open-sse/executors/codex.ts` (`clampEffort`, `transformRequest`) and `open-sse/executors/codex/reasoningSuffix.ts` at the tag and with the PR.
- Upstream's own build and checks, unchanged: `npm ci`, `npm run build:release`, `OMNIROUTE_ALLOW_CANARY_BUILD=1 npm run check:pack-artifact`, `npm pack`, `npm run check:pack-boot`.
- The earlier records this one extends: `docs/decisions/2026-09-30-omniroute-rebuild.md`, `docs/decisions/2026-10-03-omniroute-3851-pin.md`, `evidence/artifacts/omniroute-sol-max-20260930/`.

### Evidence-class table

| Claim | Evidence class | Command / receipt |
| --- | --- | --- |
| With PR 15167 the executor sends model `gpt-6.1-sol` and effort `max` for `gpt-6.1-sol-max`, `-ultra` and `gpt-6.1-sol` with client `max`; without it `xhigh`, `medium` and an unsplit model name | `local_integration` (upstream code, our probe; nothing was sent) | `checks/wire-probe-with-15167.txt`, `checks/wire-probe-without-15167.txt` |
| The live call log shows requested `max` and upstream `max` for Sol after the 2026-09-30 restart (7,550 and 2,728 rows) and `xhigh` before it (1,165 rows) | `local_integration` (read-only read of metadata columns; the upstream effort is the one in the provider request the attempt captured, only for rows with encrypted reasoning) | `checks/live-effort.json`, `checks/live-requests.json` |
| The deployed prefix carries the probed code (four files byte-identical, bundle literal counts 40/8 against 0/0 for the clean package) | `local_integration` | `checks/source-identity.json` |
| The base tree equals the tag commit's tree and so the published package content | `source_review` (git facts, npm metadata) | `checks/source-identity.json` |
| The patch file applies to the tag and, with PR 15167's diff, reproduces the trees of the two built commits | `local_integration` (git, temporary index) | `checks/composition-trees.txt`, `patches/045aa81f3.patch` |
| The affinity patch's unit test (7 tests): 6 fail on the tag with only the test file (negative control), 7 of 7 pass on the tag plus the patch and on the composition; the wire probe re-run on both reproduces the committed probe files byte for byte | `local_integration` (upstream runner flags, trees built from public refs, our test and probe) | `checks/affinity-test-results.txt`, `scripts/affinity-test.sh.txt` |
| PR 13788's two public commits have the same patch-ids as the four local cherry-picks; the carry bundle restores into a fresh repo | `local_integration` (git) | `checks/pr13788-carried-patch-ids.txt` |
| The composition builds with upstream's release scripts and its tarball boots and persists in a clean prefix | `local_integration` (upstream checks on our build; the first `check:pack-boot` run failed on a port collision and passed on the rerun, both recorded; the kept tarball equals a fresh `npm pack --dry-run` of the booted tree by sha1 and sha512) | `checks/build-notes.txt` |
| 7-day use of `/v1/responses`: 20,371 calls, 93.2% cache reads; 21.7% of calls use `-max`/`-ultra` names | `local_integration` (read-only counts) | `checks/usage-7d.json` |
| Without #15167 the live gateway rejects `cx/gpt-6.1-sol-max` and `-xhigh` at the catalog gate (HTTP 400) and clamps `cx/gpt-6.1-sol` with `max` to `xhigh`; with it all answer 200 with upstream `max`, `max`, `xhigh`, `max` | `local_integration` (main's recorded live probes of 2026-09-30, cited, not re-run) | `evidence/artifacts/omniroute-sol-max-20260930/checks/probe-gate-before-switch.json` (C7), `probe-gate-after-switch.json` |
| The kept tarball carries PR 15167's head of 2026-10-05 (17 files), not the running build's head of 2026-09-30 (5 files); the 13 test files covering the extra pieces pass on the composition, 145 of 145 | `local_integration` (upstream test runner on a tree built from public refs); the version-header change is not observed live | `checks/affinity-test-results.txt` (last block), `evidence/artifacts/omniroute-sol-max-20260930/checks/upstream-pr-15167-identity.txt` |
| NativeStack2604's 21128 delivers max on `sol-max`; `-xhigh`, bare and `astra-max` answer 200 | relayed from the co-op's read-back (an exact `X-Correlation-Id` join; request headers unobservable); the files are in its private coordination record, not in the repository | the co-op's ledger row 165024Z, cited as relayed by the command center |
| The backend applies `max` | not observable from our side; not claimed | |
| The cache cost of dropping the affinity patch | not measured | |

### Local commands run

```
$ python3 scripts/validate.py
{"components": 69, "hashed_files": 10232, "profiles": 4, "receipts": 204, "status": "passed"}
$ python3 scripts/validate_convergence.py --all-recorded
record[30]: valid
$ python3 -m unittest tests.test_component_matrix tests.test_evidence_manifest tests.test_new_host_grand_list tests.test_validate tests.test_frozen_macos_variant_no_use
Ran 172 tests ... OK; Ran 10 tests ... OK
(gitleaks, run by the commit hook on each commit: no leaks found)
```

### Decision record

`docs/decisions/2026-10-05-omniroute-gateway-composition.md`: the composition table with each carried change at its commit and its removal or re-pin condition, the user's choices as the command center relayed them, the swap-impact measurements, the wire evidence, alternatives A/B/C, limits and the overturn conditions.

### Host evidence

Not applicable (no files under `evidence/hosts/`).

### Checklist

- [x] New/changed GitHub Actions are pinned to a full commit SHA with a version comment (no workflow changed).
- [x] New/changed workflows declare top-level `permissions: {}` (no workflow changed).
- [x] No secrets are printed, logged or committed; no new required secret was added (callers use the documented `local-loopback` placeholder; no connection id, account or request body is recorded).
- [x] No new paid hosting, subscription or billing surface was introduced.
- [x] Peer-owned untracked files and worktrees were preserved.

### Recorded residuals (bounded review, 2026-10-05)

GPT-6.1 Sol micro delta read (session 5f) at 08e749e at `08e749ec4b8c` returned FINDINGS with no p1. Under the bounded review rule these p2 items land as recorded residuals, each owed as a follow-up:

- ``: 
- ``: 

🤖 Generated with [Claude Code](https://claude.com/claude-code)

… the PR 15167 dependency, -max alternative, owed re-measure

The command center's verdict on 640a719 (ACK_AFTER; item
task-ns2604-coop-20261006T055125Z).

P2-1. The call-log API returns requestedModel under the provider id
codex/, not the requested cx/ alias: OmniRoute@c1e30b76
src/lib/usage/callLogs.ts L221-231 and L479 rewrite only provider-node
prefixes. Live rows for gptr-20261006T044527Z-3989681 read
codex/gpt-6.1-sol-xhigh, provider codex.
- gateway-effort-accept.py: ROUTES now holds the cx/ and codex/ spelling
  of each route (plain and -high as #723 adds them, plus -xhigh). It uses
  #723's stricter predicate (alias suffix equals the logged model; provider
  codex), so the two PRs differ only by the -xhigh entries.
- Its test uses the observed row shape, with the mismatch and wrong-
  provider negatives.
- The live session-joined acceptance run now exits 0 (join=session, high
  and xhigh). Main's script and this branch's first one exit 1 on the
  same session, and the new test rows fail against both.

P2-2. The -xhigh route needs OmniRoute PR 15167. Main's plan gpt-gateway
row (owners[75]) still installs the published [email protected], which
answers HTTP 400 for cx/gpt-6.1-sol-xhigh (receipt C7). The amendment's
dependency field and the research-harnesses plan notes now record that
this lands after #723.

P3:
- The amendment lists the -max alternative, why it is out of the ruling's
  scope, and the comparison that would restore it.
- It records the owed 24 h zero-downgrade re-measure after the reinstall.
- Citations move to public pins (c1e30b76 for codex.ts and callLogs.ts,
  0585aba55 for reasoningSuffix.ts L54-58) and the install lines (install.sh
  L911 and L930).
- It qualifies NULL in the effort columns (encrypted-reasoning rows only),
  so the 12-row before-count is a lower bound.

The wrapper and config bytes are unchanged (fbf0f46a, 8edd6747), so the
observed run still describes them.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

… the PR 15167 dependency, -max alternative, owed re-measure

The command center's verdict on 640a719 (ACK_AFTER; item
task-ns2604-coop-20261006T055125Z).

P2-1. The call-log API returns requestedModel under the provider id
codex/, not the requested cx/ alias: OmniRoute@c1e30b76
src/lib/usage/callLogs.ts L221-231 and L479 rewrite only provider-node
prefixes. Live rows for gptr-20261006T044527Z-3989681 read
codex/gpt-6.1-sol-xhigh, provider codex.
- gateway-effort-accept.py: ROUTES now holds the cx/ and codex/ spelling
  of each route (plain and -high as #723 adds them, plus -xhigh). It uses
  #723's stricter predicate (alias suffix equals the logged model; provider
  codex), so the two PRs differ only by the -xhigh entries.
- Its test uses the observed row shape, with the mismatch and wrong-
  provider negatives.
- The live session-joined acceptance run now exits 0 (join=session, high
  and xhigh). Main's script and this branch's first one exit 1 on the
  same session, and the new test rows fail against both.

P2-2. The -xhigh route needs OmniRoute PR 15167. Main's plan gpt-gateway
row (owners[75]) still installs the published [email protected], which
answers HTTP 400 for cx/gpt-6.1-sol-xhigh (receipt C7). The amendment's
dependency field and the research-harnesses plan notes now record that
this lands after #723.

P3:
- The amendment lists the -max alternative, why it is out of the ruling's
  scope, and the comparison that would restore it.
- It records the owed 24 h zero-downgrade re-measure after the reinstall.
- Citations move to public pins (c1e30b76 for codex.ts and callLogs.ts,
  0585aba55 for reasoningSuffix.ts L54-58) and the install lines (install.sh
  L911 and L930).
- It qualifies NULL in the effort columns (encrypted-reasoning rows only),
  so the 12-row before-count is a lower bound.

The wrapper and config bytes are unchanged (fbf0f46a, 8edd6747), so the
observed run still describes them.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

### Scope

Record the command center's orchestration round 2 and the co-op's measured launch-and-close gate. Add the dated decision, five contiguous anti-pattern lessons and three portable snapshots of the deployed hcom/tmux/agentsview configuration. After #753 landed, rebase these records and correct its VHDX statement to distinguish non-sparse disks from automatic sparse reclamation.

- Base commit: `0d5e6506434fab598dee861c749a22e628beb75a` (includes landed #753 at `9f3af37d`)
- Lane: `lane:foundation` (the sole PR label).
- Owned paths: `docs/decisions/2026-10-06-cc-orchestration-composition.md`, `docs/harness-defaults.md`, `examples/hcom-wt-tmux.toml.example`, `examples/hcom-lanes.conf`, `examples/agentsview.service.example`; their registrations in `manifests/evidence.json` are isolated in the final commit.
- The record covers receipt entries through 6:00:21 AM EDT (10:00:21Z). Later stopper observations remain with their owner. No host settings, install-plan files or credentials are changed; this PR does not merge anything.

## SOTA sources

- [aannoo/hcom v0.7.27, 2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b](https://github.com/aannoo/hcom/tree/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b): `src/config.rs` user-preset field merge; `src/terminal.rs` open/close; `src/launcher.rs:1991–2044` generated name/tag distinction; `src/commands/kill.rs:557–569,677–679` bare-name result; native Codex hook delivery.
- [tmux/tmux 3.6a, cc117b5048f77a4842820f8ebbe3a86e5c077224](https://github.com/tmux/tmux/tree/cc117b5048f77a4842820f8ebbe3a86e5c077224): `server-fn.c`, `server-client.c`, `server.c`, `client.c` close/exit ordering and `tmux.1` lane options. Installed host reports tmux 3.6; the record distinguishes that execution from the 3.6a source pin.
- [kenn-io/agentsview v0.43.0, 9be7745ad1906ee24e04eb05bb86c872ef0939a1](https://github.com/kenn-io/agentsview/tree/9be7745ad1906ee24e04eb05bb86c872ef0939a1): `cmd/agentsview/main.go`, `serve_replacement.go`, configuration/command docs; supervised foreground `serve --replace`, idle timeout and optional authentication. Passwordless operation is the user's scoped host divergence.
- [MicrosoftDocs/terminal, c341a6362f9f0346a17ecc5e1e74d2cd9372c8f9](https://github.com/MicrosoftDocs/terminal/tree/c341a6362f9f0346a17ecc5e1e74d2cd9372c8f9): `TerminalDocs/customize-settings/profile-advanced.md` `closeOnExit=graceful` and command-line tab launching.
- [systemd/systemd v259, 9ca433482f2281d71718718705ca8cd3bf562ad6](https://github.com/systemd/systemd/tree/9ca433482f2281d71718718705ca8cd3bf562ad6): `man/systemd.service.xml` foreground simple service and restart behavior.
- [openai/codex rust-v0.160.0, a956835d](https://github.com/openai/codex/tree/a956835d): per-thread writer locks and app-server in-process live-status scope; [OmniRoute v3.8.51, c1e30b76](https://github.com/diegosouzapw/OmniRoute/tree/c1e30b76): chat-completions caller correlation-ID preservation.

- Microsoft [WSL disk-space documentation](https://learn.microsoft.com/windows/wsl/disk-space), updated 2025-02-05 ([MicrosoftDocs/WSL source 7b28cc1e](https://github.com/MicrosoftDocs/WSL/blob/7b28cc1ee9b8ff672ada5e1c6c326d3573d703e5/WSL/disk-space.md)); [automatic disk-space cleanup announcement](https://devblogs.microsoft.com/commandline/windows-subsystem-for-linux-september-2023-update/#automatic-disk-space-clean-up-set-sparse-vhd), 2023-09-18; [experimental sparseVhd setting](https://learn.microsoft.com/windows/wsl/wsl-config#experimental-settings), displayed update 2026-09-16 ([source 7ea1c6f9](https://github.com/MicrosoftDocs/WSL/blob/7ea1c6f9e25f1c89a05a0e97e5325a02a66ac6cd/WSL/wsl-config.md)). The disk-space page covers disk management; the announcement/configuration provide the sparse exception. No claim is made that disk-space.md contains a sparse section.

### Evidence-class table

| Claim | Evidence class | Command / receipt |
| --- | --- | --- |
| Corrected gate passed: steps 0, 3, 4, 8, 9 and 10; run-3 transport passed in substance | `local_integration` | Private co-op `orchestration-round2-20261006/receipt.md`, measured times/exits and failures transcribed in the decision; no new lifecycle execution in this PR |
| Examples preserve the deployed bytes after only documented personal-path substitutions | `local_integration` | Direct host-file byte comparison: tmux exact; TOML/unit exact after `<WINDOWS_USER>`, `<WSL_USER>` and `%h` substitutions; TOML parses |
| Bare generated name differs from lane tag; native preset/close/supervision interfaces | `source_review` | Pinned files above, checked independently against primary sources |
| The VHDX statement excludes automatic sparse reclamation; sparse remains off under the recorded WSL 3.0.1 guard | `source_review` | Dated Microsoft sources above; no disk operation, sparse toggle or new host acceptance |
| Anti-pattern table and hashes remain consistent | `local_integration` | Existing unittest modules and `scripts/validate.py`; structural checks, no provider/GPU execution |

Step 6, step 5 OTel queries, 11a–f, 11h and 11i were not run; only the co-op-caller half of 11g ran. The example still carries the deployed `ecosystem.lane={instance_name}` value, so stable OTel lane attribution remains unverified. The no-prompt `zumi` spontaneous close remains unexplained. The decision drops the refuted token figures and refers to `e2e-truth-sweep-wf_6f2c775d-293.json` per critic finding 3.

### Local commands run

```text
nice -n 19 python3 scripts/component_matrix.py --write
exit 0: 32 rows, zero flip-rule violations (no generated-file diff)
nice -n 19 python3 scripts/new_host_grand_list.py --write
exit 0: 32 layers, 66 winners (no generated-file diff)
nice -n 19 python3 scripts/validate.py
exit 0: 69 components, 10340 hashed files, 4 profiles, 214 receipts
nice -n 19 python3 -m unittest tests.test_adoption_docs_consistency tests.test_evidence_manifest
exit 0: Ran 44 tests in 25.095s; OK (skipped=1)
git diff --check
exit 0
```

Post-rebase validation ran 10:01:59–10:02:49 AM EDT (14:01:59–14:02:49Z); touched tests ran 10:02:50–10:03:15 AM EDT (14:02:50–14:03:15Z), outside both paper windows. Fixture sort-error output is expected negative-control evidence, not manifest drift. A read-only completeness critic verified the unchanged four artifacts and five contiguous rows, the bounded P3 change and the five matching registrations; no blocker.

The rebased tree retains both owners' table rows. The final evidence commit is rebuilt from main's manifest instead of hand-merging registry entries. Checks run at nice 19 outside the paper windows; no live provider/GPU or disk operation is part of this PR. Restart loss inventory records only regenerable tool scratch, with no sole-copy repository work or lane-created transient units lost. A post-restart API read found zero review threads, including connector threads.

### Decision record

[`docs/decisions/2026-10-06-cc-orchestration-composition.md`](docs/decisions/2026-10-06-cc-orchestration-composition.md) records the alternatives, overturn conditions, passwordless agentsview divergence, lane-tabs-only reversal of the tmux rejection, measured results and corrections.

## Handoff to the install-plan owner

`fixwave-defects` holds the install-plan files through #723. **Proposed text only; none of the following is applied by this PR.** Select the `session-analytics` row in `evidence/artifacts/new-wsl-install-plan-20261002/install-plan.json` (slot at line 2724 on the original `ecfa1127` base), retain its release/download/launcher provenance, and apply these exact field replacements:

```json
"owner": "agentsview 0.43.0 (supervised local live archive)"
```

Within `needs` (line 2737):

```json
"systemd_user_unit": true
```

Replace `service` (lines 2749–2753) with:

```json
{
  "form": "supervised systemd user unit agentsview.service; foreground agentsview serve --replace; Restart=always; RestartSec=10",
  "port": 21808,
  "port_setting": "host=127.0.0.1, port=21808 and daemon_idle_timeout=\"0s\" in the owned archive config.toml",
  "start_command": "systemctl --user daemon-reload\nsystemctl --user enable --now agentsview.service",
  "stop_command": "systemctl --user stop agentsview.service"
}
```

Carry `examples/agentsview.service.example` into the plan's `config/agentsview.service` under the plan's ownership/overwrite rules. After config installation, add this exact `commands` entry:

```json
"install -d -m 0755 -- \"$HOME/.config/systemd/user\"; install -m 0644 -- \"$plan_dir/config/agentsview.service\" \"$HOME/.config/systemd/user/agentsview.service\""
```

Add the installed unit's `$HOME/.config/systemd/user/agentsview.service` path to `config_paths`. Add this exact key to the owner's `config/agentsview.toml`:

```toml
daemon_idle_timeout = "0s"
```

Register adopted worker roots as explicit `[agents.codex] homes = [...]` entries (no glob), using the owner's maintained job-home convention; the current live configuration has ten selected worker homes. Preserve the existing warning/review path for a differing owned config. The scoped passwordless choice remains explicit; do not copy the workstation's authenticated unit by accident.

Reconcile the `service_health` detached-daemon premise and notes with supervised acceptance: `systemctl --user is-active agentsview.service`, listener PID/cgroup on 21808, HTTP `/api/v1/version` and representative fresh session reads, then stop/read/no-auto-start/restart checks. Retain native sync/list/usage and fresh/absent-session controls; any remaining CLI read must use `AGENTSVIEW_NO_DAEMON=1`. Carry the config, unit and plan hashes together under `docs/lanes.md`'s final-commit protocol. These follow-ups implement step 1 and critic finding 13; they are not claimed passed by this records PR.

### Host evidence

No files under `evidence/hosts/` change and no platform status changes. The private co-op receipt is historical local integration evidence, not a newly registered host acceptance receipt.

### Checklist

- [x] No GitHub Actions change; upstream sources are pinned in the record.
- [x] No new workflow permissions or required secrets.
- [x] No secrets printed, logged or committed.
- [x] No paid hosting, subscription or billing surface introduced.
- [x] Peer-owned files/worktrees preserved; owner-held install-plan edits handed off.
- [x] Exactly one label: `lane:foundation`; draft PR; no merge.

### Scope

- **What this PR changes:** it removes the 2026-10-04 hcom safety posture from main. The user decided at 2026-10-06T03:03:10Z (11:03 PM EDT on October 5) to relax the hcom deny list; the safety rules give way to the seamless, LLM-native workflow. The PR removes:
  - the 52 Claude deny entries;
  - `config/hcom-deny.rules`;
  - the adapter's running-Codex interlock and its empty-deny refusal;
  - the acceptance checks that required `forbidden` decisions.

  Peer text stays data and never counts as the user's approval. Upstream `hcom.rules` becomes the only Codex hcom policy.
- **Base commit:** `ecfa112764c664d35377dd66b8cfcb67e5a94d60`
- **Lane:** `lane:foundation`
- **Owned paths touched:**
  - `adoption/new-wsl/client-config-map.json`
  - under `evidence/artifacts/new-wsl-install-plan-20261002/`: `config/hcom-client-config.py`, `config/hcom-deny.rules` (deleted), `install-plan.json`, `install.sh`, `accept.sh`, `check_plan.py`, `README.md` and `SOURCES.md`
  - `tests/test_new_wsl_client_config.py` and `tests/test_codex_hook_trust.py`
  - `docs/decisions/2026-10-06-hcom-relaxation.md` (new)
  - `docs/decisions/2026-10-04-round2-plan-g1-messaging.md` (an inline pointer only; no line moves)
  - `manifests/evidence.json`, in the last commit only

| Verdict P1-1 item | Main ecfa112 | Change |
| --- | --- | --- |
| `claude_settings.permissions.deny` | map :912-963 (52 entries) | The whole `claude_settings` object is removed. An empty object would still go through the settings merge. |
| Prohibition sentence in `hcom_config.launch.hints` | map :977 | Removed. The data, approval and configuration sentences stay. |
| `codex_rule_file` and `config/hcom-deny.rules` | map :983 | Removed. Upstream `hcom.rules` is the only Codex hcom policy. |
| Prohibition sentences in `peer_instructions` | map :984 | Removed, including the `hcom claude` prohibition (see below). The data and approval sentences stay. |
| Quiet interlock and empty-deny refusal | adapter :123-128 and :61 | Removed. The adapter also no longer merges settings (:98-106), installs rules (:108-114) or runs the forbidden check (:145-150). |
| Contract | `check_plan.py` :179-196 | Replaced by the relaxed contract (below). |
| post_install `--check` | install-plan row | Dropped. post_install is the upstream-derived smoke only. |
| after_sign_in | install-plan row | Reduced, not deleted, so stage counts and the after-sign-in owner lists stay valid. Revised at 7eb9bea: it takes the Codex home the way hcom does (`CODEX_HOME`, else the parent of `HCOM_DIR`). It exits 78 while retired Claude hcom deny entries remain and until `hcom codex` writes `hcom.rules`. Then it passes every `*.rules` file there to `codex execpolicy check`; `hcom send` and `hcom term inject` must both be `allow`, so a leftover `hcom-deny.rules` exits 78. |
| Decision record | supersedes `2026-10-04-round2-plan-g1-messaging.md:65-72` | `docs/decisions/2026-10-06-hcom-relaxation.md` |

The verdict cites the same pieces at #723's head, at other lines (map :894-951, :962, :968 and :969; checker :180-197). The table uses main's lines.

The relaxed `check_plan.py` contract keeps the four `hcom_config` value checks and the smoke tokens. It asserts three things:
- no Codex rule file and no Claude hcom settings are mapped;
- both peer texts keep the data and approval sentences;
- after_sign_in derives the Codex home from `HCOM_DIR`, evaluates every rules file there and checks the retired Claude denies.

### The `hcom claude` rule: hook-gap finding at hcom's current release

- **Current release.** `gh api repos/aannoo/hcom/releases/latest` returns **v0.7.27, still the latest** (published 2026-10-01T02:11:55Z, target `2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b`, the existing pin).
- **The gap still holds.** Hooks load only in `hcom <tool>` sessions ([release notes, #146](https://github.com/aannoo/hcom/releases/tag/v0.7.27)). The Claude hook handler exits 0 silently without `HCOM_PROCESS_ID` ([claude.rs:135-140](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/src/hooks/claude.rs#L135)). A plain `claude` has no hooks ([start.rs:412-417](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/src/commands/start.rs#L412)). Only `hcom claude` gets automatic delivery; anything else uses manual `hcom listen` ([README.md:230-246](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/README.md#L230)).
- **Upstream main.** Main is 20 unreleased commits ahead, and its claude.rs diff leaves the guard untouched.
- **The sentence is dropped** (the command center's read at 247d71e, finding P2, option a).
  - The sentence met the task's "stays only if" test, which is a necessary condition, not a sufficient one.
  - The gap is the *cost* of not launching through `hcom claude`, not a reason against it.
  - The peer-instruction block now keeps only the neutral route facts: a plain Claude session uses `hcom start` and `hcom listen`, which do not wake it when idle, and `hcom claude` is upstream's automatic-delivery route for Claude Code.
- **Why not option b.** Option (b) would keep the rule on the wave-5 transport-scoping basis and add Claude lanes to the command center's orchestration decision. That changes the command center's own decision, so it is not this lane's to make.
- **No recipes.** This PR adds no launch, kill, term or transcript recipe.

### Fixes after the command center's read at 247d71e (ACK_AFTER)

| Finding | Fix |
| --- | --- |
| P2: the kept `hcom claude` sentence | Option (a): `peer_instructions` drops "Never launch Claude lanes through hcom claude" and "Claude lanes stay plain Claude sessions" and keeps the route facts. The record's Result and overturn sections are rewritten. |
| P3: no supersession pointer for the 2026-10-05 combined-rules acceptance | Inline pointer at the start of the old record's :196. No line moves; :65, :109 and :196 stay where the new record cites them. |
| P3: rc 3 at `--apply` when the user's own `~/.hcom/config.toml` differs (pre-existing) | Recorded in the decision's host section (see Host evidence below). No code change: `run_slot` scores any non-zero rc, 78 included, as failed. |
| P3: the adapter's `--check` has no caller | The docstring marks it a manual operator check that no plan stage runs. The record's post_install row says the same. |
| P3: the `exec_rules_reviewed.json` entry stays | No change. The read accepts the deviation. |

The history was rebuilt so that `manifests/evidence.json` changes only in the last commit (`docs/lanes.md:96-128`):
- `f0d9b2f5`: the relaxation;
- `88eb3981`: the read's fixes;
- `10160d89`: the registry.

It was pushed with `--force-with-lease`, replacing 247d71e.

### Deliberate non-changes

- **`tools/adoption/exec_rules_reviewed.json` keeps its `hcom-deny.rules` entry.** This is a deliberate non-change to the verdict's item (e). The entry reviews one exact file for the RTK Codex hook-trust tool and enforces nothing. Removing it would rewrite about twenty trust tests and `rtk-rewrite-heads-check.json`. It would also make `codex_hook_trust.py` refuse on any host that did install the file. The plan-wide test that every plan rule file is reviewed or allow-only stays; only its docstring changed, and it is vacuous while the plan ships none.
- **The verdict's item (f) quiet-interlock and quiet-apply wording exists only in #723.** On main, `git grep -i -E 'quiet (interlock|apply|point)'` returns nothing.
- **Configuration values are unchanged.** These are `title_mode=off`, `relay.enabled=false`, `auto_trust_workspace=false` and `auto_approve=true`. The verdict reserves `auto_trust_workspace` and `title_mode` to the user.

### SOTA sources

- **aannoo/hcom v0.7.27** at `2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b` (https://github.com/aannoo/hcom/releases/tag/v0.7.27), still the latest release, read with `gh api repos/aannoo/hcom/releases/latest` on 2026-10-06:
  - **Upstream `hcom.rules`, the only Codex hcom policy:**
    - [src/hooks/codex.rs:1538-1563](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/src/hooks/codex.rs#L1538) (`build_codex_rules`);
    - [:1566-1579](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/src/hooks/codex.rs#L1566), which writes `<codex home>/rules/hcom.rules`;
    - [:337-350](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/src/hooks/codex.rs#L337), the call made when `auto_approve=true`;
    - [:72-75](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/src/hooks/codex.rs#L72), the Codex home;
    - [src/hooks/common.rs:46-72](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/src/hooks/common.rs#L46), the command list.
  - **Hook-gap check:**
    - the release notes (#146);
    - [src/hooks/claude.rs:135-140](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/src/hooks/claude.rs#L135);
    - [src/launcher.rs:920](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/src/launcher.rs#L920);
    - [src/commands/start.rs:412-417](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/src/commands/start.rs#L412);
    - [README.md:230-246](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/README.md#L230).
  - **Mapped configuration fields:** [src/config.rs:126-152](https://github.com/aannoo/hcom/blob/2c5f343b2f9ec4bf2acf49c0431860e7c2ae578b/src/config.rs#L126).
- **Codex native policy checker:** https://developers.openai.com/codex/rules, and the installed codex-cli 0.160.0 `codex execpolicy check --help` (repeatable `--rules`, JSON `decision`).

### Evidence-class table

| Claim | Evidence class | Command / receipt |
| --- | --- | --- |
| The plan rows, `install.sh`, `accept.sh`, the map and the relaxed contract agree | `local_integration` | `check_plan.py` exit 0 |
| The adapter applies while a Codex PID is reported, leaves Claude settings unchanged, writes no Codex rules directory, runs no subprocess and keeps the data and approval sentences | `synthetic` | `test_hcom_apply_never_grants_inbound_authorization_or_requires_codex` |
| `copy_config` still refreshes plan-owned helpers and keeps operator files | `synthetic` | `test_plan_owned_helpers_refresh_without_overwriting_operator_configuration` |
| The contract fails if after_sign_in falls back to a fixed `$HOME/.codex` | `synthetic` (throwaway negative control, not committed) | `check_plan.py --plan-dir <mutated copy>`: exit 1, "after sign-in must evaluate every rules file in the Codex home that hcom derives from HCOM_DIR, and report retired Claude hcom denies" |
| Native-checker probes and the after_sign_in program on frozen fixtures | `synthetic` (real codex-cli 0.160.1 and jq 1.8.1 with scratch homes) | Retained receipt `evidence/artifacts/hcom-relaxation-20261006/probe-receipt.json`, run at 13:11:32Z: `allow`/`allow`/no decision over `hcom.rules` alone, `forbidden` for term with the retired file, and 8 after_sign_in runs with the expected exits 78,0,78,0,78,0,78,0 |
| The after_sign_in shell logic (`HCOM_DIR` derivation, every rules file, retired Claude entries) | `synthetic` (stub codex) | `test_hcom_after_sign_in_reads_hcoms_codex_home_and_every_rules_file` |
| hcom v0.7.27 is the latest release, and the plain-Claude hook gap holds there | `source_review` | `gh api` releases, tags and compare; pinned source read |
| No host changed | (scope) | no `install.sh`, `accept.sh` or `--only agent-messaging` run; NativeStack2604 never had the posture (the command center's read-only check) |

### Review threads at 3b6ea9d, fixed at 7eb9bea

The fix commit is `2c8890c9`, and the registry and regenerated outputs are the last commit, `7eb9beaa`.

| Thread | Fix |
| --- | --- |
| P1, decision record :131: retain the probe's actual result | `evidence/artifacts/hcom-relaxation-20261006/` keeps the frozen synthetic `hcom.rules` (sha256 `2a667dcb…`) and `probe-receipt.json` (every argv, sanitized environment, UTC times, exit codes, stdout and stderr). The record's Evidence section cites it. |
| P2, accept.sh:330: resolve under the Codex home hcom derives from HCOM_DIR | The after_sign_in derives `CODEX_HOME`, else the parent of `HCOM_DIR` (hcom `src/hooks/codex.rs:72-75`, `src/paths.rs:26-53`). The check_plan contract requires it. |
| P2, accept.sh:335: check the effective policy | Every `*.rules` file in that home goes to the native checker, as Codex loads them (openai/codex rust-v0.160.0 `exec_policy.rs:662-700`). `hcom send` and `hcom term inject` must both be `allow`. A leftover `hcom-deny.rules`, or any of the 52 retired Claude hcom deny entries, reports needs_user (78). |
| P2, README.md:476: the generated handbook still stated the retired posture | The handbook's source record (layer consensus, wave 5, agent-messaging) and the WSL recipe's exec-rules sentence were updated. `assemble_manifest.py` and `scripts/build_new_wsl_handbook.py --write` then regenerated the outputs, and the handbook receipt follows them. |

The installed Codex is now 0.160.1, which adds two commits to rust-v0.160.0, neither touching exec policy.

### Local commands run

Run at head `7eb9beaaf9680acebe0d8d1c8b0331cb50e4ff2a` with `nice -n 19` and `PYTHONDONTWRITEBYTECODE=1`:

```
$ python3 scripts/validate.py
exit 0: {"components": 69, "hashed_files": 10322, "profiles": 4, "receipts": 212, "status": "passed"}
$ python3 evidence/artifacts/new-wsl-install-plan-20261002/check_plan.py
exit 0: OK: 84 rows ... 185 commands and 113 acceptance entries agree with the scripts (2 additional checks included)
$ python3 tools/adoption/new_wsl_client_config.py --check
exit 0: check passed (two existing MCP_AUTO_OPEN_ENABLED warnings)
$ python3 scripts/build_new_wsl_handbook.py --check
exit 0
$ (cd evidence/artifacts/new-wsl-definitive-defaults-20261001 && python3 assemble_manifest.py --check && python3 render_tables.py --check ../../../docs/decisions/2026-10-01-new-wsl-definitive-defaults.md)
exit 0, exit 0
$ bash -n install.sh && bash -n accept.sh; git diff --check 3b6ea9d..HEAD
exit 0, exit 0
$ python3 -m unittest <the 6 touched modules>; python3 -m unittest <the 4 other pinning modules>
exit 0: 567 tests OK (skipped=3); exit 0: 122 tests OK (skipped=1)
```

The earlier runs at 10160d8 and 247d71e follow.

```
$ python3 scripts/validate.py
exit 0: {"components": 69, "hashed_files": 10271, "profiles": 4, "receipts": 212, "status": "passed"}
$ python3 evidence/artifacts/new-wsl-install-plan-20261002/check_plan.py
exit 0: OK: 84 rows ... 185 commands and 113 acceptance entries agree with the scripts (2 additional checks included). Base ecfa112 gives the same counts, so no stage was dropped.
$ python3 tools/adoption/new_wsl_client_config.py --check
exit 0: check passed, with two MCP_AUTO_OPEN_ENABLED warnings. Base ecfa112, run in a `git archive` extraction, gives the same exit 0 and the same two warnings.
$ python3 scripts/build_new_wsl_handbook.py --check
exit 0: status passed (no regeneration needed)
$ python3 evidence/artifacts/new-wsl-install-plan-20261002/config/hcom-client-config.py --repo-root . --check-map
exit 0
$ bash -n evidence/artifacts/new-wsl-install-plan-20261002/install.sh && bash -n evidence/artifacts/new-wsl-install-plan-20261002/accept.sh
exit 0
$ git diff --check origin/main...HEAD
exit 0
$ python3 -m unittest tests.test_codex_hook_trust tests.test_new_wsl_client_config tests.test_new_wsl_definitive_defaults tests.test_new_wsl_handbook tests.test_new_wsl_profile tests.test_wsl_new_distro_recipe tests.test_gpt6_family_tiering_20260926 tests.test_gpu_inference tests.test_local_inference_latest_20260926 tests.test_workflow_policy
exit 0: Ran 670 tests in 176.855s, OK (skipped=4)
$ python3 scripts/component_matrix.py --write && python3 scripts/new_host_grand_list.py --write
exit 0, exit 0: no output change
```

The module list covers every test module that names hcom, agent-messaging, hcom-deny, the plan directory, the map, `check_plan`, `exec_rules_reviewed` or the round-2 record. It is the `git grep -l` over `tests/`.

### Decision record

`docs/decisions/2026-10-06-hcom-relaxation.md` records:
- the user's decision, described rather than quoted;
- the sources;
- six alternatives;
- the overturn conditions, both for the posture and for reinstating an `hcom claude` launch rule;
- the host boundaries and a completeness critic.

It supersedes `docs/decisions/2026-10-04-round2-plan-g1-messaging.md:65-72`, plus that record's 2026-10-05 combined-rules acceptance.

### Host evidence

Not applicable: no `evidence/hosts/` change. NativeStack2604 never had the posture applied, so nothing needs undoing. A host that did apply it keeps its hcom deny entries and `~/.codex/rules/hcom-deny.rules` until that host's owner removes them; none is known.

**Expected after landing on NativeStack2604.** This behavior is unchanged from base.
- The user's own `~/.hcom/config.toml` already exists there.
- Unless it matches the mapped template's digest, `install.sh --only agent-messaging` writes the two instruction blocks, keeps the file, prints `needs_user` and prints `agent-messaging | install | 3`. `run_slot` scores that rc as failed.
- The four mapped hcom values are not written there.

### Integration

- Hot files are in the last commit only (`docs/lanes.md:96-128`). That commit removes the retired file's registry entry and re-registers the ten changed registered files.
- #723 rebases onto this PR after it lands, in the fixwave-defects lane.

### Checklist

- [x] New/changed GitHub Actions are pinned to a full commit SHA with a
      version comment (no floating tags). No workflow changes.
- [x] New/changed workflows declare top-level `permissions: {}` and grant each job
      only what it needs (`contents: read`, or an explicitly justified addition). No workflow changes.
- [x] No secrets are printed, logged or committed; no new required secret was
      added without a documented owner.
- [x] No new paid hosting, subscription or billing surface was introduced.
- [x] Peer-owned untracked files and worktrees were preserved (not deleted,
      moved or overwritten).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

### Scope

- Select one default for each logical NativeStack2604 host tool and name every coordinated consumer amendment. This decision exposes the bootstrap/trading/CI pin split without claiming it has already been resolved.
- Base commit: `67c6b6f94b456a3a7b5d28bb1fa34625a808d316`.
- Lane: exactly `lane:foundation`; this PR remains draft for the command center's cross-family read.
- Owned paths: two dated decisions, resolver watch documentation, source/version and partial context-review artifacts, sanitized assignment metadata, evidence registry last. Live bootstrap/profile/install-plan/CI and trading files are not edited. Currency's consumer follow-up starts only after #642/#645 land, or is folded by 5f's request; fixwave-defects owns #723/#776, github-ci-finalize owns the CI uv/hash, and 5f owns the trading gate/digest.

The canonical defaults are Node24.21.0,uv0.12.22,gh2.102.0,host Python3.13.16,Codex0.160.1,Claude2.1.292,Harbor0.24.0,Collector0.162.0 andvLLM0.31.0. This is a decision and owner handoff. Claude's ordinary cooldown and Harbor/vLLM qualification remain gates; the trading project's Python3.12.3 remains a separate project requirement.

The executable bootstrap consumes pins-linux-x86_64.json, so a profile summary edit alone would leave drift. 5f must fold the uv0.12.22 gate and verified sync-vector digest together. CI's promotion uv/hash and Python's family-versus-patch selection are named explicitly. C5's reopened context audit is ongoing in this same PR: the command center assigned the NativeStack2604 resolver loop to currency. Seven of nine items have primary review evidence; two Codex tagged-source checks remain pending. Nice19 local publication validation passed on the rebase and is rerun for the J805 fixes. No instruction/template file is edited. Preserve unrelated rows, update the three existing document rows by key, and append only newly reviewed name rows. These final catalog changes are pending; the live catalog remains unchanged.

## SOTA sources

- [0d5e6506:profile defaults:4655](https://github.com/seathatflowsinourveins/native-agent-stack/blob/0d5e6506434fab598dee861c749a22e628beb75a/adoption/new-wsl-profile.json#L4655), [plan mise pins:6-15](https://github.com/seathatflowsinourveins/native-agent-stack/blob/0d5e6506434fab598dee861c749a22e628beb75a/evidence/artifacts/new-wsl-install-plan-20261002/mise.toml#L6-L15), [bootstrap artifact consumer:233](https://github.com/seathatflowsinourveins/native-agent-stack/blob/0d5e6506434fab598dee861c749a22e628beb75a/adoption/bootstrap-linux.sh#L233), [native newer-client preservation:843](https://github.com/seathatflowsinourveins/native-agent-stack/blob/0d5e6506434fab598dee861c749a22e628beb75a/adoption/bootstrap-linux.sh#L843): exact split and qualified preservation policy.
- [Node v24.21.0](https://nodejs.org/en/blog/release/v24.21.0), nodejs/node@955266bf; [uv0.12.22](https://github.com/astral-sh/uv/releases/tag/0.12.22), astral-sh/uv@70fe1196; [gh2.102.0](https://github.com/cli/cli/releases/tag/v2.102.0), cli/cli@fc4b137c; [Python3.13.16](https://www.python.org/downloads/release/python-31316/), python/cpython@cbc944f4: plan-aligned maintained host defaults and release dates.
- [Codex rust-v0.160.1](https://github.com/openai/codex/releases/tag/rust-v0.160.1), d27764b8; [Claude v2.1.292](https://github.com/anthropics/claude-code/releases/tag/v2.1.292), release-repository fbe20e00; [Harbor v0.24.0](https://github.com/harbor-framework/harbor/releases/tag/v0.24.0), b53b8134; [Collector v0.162.0](https://github.com/open-telemetry/opentelemetry-collector-contrib/releases/tag/v0.162.0), ae8c5075 and [distribution](https://github.com/open-telemetry/opentelemetry-collector-releases/releases/tag/v0.162.0), f6159a77; [vLLM v0.31.0](https://github.com/vllm-project/vllm/releases/tag/v0.31.0), db9527a4: F12 selected targets, identities and pending gates.
- [Trading sync pins:8-9](https://github.com/seathatflowsinourveins/native-agent-stack/blob/0d5e6506434fab598dee861c749a22e628beb75a/blueprints/us-equities/runtime-2604/sync-trading-2604.sh#L8-L9), [verified vector:84-88](https://github.com/seathatflowsinourveins/native-agent-stack/blob/0d5e6506434fab598dee861c749a22e628beb75a/blueprints/us-equities/runtime-2604/install-trading-2604.sh#L84-L88), [uv gate:112](https://github.com/seathatflowsinourveins/native-agent-stack/blob/0d5e6506434fab598dee861c749a22e628beb75a/blueprints/us-equities/runtime-2604/install-trading-2604.sh#L112): exact 5f handoff; no trading file edit.

C5 primary sources: [Claude memory](https://code.claude.com/docs/en/memory), [skills lifecycle](https://code.claude.com/docs/en/skills#skill-content-lifecycle), [environment reference](https://code.claude.com/docs/en/env-vars), [network trust](https://code.claude.com/docs/en/network-config#ca-certificate-store), [official Codex Markdown AGENTS guide](https://learn.chatgpt.com/docs/agent-configuration/agents-md.md), read2026-10-06; [Claude2.1.292 changelog](https://github.com/anthropics/claude-code/blob/fbe20e00e2851fc01506f54f98a8f0b875af3847/CHANGELOG.md). Installed Claude artifact/byte windows and qualified comparison limits are in review.json; assignment source is resolver-assignment.json.

J805 fixes: the residual map covers the exact Codex lane guard, uv CI downloader/hash, generated installer/acceptance/Python selections, Inspect/Scout's Harbor package, producer contract, vLLM/Collector recipes and inactive template. SDK/bundled CLI0.160.0, dedicated SDK interpreter, dated holds, rollback and macOS pins are classified separately. The idleCompaction source now names the actual byte-window line113; row updates are by key, not duplicates. No executable pin/guard is changed by this decision PR.

### Evidence-class table

| Claim | Evidence class | Command / receipt |
| --- | --- | --- |
| Profile, bootstrap, plan, CI and trading consumers differ | source_review | Immutable main reads and exact linked locators |
| Installed host-tool versions match the plan; F12 drift is dated | local_integration, read-only version observation | selection.json; normalized versions and command labels explicitly identified |
| Selected default versions have official release identities/dates | source_review | Maintainer release/ref metadata; no downloaded-asset verification or new runtime acceptance |
| Every in-scope consumer is named; qualification is not inferred | source_review, independent completeness critic | 0P1/0P2; two P3 provenance refinements corrected |
| Publication integrity | local_integration | Nice19 validate.py exit0 after registration; this is integrity/scope evidence only |

### Local commands run

```text
Fresh owned worktree creation from origin/main with Worktrunk --no-hooks
exit0; hooks skipped for the paper window; original worktrees preserved.
Installed --version and cached official release/ref reads
exit0; source ledger records normalized versions, not full argv/raw outputs.
Independent bounded completeness critic
0P1/0P2; two P3 source/provenance refinements fixed.
git diff --check / staged whitespace check
exit0.
host_receipts.register_file for the two owned new files
exit0; registry-only commit LAST.
python3 scripts/validate.py
Exit0 under the later REBASE-805/J805 authorisation for light checks with the paper session inactive; repeated after J805 evidence registration.
```

### Open shared-file neighbours

#802, #770, #769 and #764 also edit upstream-surface-dispositions.json. Rebase after any lands first and take main's catalog. Preserve unrelated rows, update the three existing document rows by key, and append only newly reviewed name rows. Keep #802's corrected context_management source locator. Queued branches remain 5f-only. This PR remains currency-written and draft while the review completes.

J805 checks:6 DispositionCitationTests pass (nice19), actual proposed source113 passes the existing predicate while old line1 is rejected, and bounded independent completeness critic reports no remaining material P2. Source-review findings are not new runtime acceptance.

### Decision record

`docs/decisions/2026-10-06-one-host-tool-default.md` names defaults, full residual inventory/exceptions, owners and overturn conditions. `docs/decisions/2026-10-06-harness-context-budget-refresh.md` records the reopened partial C5 review and proposed CC-only sentences. Executable one-pin acceptance remains pending owners' folds.

### Host evidence

No evidence/hosts or platform-status change. Version output is not native adoption or a passed new host run.

- [ ] Host-receipt validation: not applicable.
- [x] Independent source/consumer completeness read recorded.
- [x] No platform-status update inferred.

### Checklist

- [x] No Actions/workflow permissions change.
- [x] No credential values/files read or committed; no new required secret.
- [x] No paid hosting/subscription/billing surface.
- [x] Peer-owned files, historical receipts, main and other worktrees preserved.
- [x] Registry committed last; draft retained.
- [x] Nice19 local publication validation passed for the registered J805 content; no native acceptance inferred.

### Scope

Record the owner's 2026-10-06 foundation-selection rule: use upstream evidence for component choices, maintain clean installations, and verify our wiring with smoke checks and organic native counters. The decision names all six superseded gate groups, the 13-row #723 cohort, retained checks, re-scoped S4, alternatives and the upstream-change comparison that reopens a choice. Four current policy guides gain a pointer to this rule; instruction-file changes remain a CC handoff.

B3's read-back ruling is an appended, dated "Amendment 2026-10-06" section in the October5 context-budget decision:23 lines inserted,0 removed. NativeStack's part is waived until retirement; the recorded NativeStack2604 pass and Skills row remain historical observations, and the co-op owns the remaining bounded SDK read-back. The CC's clarified preservation rule permits this addendum form. No existing historical or DECIDED line is edited.

- Base commit: `d9eb68750311d5f888adec140723da174f9fe10c`.
- Lane: `lane:foundation` (sole label).
- Owned source paths: NEW `docs/decisions/2026-10-06-upstream-evidence-over-local-evaluation.md`, the appended B3 section in `docs/decisions/2026-10-05-harness-context-budget.md`, `docs/acceptance-evidence-policy.md`, `docs/convergence-architecture.md`, `docs/harness-defaults.md`, `docs/token-practice.md`, and `catalogs/foundation/upstream-surface-dispositions.json`.
- The October5 record's existing text remains unchanged. Its append-only form is byte-identical to reviewed58dff931's file, SHA256 `dd3df75f9a7c2d736c476f6df07ffdb4e83e960ccfad79ba3f1826810986cbef`. Existing receipts and measured observations retain their history.
- `manifests/evidence.json` registrations are in the final registry-only commit. The two active `context_management` disposition citations point to line134 after the current policy pointer.

## SOTA sources

- [affaan-m/ECC](https://github.com/affaan-m/ECC/blob/2b6e839771e53096d8451a213d40dc64ec8acac0/skills/search-first/SKILL.md), commit `2b6e839771e53096d8451a213d40dc64ec8acac0`, Workflow and Decision Matrix: source-backed discovery and reuse.
- [modelcontextprotocol/modelcontextprotocol](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/38c84e9f93ad191d9eb26d92b945d17bd0efcaf3/docs/specification/2025-11-25/basic/lifecycle.mdx), commit `38c84e9f93ad191d9eb26d92b945d17bd0efcaf3` / protocol tag `2025-11-25`, Initialization and Operation: client/server negotiation and native operation underlying wiring checks.
- [promptfoo/promptfoo](https://github.com/promptfoo/promptfoo/blob/0.123.1/README.md), tag `0.123.1`, README: upstream application-evaluation tooling retains its appropriate integration scope.
- [anthropics/claude-code](https://github.com/anthropics/claude-code/blob/v2.1.289/CHANGELOG.md), tag `v2.1.289`, changelog, and [Claude memory documentation](https://code.claude.com/docs/en/memory), reviewed2026-10-06: native context surfaces underlying the preserved context-budget record.
- Policy authority: CC interpretation `ITEM-ns2604-coop-20261006T190307Z.md`, SHA256 `425a46312a9dae9a2234e2ec64951f802b389bbb0c11cf744ac120dcce2f4734`; B3 item `task-ns2604-coop-20261006T203515Z`, section5; final preservation scope item `task-ns2604-coop-20261006T230116Z`; FormA item `task-ns2604-coop-20261006T230854Z`. The records paraphrase the policy and contain no verbatim owner quotation.

### Evidence-class table

| Claim | Evidence class | Command / receipt |
| --- | --- | --- |
| Five rules, six superseded gate groups, retained checks and S4 match the CC interpretation | source_review | Canonical item190307Z and independent GPT read; named sources are linked in the new decision |
| The #723 cohort contains exactly13 named rows | source_review | `foundation-eta-rerun-wf_91416191-566.json#/result/units/0/result/items`; indices6,10,11,13,14,18,46,48,49,50,51,64,70 independently checked |
| B3 records its waiver, measured observation and deferred SDK check without a new host run | source_review | `session-d91d55ad-20261006/IMPROVEMENT-MANIFEST.md` B3, SHA256 `38b27a5646c65d6a5afdb1478f5312c411b038a13b12c576e636e138b5d7284d`; item203515Z section5/B3, SHA256 `fd44de4938cc96e9efcb29f8b7a17077275427b746455a275ca9db5a75f64966` |
| B3 is an append-only dated amendment; reviewed58dff source content survives a pure main rebase | source_review | Four source commits are patch-equivalent, append-only diff and dd3df75f... hash; independent rebase/registry critic |
| Registry, references and active disposition citations pass locally | local_integration | Fresh native validate and upstream_surface_watch module below; returned streams retained privately |

### Local commands run

```text
rtk proxy nice -n 19 ionice -c3 python3 scripts/validate.py
exit0:69components,10383hashedfiles,4profiles,223receipts

rtk proxy nice -n 19 ionice -c3 python3 -m unittest tests.test_upstream_surface_watch
exit0:114tests,6skips

rtk proxy git diff --check
exit0
```

These are structural and local integration checks. The B3 Skills figure describes its retained `/context` row; it establishes no provider-token saving or comparative benchmark. Native streams and earlier failed/reviewed attempts remain durable. FormA preserves reviewed58dff's content with only a rebase and registry regeneration; the withdrawn separate-record move is retained privately and is absent from this PR.

### Decision record

`docs/decisions/2026-10-06-upstream-evidence-over-local-evaluation.md` contains the selection/evidence rule and CC instruction handoff. The dated B3 amendment in `docs/decisions/2026-10-05-harness-context-budget.md` carries its alternative and overturn comparison beside the original gate. The new decision's B3 link targets that amendment.

### Handoff to the CC

The decision lists the instruction sentences in `AGENTS.md`, `examples/claude-native/CLAUDE.md`, `adoption/templates/codex.AGENTS.template.md` and `adoption/scaffold/AGENTS.md` whose selection/evaluation scope needs to follow the rule, including AGENTS.md:9's foundation-selection reference. Those files and deployed configuration are outside this PR. FormA retains the earlier content acknowledgement; the co-op checks the pure range-diff and new-head CI before5f lands.

### Host evidence

No `evidence/hosts/` files or live client configuration change. B3 reports existing observations; the SDK kit owner performs the deferred bounded-job check.

### Checklist

- [x] Third-party action pin requirements retained; no workflow change.
- [x] Workflow permission requirements retained; no workflow change.
- [x] No secrets printed or committed; no new required secret.
- [x] No paid hosting, subscription or billing surface added.
- [x] Peer-owned instruction, install-plan, evidence and decision files preserved.

### Scope

Enforce the owner's 42-day model-currency rule in the existing offline validator, add daily review proposals, and fill the ruled partial inventory. This combined revision closes J826's three P2 findings, keeps J826b's simple background tasks on Haiku's own line, prepares independent model carriers and proposes MinerU's persistent local-source unit.

- Base: `3d7d4a4b2640c8583d8855670111ef5d023d3e03`; no rebase for this revision.
- Head: `de7a7f2b6b6d7eac4241701b5c06a63b3265cbe0`.
- Lane: `lane:foundation`; draft.
- Owned paths: model catalog/schema, existing validator/freshness proposer, currency and MinerU unit templates, focused tests, independent model carriers, current guides, dated decision amendments and new evidence. Shared stack model rows, current catalog citations and registry go in the last commit.
- **Named landing path:** co-op GPT delta read → command center ACK → 5f's queue **after #810 and before #645**. Keep draft until that read and ACK; rebase once on the landing cue.

The inventory declares **21 artifact/model-consumer rows and seven package snapshots**, remains `pending`, and retains **eight unresolved groups**. Passing validation checks declared rows; it does not prove complete inventory or deployed selections.

**FILL item 7 is a prerequisite, not a completed fold.** Independent Nemotron endpoint/prefix carriers are prepared, but fixwave-defects owns the six-field memory-owner amendment to the living install plan/generated installer. It rides #810 after finding-2, per A26/A28/A27b. This lane neither recreates the absent generator nor hand-edits `install.sh`. The ai-memory example requires 2.5.2 prefix support; its stack component remains 2.4.1 under the model-only scope. This PR does not claim all folds 7/8/9 complete.

Bounded item-7 state at landed #723 (`41b65ac6bf574afa247a2542e70340a3cadf38bb`): [install-plan.json:1590-1597](https://github.com/seathatflowsinourveins/native-agent-stack/blob/41b65ac6bf574afa247a2542e70340a3cadf38bb/evidence/artifacts/new-wsl-install-plan-20261002/install-plan.json#L1590-L1597) selects ai-memory 2.5.2, but its [memory command at :1599](https://github.com/seathatflowsinourveins/native-agent-stack/blob/41b65ac6bf574afa247a2542e70340a3cadf38bb/evidence/artifacts/new-wsl-install-plan-20261002/install-plan.json#L1599), [notes at :1644](https://github.com/seathatflowsinourveins/native-agent-stack/blob/41b65ac6bf574afa247a2542e70340a3cadf38bb/evidence/artifacts/new-wsl-install-plan-20261002/install-plan.json#L1644) and [generated install.sh:465](https://github.com/seathatflowsinourveins/native-agent-stack/blob/41b65ac6bf574afa247a2542e70340a3cadf38bb/evidence/artifacts/new-wsl-install-plan-20261002/install.sh#L465) still select local MiniLM. The [stack component at :96](https://github.com/seathatflowsinourveins/native-agent-stack/blob/41b65ac6bf574afa247a2542e70340a3cadf38bb/manifests/stack.json#L96) remains 2.4.1. Fixwave's prerequisite patch owns all six settings: `embedding_provider=openai-compat`, `embedding_base_url=http://127.0.0.1:28231/v1`, `embedding_model=nvidia/Nemotron-3-Embed-8B-BF16`, `embedding_dim=4096`, `embedding_query_prefix="query: "`, and `embedding_document_prefix="passage: "`. This source review does not establish the host's effective configuration.

**MinerU's unit is source-only.** It sets `MINERU_MODEL_SOURCE=local`, supervises the shipped foreground DocLib module and carries `OnFailure=stack-alert@%n.service`. The embedded CPU guard is a **gap dated 2026-10-07**: no documented embedded ingress was found in the inspected installed source/tag. The maintained external wrapper offers a separate supported ingress and lifecycle for the CC to consider. The CC resolves the CPU precondition before activation, verifies managed mode/tier, applies the unit and performs the fresh-shell smoke. No host setting is applied here.

### CI repair at this head

The previous head `5a6842f1` failed the hosted 11,544-test suite (nine failures, one error). This revision repairs all four dependency groups: retain the complete historical 1B model/evidence record with retired-on-2604 scope and its current locator; restore the portable Claude endpoint defaults while retaining 8B/4096; disclose the post-release MCP change on three setup pages; and move the SDK disposition citation to its actual assertion line.

The setup-page changes regenerate both handbook outputs with the repository's existing builder. The original October 1 receipt stays byte-identical. A new dated [handbook projection](https://github.com/seathatflowsinourveins/native-agent-stack/blob/de7a7f2b6b6d7eac4241701b5c06a63b3265cbe0/evidence/artifacts/model-currency-enforcement-20261007/handbook-projection.json) binds the current bytes; the publication test changes only its receipt locator and keeps every exact assertion. No parity, release-marker, pin-source or citation oracle is relaxed.

All 23 targeted failure/negative-control tests and 95 handbook/stack/pin tests pass (exit 0). Validation passes before and after the final shared-metadata/registry commit (exit 0, 10,404 file hashes). The [CI repair receipt](https://github.com/seathatflowsinourveins/native-agent-stack/blob/de7a7f2b6b6d7eac4241701b5c06a63b3265cbe0/evidence/artifacts/model-currency-enforcement-20261007/ci826-repair.json) retains the hosted failure and local failed attempts. The new head's hosted CI and synthetic-merge execution are separate, still unverified observations. One same-branch push; no rebase, host apply or #790 change.

## SOTA sources

- CI dependency sources: `native-agent-stack@5a6842f`: `adoption/hosts/example.json`, `tools/adoption/install_claude_profile.py:350-378`, `tests/test_install_claude_profile.py:1509-1530`, `tests/test_adoption_docs_consistency.py:499-538`, `tests/test_new_wsl_handbook.py:1672-1689`, and `tests/test_upstream_surface_watch.py:2054-2060`; original 1B fields at `native-agent-stack@3d7d4a4:manifests/stack.json:2098-2109`. The new dated decision amendment records the exact source contracts and preserves historical acceptance.

- `huggingface/[email protected]` / `bd4a76030582d118e28dc9ad6c7a5911ea76176b`: [native models-info CLI](https://github.com/huggingface/huggingface_hub/blob/bd4a76030582d118e28dc9ad6c7a5911ea76176b/src/huggingface_hub/cli/models.py#L223-L237), [moving main revision](https://github.com/huggingface/huggingface_hub/blob/bd4a76030582d118e28dc9ad6c7a5911ea76176b/src/huggingface_hub/constants.py#L60), [metadata semantics](https://github.com/huggingface/huggingface_hub/blob/bd4a76030582d118e28dc9ad6c7a5911ea76176b/src/huggingface_hub/hf_api.py#L799-L819), [implicit-token early return](https://github.com/huggingface/huggingface_hub/blob/bd4a76030582d118e28dc9ad6c7a5911ea76176b/src/huggingface_hub/utils/_headers.py#L147-L151). Installed native 2.1.1 is reused. P2a keeps exact Hub origins independent of package age.
- [GitHub latest-release API](https://docs.github.com/en/rest/releases/releases#get-the-latest-release) and [PyPI JSON API](https://docs.pypi.org/api/json/#get-a-project), read 2026-10-07, supply primary metadata; changes become review requests.
- [Python 3.13 URL parsing](https://docs.python.org/3.13/library/urllib.parse.html#urllib.parse.urlsplit) documents lazy port errors and control/space stripping. The check rejects raw whitespace/C0/C1 controls before parsing and evaluates `parts.port` (P2c). [JSON Schema object semantics](https://json-schema.org/understanding-json-schema/reference/object#additionalproperties) supplies `additionalProperties: false` on complete object definitions, mirrored by validator allowed-key checks (P2b); partial conditional schemas are not incorrectly closed.
- [Filled primary provenance](https://github.com/seathatflowsinourveins/native-agent-stack/blob/de7a7f2b6b6d7eac4241701b5c06a63b3265cbe0/evidence/artifacts/model-currency-enforcement-20261007/fill-source-review.json) preserves packet SHA-256 `44679fd1d26dfec36b3b57cdbde2df4290d1b068118562cb8811bf3eb7cd6941`, per-row vendor/artifact/package sources and corrections. Unknown identities remain pending. Haiku's public date is from [Anthropic's October 15, 2025 announcement](https://www.anthropic.com/news/claude-haiku-4-5); the exact ID is checked against [the current Haiku specification](https://platform.claude.com/docs/en/models/haiku-4-5/overview), read 2026-10-07. Its snapshot suffix is not its public launch date. A Haiku 5.x ID overturns this dated exception.
- `akitaonrails/[email protected]` / `7580b74d0fb9d14a6d949dc92f5ea8bb7feb3c83`: [prefix configuration](https://github.com/akitaonrails/ai-memory/blob/7580b74d0fb9d14a6d949dc92f5ea8bb7feb3c83/crates/ai-memory-cli/src/config.rs#L454-L502) and [factory wiring](https://github.com/akitaonrails/ai-memory/blob/7580b74d0fb9d14a6d949dc92f5ea8bb7feb3c83/crates/ai-memory-llm/src/factory.rs#L262-L269). Other independent carrier sources and exact pins remain in the [fill amendment](https://github.com/seathatflowsinourveins/native-agent-stack/blob/de7a7f2b6b6d7eac4241701b5c06a63b3265cbe0/docs/decisions/2026-10-07-model-currency-enforcement.md#amendment-2026-10-07-ruled-partial-fill-and-current-carriers). Installer/component alignment stays owner-routed.
- `opendatalab/[email protected]` / `c221cc41bc911ad0df3eaeda97acf6a1bfe9bf93`: [documented server command](https://github.com/opendatalab/MinerU/blob/c221cc41bc911ad0df3eaeda97acf6a1bfe9bf93/README.md#L462-L484), [native foreground-module launch](https://github.com/opendatalab/MinerU/blob/c221cc41bc911ad0df3eaeda97acf6a1bfe9bf93/mineru/cli/commands/server.py#L242-L248), [module entry](https://github.com/opendatalab/MinerU/blob/c221cc41bc911ad0df3eaeda97acf6a1bfe9bf93/mineru/doclib/app.py#L443-L449), [environment override](https://github.com/opendatalab/MinerU/blob/c221cc41bc911ad0df3eaeda97acf6a1bfe9bf93/mineru/config.py#L156-L176), and [managed-parser inheritance](https://github.com/opendatalab/MinerU/blob/c221cc41bc911ad0df3eaeda97acf6a1bfe9bf93/mineru/doclib/background/parse_server_health.py#L205-L221). [Embedded kwargs](https://github.com/opendatalab/MinerU/blob/c221cc41bc911ad0df3eaeda97acf6a1bfe9bf93/mineru/model/vlm/runtime.py#L175-L180) differ from the [external wrapper's environment ingress](https://github.com/opendatalab/MinerU/blob/c221cc41bc911ad0df3eaeda97acf6a1bfe9bf93/mineru/kit/vlm_server/llama_cpp_server.py#L263-L273); installed `mineru_llama_cpp/engine.py:46-52,107-108` defaults to 99 GPU layers. This is repository systemd integration, not an upstream systemd recipe.
- `systemd/[email protected]` / `b3d8fc43e9cb531d958c17ef2cd93b374bc14e8a`: [currency command-failure prefix](https://github.com/systemd/systemd/blob/b3d8fc43e9cb531d958c17ef2cd93b374bc14e8a/man/systemd.service.xml#L1443). MinerU follows [systemd@v260 service semantics](https://github.com/systemd/systemd/blob/v260/man/systemd.service.xml#L158), [failure/start limits](https://github.com/systemd/systemd/blob/v260/man/systemd.unit.xml) and [control-group stop semantics](https://github.com/systemd/systemd/blob/v260/man/systemd.kill.xml#L56), checked against the installed 259 manual. Alerting covers DocLib/unit failure, not a parser failure that leaves DocLib alive.
- `native-agent-stack@3d7d4a4`: `scripts/freshness_propose.py:861,942`, `scripts/validate.py:144,484`, `adoption/templates/systemd/stack-currency.service:16-26`, `docs/acceptance-evidence-policy.md:24-38`, `docs/lanes.md:94-115`. The owner-defined 42/7-day policy and package join are the deterministic gap. No upstream is rebuilt and no validator executable is added.

### Evidence-class table

| Claim | Evidence class | Command / receipt |
| --- | --- | --- |
| UTC clock, 42/43-day and 7/8-day boundaries, package join, J826 P2 positive/negative controls | `synthetic`, `local_integration` | 113 combined policy/proposal/existing-validator tests, exit 0; [new J826 checks](https://github.com/seathatflowsinourveins/native-agent-stack/blob/de7a7f2b6b6d7eac4241701b5c06a63b3265cbe0/evidence/artifacts/model-currency-enforcement-20261007/j826-checks.json). |
| Primary filled dates/revisions, retained exceptions and unresolved roles | `source_review` | `fill-source-review.json` records the earlier 20-row partial fill; `j826-checks.json` adds the source-reviewed Haiku ruling and current 21-row state. Seven packages and eight unresolved groups remain; no inference or live-selection claim. |
| Legacy currency proposer/timer compatibility | `local_integration` | Earlier 91 checks, exit 0, in `checks.json`. |
| Handbook/stack/pin carriers and SDK controls | `synthetic`, `local_integration` | Earlier 95 handbook/stack/pin checks and 27 SDK tests, exit 0, in `fill-checks.json`; the recorded 516-test carrier check also exited 0. |
| MinerU source/failure/lifecycle template | `synthetic`, `local_integration` | Eight focused tests and unit syntax verification, exit 0, in `fill-checks.json`; no host application. |
| Repaired architecture, portable parity, release disclosures and citation controls | `synthetic`, `local_integration` | 23 targeted tests plus 95 handbook/stack/pin tests, exit 0; `ci826-repair.json` and dated `handbook-projection.json`. |
| Publication consistency after the registry-last commit | `structural_validation` | `exit 0; 69 components, four profiles, 223 receipts, 10,404 file hashes; structural integrity/scope only`. |

### Local commands run

Checks use owned durable scratch and `nice -n 19 ionice -c3`.

```text
python3 -B -m unittest tests.test_model_currency tests.test_model_currency_propose tests.test_validate
exit 0: 113 tests after J826 fixes.
python3 -B -m unittest tests.test_new_wsl_handbook tests.test_stack_lifecycle tests.test_foundation_stack_pins
exit 0: earlier 95 tests.
uv run --no-project --with claude-agent-sdk==0.2.162 python3 -B -m unittest discover -s examples/claude-runtime-sdk/tests
exit 0: 27 tests.
uv run --no-project --with claude-agent-sdk==0.2.162 python3 -B examples/claude-runtime-sdk/tests/check_controls.py --disarm-route
exit 1: deliberate negative; unchanged normal control exit 0.
python3 -B -m unittest tests.test_mineru_user_unit
exit 0: 8 tests.
systemd-analyze --user verify adoption/templates/systemd/mineru.service
exit 0: syntax only; no unit loaded or started.
nice -n 19 ionice -c3 python3 -B scripts/validate.py
exit 0; 69 components, four profiles, 223 receipts, 10,404 file hashes; structural integrity/scope only
```

The **two-day advance refresh is included**, beginning on landscape-check day five. The collector appends private review JSON/Markdown rather than publishing a GitHub PR, renewing dates or switching models. Hub SHA differences are revision candidates, not proof of new weights. Unsupported vendor-page adapters request source review. The initial pending/empty offline dry run returned `complete_inventory`, zero source checks and no writes; it remains a dated scaffold observation.

Retained failed attempts remain in the original receipts: the initial legacy check's old owned-file hash failure, the fixture's missing overturn field and the scratch-classification correction. Historical observations and decided text are preserved; new checks and dated amendments extend them.

### Decision record

[Dated decision and amendments](https://github.com/seathatflowsinourveins/native-agent-stack/blob/de7a7f2b6b6d7eac4241701b5c06a63b3265cbe0/docs/decisions/2026-10-07-model-currency-enforcement.md) records alternatives, sources, overturn triggers, partial fill and J826/J826b. [Current guide](https://github.com/seathatflowsinourveins/native-agent-stack/blob/de7a7f2b6b6d7eac4241701b5c06a63b3265cbe0/docs/model-currency.md) carries the pending item-7 prerequisite. [MinerU recipe](https://github.com/seathatflowsinourveins/native-agent-stack/blob/de7a7f2b6b6d7eac4241701b5c06a63b3265cbe0/recipes/mineru-local-service.md) carries CC activation and the dated embedded-guard gap.

Receipts: [initial checks](https://github.com/seathatflowsinourveins/native-agent-stack/blob/de7a7f2b6b6d7eac4241701b5c06a63b3265cbe0/evidence/artifacts/model-currency-enforcement-20261007/checks.json), [fill checks](https://github.com/seathatflowsinourveins/native-agent-stack/blob/de7a7f2b6b6d7eac4241701b5c06a63b3265cbe0/evidence/artifacts/model-currency-enforcement-20261007/fill-checks.json), and [new J826 checks](https://github.com/seathatflowsinourveins/native-agent-stack/blob/de7a7f2b6b6d7eac4241701b5c06a63b3265cbe0/evidence/artifacts/model-currency-enforcement-20261007/j826-checks.json). Raw logs stay private.

### Host evidence

No new host receipt/status is promoted. No weights, inference, package bump, live model switch, timer/service installation or client-configuration change was run for this revision. CC MinerU application and fresh-shell acceptance remain pending; A23's one-page parse remains a separate dated observation. Complete inventory, unsupported adapters, native timer execution and whole-unit timeout recovery remain unqualified. Item 7's owner-routed prerequisite is not counted as a completed fold.

### Checklist

- [x] Draft, exactly `lane:foundation`, named read/ACK/queue path.
- [x] No new validator executable, rebuilt upstream, workflow or paid surface.
- [x] No credentials inspected, logged or committed; Hub implicit auth disabled.
- [x] Peer-owned paths/heads and queued branches preserved.
- [x] Historical results/decided text preserved; dated amendments and new receipts used.
- [x] Targeted controls pass; partial inventory and pending owner/CC apply gates explicit.
- [x] Final stack/registry commit is last; validation passed before and after it (exit 0).

### Scope

Provision the NativeStack2604 Lanes dashboard and retain the native dimensions needed to distinguish tool, hook, skill, service and token activity. Monitoring steps 6–8 include the collector route, supported file provisioning and matching install-plan acceptance. A13 makes main's rendered Prometheus unit the sole startup carrier; the old drop-in is a dated, inert, do-not-apply record. Activation and start-timestamp/new-turn qualification remain the command center's later host step.

- Landing base commit: `475127d43c1cce70dba5cd31238af4e078fa17eb` (the command center's relayed #645 squash merge).
- Lane: `lane:foundation`.
- Owned paths: observability collector/dashboard/readers, focused checks, generated NativeStack2604 Grafana assets, monitoring install-plan mirrors and dated decisions.
- Shared install-plan changes preserve landed #723/A27 qualification, custody and the authoritative rendered Prometheus unit. The repair was replayed once onto #645's relayed squash merge. The Grafana notes retain main's exact W1b selection/qualification statement and re-apply the reviewed dashboard/provisioning note. Main's registry is restored and owned rows are regenerated last; no shared registry lines are hand-merged.

The Lanes UID is `cc-lanes`, provisioned under the existing Token efficiency provider. Withdrawal is file based: restore the prior `lanes.json`, or remove only it, temporarily allow provider deletion, restart in a permitted slot, verify the anonymous dashboard endpoint returns 404, and restore `disableDeletion: true`. Keep token-layer, the provider and private registry.

Every provisioned dashboard using `codex_turn_token_usage_sum` carries lower-bound titles and descriptions until deployed start timestamps and a newly born single-turn reconciliation pass. The standalone template-copy publisher and maintained renderer share that policy. Latest unknown status values retain nulls; known RTK zero share requires an observed classified-shell denominator.

One clock panel retains the producer's 50 ms error-bound warning, 100 ms absolute-offset critical threshold and 1,200 s reference-age warning. Its separate three-minute UI freshness preserves missing data as No data. Collector serialization and native configuration validation pass; live clock-panel acceptance remains pending.

## SOTA sources

- [Codex rust-v0.160.1 / immutable source](https://github.com/openai/codex/tree/d27764b82f7118f674371e6d6e76271d9d606edb/codex-rs/otel): `events/session_telemetry.rs` and config schema for native named tool events. Native `item_completed` and fork-history metadata supply the bounded readers.
- [OpenTelemetry Collector Contrib v0.162.0](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/v0.162.0): transformprocessor, signaltometricsconnector, spanmetricsconnector and otlpjsonfilereceiver for bounded dimensions, sanitization and supported routes.
- [Grafana v13.2.3 file provisioning](https://github.com/grafana/grafana/blob/v13.2.3/docs/sources/administration/provisioning/index.md): provider deletion policy and JSON dashboard format. [Loki v3.7.8 metric queries](https://github.com/grafana/loki/blob/v3.7.8/docs/sources/query/metric_queries.md): range aggregation and observed-denominator zero filling.
- [Prometheus v3.15.0](https://github.com/prometheus/prometheus/tree/v3.15.0): `created-timestamp-zero-ingestion` feature flag; deployed single-turn reconciliation remains required.
- [OmniRoute v3.8.51](https://github.com/diegosouzapw/OmniRoute/tree/v3.8.51): `open-sse/services/routing/otel.ts` optional upstream GenAI OTLP sink. Its environment application and native identity qualification remain with the command center.

### Evidence-class table

| Claim | Evidence class | Evidence |
| --- | --- | --- |
| Named nested context-mode and RTK shell results reach Loki | native_proven | Retained one-shot per-run Codex OTel probe, 2026-10-06; no repeated model probe |
| Native BEFORE readers exclude inherited history | local_integration | Bounded 90-minute/246-minute receipts; method differences remain recorded |
| Fork/window/dedup, null-preserving status and provisioning behavior | synthetic / local_integration | Focused fixtures and 12 dashboard tests; not unchanged upstream acceptance |
| Both Collector configurations are valid | native_proven | Installed Collector validation, exit 0; configuration validation is not host application |
| Dashboard routes and file-based withdrawal follow supported formats | source_review / local_integration | Pinned provisioning sources, actual publisher coverage and passing install-plan checker; no deployed browser acceptance |

### Local commands run

```text
nice -n 19 python3 -m unittest tests.test_ns2604_dashboards
exit 0; 12 tests pass, including every provisioned Codex-token dashboard and standalone portability

nice -n 19 python3 evidence/artifacts/new-wsl-install-plan-20261002/check_plan.py
exit 0; 84 rows, 186 commands and 113 acceptance entries agree

nice -n 19 otelcol-contrib validate --config=evidence/artifacts/new-wsl-install-plan-20261002/config/otel.yaml
nice -n 19 otelcol-contrib validate --config=observability/collector/collector.yaml
both exit 0

nice -n 19 python3 scripts/validate.py
exit 0; 69 components, 10,379 hashed files, 4 profiles, 214 receipts

git diff --check
exit 0
```

The initial plan-check failure from import-generated configuration bytecode is retained in the private check receipt. The loader now suppresses bytecode during dynamic imports, restores the prior setting and passes the rerun. Generated dashboard JSON is source evidence; it is not visual acceptance.

### Decision record

- `docs/decisions/2026-10-06-native-lane-invocation-observability.md`.
- `docs/decisions/2026-10-06-ns2604-native-dashboard-countability.md`.

The README classifies all six retained 13000 references without rewriting frozen observations and requires a compatible emitter checkout while its timer is enabled. Storage COUNT/AGE read-back, unit/GPU export, client limit headroom and the GitHub snapshot feed retain named owners and explicit remaining gates.

### Host evidence

No host receipt or client configuration is applied by this PR. Host apply waits for the GPT delta read, command-center ACK and the permitted post-Claude-window slot. Native Loki/Prometheus read-backs and an anonymous browser capture remain required.

Organic BEFORE/AFTER counts are not yet measured under the all-prompts, first-turn and actual steer-visibility rules. Effective role grants and referenced co-op blocks remain coverage gaps. No exclusion, readiness or token-row closure is claimed. No local A/B or trial gates today's read-back.

### Earlier rebase

Commit 1 (`f19626d6` → `35bfa72f`) preserves main's Grafana
`--show-error --output "$GRAFANA_HEALTH_FILE"` flags and uses the same flags
in the NativeStack2604 port annotation. Commit 4 (`ceaca5ee` → `a752852c`)
changed only the surrounding anti-pattern-log context: both zero-context stable
patch IDs are `947dc92f4ad5ded7b6258d65eb1b290de6c294f2`, so its added/deleted
content is unchanged.

### Checklist

- [x] GitHub Actions changes: not applicable.
- [x] No secrets printed, logged or committed; no new required secret.
- [x] No new paid hosting, subscription or billing surface.
- [x] Peer-owned worktrees and unrelated files preserved.
- [x] Registry commit is last; PR remains draft for cross-family review.



## Landing review follow-up

The local follow-up preserves landed metric privacy and records the configured source/query for every invoke column. Validated native names remain on Loki; bounded native metric keys remain permitted where the provider supplies them, and hook identity is qualified as lifecycle rather than repository identity. It restores main's run-correlation test byte-for-byte and removes run correlation from every exported metric route, while retaining log correlation. The clock serialization note moves verbatim into a dated appended amendment, and renderer source references use named exporter sections. F6/F7 remove the unnecessary agentsview version literal from the health comment. F8 preserves render-only Grafana checking and requests installed-unit byte verification explicitly in the three acceptance calls and their plan mirrors. The next exact-head read covers all eight findings. No host activation or client change is included.

## Landing validation and path

The authorized landing replay is on475127d4 (#645). It preserves main's complete Grafana W1b notes and re-applies the reviewed dashboard note. All unowned main registry entries remain byte-identical, and all53 owned non-registry files have current registry hashes. Replay checks pass:223 affected tests (7 skips),721 tests in the eleven PyYAML-gated modules (47 skips), and six focused merger controls (no skips). Main's unchanged sources from475127d4 pass150 tests (7 skips), including the unchanged host-merger, tool-name and run-correlation modules. The install-plan and generated-dashboard checks pass; scripts/validate.py exits0. Native Node6/6 is reused from the completed phase because its inputs did not change.

The earlier complete Python phase on base003804f2 ran11,561 tests in the private, activated Python3.12 environment with checksum-locked CI dependencies and an initially empty HOME. It returned12 failures,1 setup error and1,211 skips. Each of the13 failing method/class selectors reproduces on clean main003804f2 in the same environment; no test was edited. These are declared baseline failures under the co-op's instructions, not a claim that the full phase passed. The setup-error selector is the runnable LinuxPlatformDependencyTests class. CI requirements SHA256:0b37433fb0fb165c893737e8e887581a07a6469683fbdf67ada1a08288758605; original pip-freeze SHA256:efd7c60ca69afe49918441138c3f3461b9c6e513628f562d5503362f8225c105. C1 exposed that this environment lacked the workflow's second pinned requirements file, so its YAML-gated tests had skipped. The replay adds unchanged requirements-validation.txt (SHA256:458d8cb1fef26d0d0a9a6a76707c0bad04fe84558550db750d50af206fecba81) and runs all eleven gated modules, as the command center directed instead of a second full phase. The new freeze SHA256 is e7d19cac4e91ceebe0d41b55581eb7a6dd8e7ebc021ce9a8b03dfe16056789d0. Original baseline logs and runnable IDs remain unchanged in durable lane state.

Landing path: the co-op's content read of27c8a4de closes F1–F8; the next head carries C1/V1–V4 and only the authorized #645 replay delta. The command center ACKs that head;5f alone lands it with green hosted CI. The relayed queue position is after#645;#825 remains dependent on LANDED775. The public hosted validate result remains the landing gate. Shared install-plan neighbour#723 is already landed and preserved.

## Contract changes

- `tests.test_observability_writer_identity.NativeCollectorTests`: kind5 runtime binding/eligibility adaptation, accepted by name under CC item171356Z. Maintained inputs are `manifests/stack.json:1102` (Collector pin) and `evidence/artifacts/new-wsl-install-plan-20261002/install-plan.json:2239` (native executable destination). The dated7October existing-native-writer-contracts amendment records the choice; it does not supply either maintained input.
- `NativeCollectorTests.setUp` and `.post`: kind2a synthetic fixture extensions for the new isolated guard/scope-attribute test; existing methods retain the prior pipeline and default payload.
- `NativeCollectorTests.test_sessions_and_processes_are_separate_writers_and_collapsed_streams_add_up`: kind1 assertion inventory, retained by name under CC item172216Z. All five prior main assertions remain AST-identical (Claude60/14, Codex2000/4000, phase4/4, no conversion errors, incoming session-group telemetry); exactly-two-point/no-agent-label checks add constraints. Main had no three-point assertion.

The npm setup-class failure is environment-dependent: this lane resolves npm to a mise shim invalid under empty HOME, while the co-op launcher places real node/npm directories first on PATH and all28 tests pass there. The lane's exact main-run failure remains in baseline-final-summary-failures.log and its class selector remains in the declared baseline file.

## C1 and V1–V4 closures

- C1: the maintained host merger explicitly copies the reviewed export guard and permits its one insertion immediately before conversion. Other host settings/order and refusal checks remain. Main's host module is byte-identical and passes; six new controls cover acceptance, idempotence, unknown processors, misplaced/duplicate guards, missing definitions and conflicting host settings.
- V1: the four existing-member declarations above are recorded in the dated native-writer-contracts and disposition amendments. The command center accepts the maintained runtime binding as kind5 and the session assertion inventory as kind1 by name.
- V2: the environment-dependent npm setup-class failure stays declared with its same main-run log; no test contract is weakened.
- V3: the disk-headroom decision gains only an appended dated amendment naming processors.batch.timeout; every earlier byte and its observed one-second value remain unchanged.
- V4: the current NativeStack2604 README explicitly requires the21300 manual Loki push URL.

The replay's extra adaptations are the dated M1/disposition record, preserved645 Grafana notes, the C1 merger guard/order support and new controls, the appended historical documentation locator and manual Loki endpoint instructions. The original fifteen disclosed adaptations remain. No host activation, client configuration or new feature selection is included.