docs: checkpoint row 332 and hand off after T3 crash

BUILD-LOG.md

@@ -5574,3 +5574,11 @@ claim. Receipts and limitations in agents/lena/work/queue-296/BUILD.md and run-r
 2026-10-24T19:44:50Z | Sage | Row 224 (#1725, C2-05b, Della on Codex, Dewey) LANDED 5e77cdd09, pushed 19:18Z 10-24. Before: refactor at 7fe32d722. After: Della's 13 commits cherry-picked onto 7fe32d722. Sage gate GREEN 19:16:37Z on 27624aa66 (base 06f507dbc): bus 1011/0, business 283/0, harness 176/0, cli 990/0 plus the allowed FED R7 skip, webui 458/0, all scripts rc 0. Drift between the gated base and 7fe32d722 is only docs/plans/2026-10-24_model-proxy-rows.md, which no test reads (mos-1601 condition); manifest-r9 952482b4 matches the landed tree. Dewey APPROVE c31619 rev 3999. #1725 closed c31623; note rev 4015, done rev 4016. Correction: the first done move passed --evidence and was refused (rc 2, the round closes on its recorded verdicts); rerun without it. Follow-up: Dewey's N3, the old ask helper can't serve a library business, goes to a later row. Not re-pinned.
 
 2026-10-24T19:44:50Z | Sage | Row 328 (#1826, Vikunja 622, old T9 timer race, Fethry on Codex, Boyd and Dewey) LANDED 8bb5b3c73, pushed 19:40Z 10-24. Before: refactor at 5e77cdd09. After: Fethry's 8 commits cherry-picked onto 5e77cdd09 (same patches); T9's second start passes intervalMs 2147483647 (mos-1594), test-only. Under 8x50 concurrent loops M1 (50 ms back) gave 26 expected failures and the fix 400/400. Boyd APPROVE c31621 rev 4002, Dewey APPROVE c31622 rev 4003. Sage gate GREEN 19:38:54Z on 8bb5b3c73 itself, no drift: bus 1011/0, business 283/0, harness 176/0, cli 990/0 plus the allowed FED R7 skip, webui 458/0, every scripts/test-*.sh rc 0 (Dewey N1). Manifest 1e010468. #1826 closed c31625, Vikunja 622 done (comment 1071), note rev 4019, done rev 4020. Not re-pinned.
+
+## 2026-10-24 — row332 P3 proxy harness configuration: investigation/test placement
+
+Fethry at c8a9bcf94, per Sage sage-4292 and mos-1616 pi-route amendment. Before: every managed session receives instance-wide provider credentials; harnesses have no transient per-session proxy context; pi preflight checks only its binary. Intended after: proxy-mode isolation, Claude proxy env, pi private run-local route config using environment references only, credential preflight, and business proxy account settings. Design/test plan: agents/fethry/work/queue-332/BUILD.md. Initial tests placed before production changes. No tests run: Sage CLEAR is required and has not arrived. No success/acceptance claim, live change, or dependency landing. Existing proxy issue number requested from Sage; not yet received.
+
+## 2026-10-24 — row332 crash stop, documentation-only checkpoint
+
+Fethry stopped under Mos mos-1630/Jason's T3 crash instruction. No production implementation, tests, probes, mutants or acceptance runs occurred; Sage CLEAR never arrived. Explicit route metadata per sage-4293 is recorded in agents/fethry/work/queue-332/BUILD.md; full state and resumption boundaries are in HANDOFF.md there. Safe crash checkpoint commits documentation/historical plain-text import manifest only; four unrun tests and the import-audit script remain uncommitted. No long jobs restarted, protected branch changes, merges, live changes or further thread messages.

agents/fethry/work/queue-332/BUILD.md

@@ -0,0 +1,88 @@
+# Row 332 — P3 harness config from the model proxy
+
+## Assignment and boundaries
+
+2026-10-24: Fethry, thread 65673bd9-3bfa-412b-85d5-9b364187d8b6, branch fethry/row332, baseline c8a9bcf94. Sage assignment sage-4292; accepted brief plus full pi-routes amendment c8a9bcf94 (mos-1616). Gladstone first review, Dewey landing review; landing waits for P1/329 and P2/331, rebase on both and Sage's gate. No tests before Sage's CLEAR. No live proxy, host credential directories, real proxy data, management key, cutover, policy edits, or Codex harness changes.
+
+Queue next in canonical checkout returned `nothing` during assignment. Starting row with op fethry-332-start met Sage's queue update lock; retry through the queue only. Root npm ci --ignore-scripts --no-audit --no-fund completed in this worktree (128 packages); no canonical node_modules use.
+
+## Design note (line numbers at c8a9bcf94)
+
+- packages/seat/src/session.mjs:242-247 defines ENV_ALLOW; keep it unchanged. sessionEnv:256-262 gains optional proxy context and drops CLAUDE_CODE_OAUTH_TOKEN, every passed ANTHROPIC_* variable, OPENAI_API_KEY, OPENROUTER_API_KEY and ZAI_API_KEY before adding harness env. Non-proxy results retain current behavior exactly.
+- packages/plugins/harness/claude-code/index.mjs:56-67 preflight accepts the session proxy credential; env:119-126 sets ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN from that context.
+- packages/plugins/harness/pi/index.mjs:33-36 preflight requires its own provider credential or proxy key, never a Claude OAuth token. env:63-70 sets only the session's proxy key as ANTHROPIC_API_KEY and selects the generated provider. Fresh run-local home/.pi/agent/models.json is private (0600; parent directories 0700). Every apiKey is the literal reference $ANTHROPIC_API_KEY; recursively forbid values beginning with !. Nothing stores the key in models.json or a manifest.
+- packages/harness/src/bundle.mjs:313 buildBundle accepts transient proxy context; :379 harness.env call needs it plus run location and launch.models. Context must never be added to session metadata, source digests, or manifest. The run-local file regenerates on each launch.
+- packages/cli/src/launcher.mjs:391,400 preflight, :412 account checks, :529 bundle creation and :592 child env must agree on the same session credential. Coordinate its acquisition with P2; build/test now against the specified { baseUrl, key } stand-in, not a management client or a key-store implementation.
+
+Exact business setting keys remain launch.models.<selection>.provider, launch.models.<selection>.model, launch.account.name and launch.account.credential (launch.mjs:12-24,81-89). Provider already accepts proxy. Proposed account credential sentinel is the literal proxy (add alongside existing uppercase environment-set syntax), with launch.account.name a human-readable id such as proxy. No new fields. Existing provider anthropic selects the Anthropic route, zai selects GLM, and proxy selects the stack-owned GPT route; send this interpretation to Sage before implementation because the brief doesn't specify route encoding for provider proxy.
+
+## Build-time API choice and pinned binary
+
+P1's committed magica/row329 has CLIProxyAPI 8.0.42 in packages/model-proxy/PIN. Use that commit's fetchPinned({dataRoot:<fresh temporary root>}) implementation, copied from Git objects to this seat's temp tooling directory with its relative dependencies and PIN, until P1 lands. Never inspect another seat's worktree/scratch. It fetches only pinned GitHub release assets and checks archive, executable and panel hashes. No production instance config is needed and nothing under a real dataRoot/proxy is read.
+
+After CLEAR, try actual pinned pi requests with both openai-responses and openai-completions through that binary under unshare -rn, against stand-in upstreams with made-up credentials under 24 characters. Record version, API path, safe request fields, response status and turn result. Choose one shape once from those results and hard-code it; no runtime fallback. Real Codex OAuth cannot be simulated as a real authenticated turn: first real Codex turn remains row209 phase A step7. Distinguish the offline compatibility evidence from that deferred real-auth proof.
+
+The separate offline GLM acceptance script (outside scripts/test-*.sh) uses pinned pi and proxy, checks the upstream sees the model id from /v1/models, and records whether thinkingFormat/zaiToolStream-derived fields survive translation. All configs/auth placeholders belong to its fresh temp root.
+
+## Implementation and test sequence
+
+1. Add tests first for env isolation, Claude proxy env and preflight, pi credential refusal and each generated route/file invariant, and business account acceptance. Do not run until CLEAR; first new-test red is reported afterward, old-test red or second red is reported before changing anything.
+2. Implement harness/bundle/env handling against P2's transient interface. Add launcher boundary integration once its exact P2 acquisition seam is agreed. Keep secrets out of session.json and bundle manifests.
+3. With CLEAR, run the offline API-shape probe and GLM turn, then whole touched test files. Before each whole-file run report the list derived by parsing imports and traversing local dependencies; include harness plug-in dynamic loading explicitly. packages/cli/tests/case1-accept.test.mjs remains excluded without Mos approval.
+4. Kill named mutants; restore production source and verify. Record exact output and nice. Use a fresh shell mktemp -d /mnt/storage/scratch/tmp/XXXXXX TMPDIR for each run, absolute nice 19, and timeout -k 10 for each scripts/test-*.sh. No hidden skips; Sage owns the package/script landing gate.
+5. After dependency landings, rebase, complete review and gate stages, update queue only through its CLI, and append session/build receipts. Push only fethry/* when ready for authorized review; no force-push or attribution trailers.
+
+Planned tests:
+- Each forbidden environment variable is absent in proxy mode; all existing allowed env is identical without a proxy; two launches receive distinct own keys and no other agent's key.
+- Claude env has exactly the supplied proxy base URL/auth token; proxy credential satisfies preflight without host upstream credentials.
+- pi refuses no-session-credential for no key or Claude OAuth alone, accepts an own provider key and a proxy key.
+- models.json covers Anthropic anthropic-messages at root URL, GLM openai-completions at /v1, and a stack-owned GPT provider at /v1 with the chosen API; routes use configured model ids.
+- Every apiKey is $ANTHROPIC_API_KEY; no key value occurs in file; recursively no value starts with !; mode 0600 and private parents; next launch uses changed port/models/key reference with no stale content.
+- Business accepts provider proxy and account credential proxy while preserving existing valid and invalid account behavior.
+- Launcher/bundle integration keeps context transient and passes only the launch's own key.
+- Every new refusal code gets a separate test.
+- Offline GLM pinned-pi turn and z.ai compat observation; both GPT API-shape requests recorded with limitations.
+
+Named gate mutants:
+1. Proxy mode still passes CLAUDE_CODE_OAUTH_TOKEN (original brief).
+2. models.json receives the key value instead of $ANTHROPIC_API_KEY (amendment).
+
+No tests have run. API-shape choice is pending evidence, not claimed.
+
+## Progress 22:27Z
+
+Placed initial RED tests (not executed): packages/seat/tests/proxy-session-env.test.mjs and packages/plugins/tests/proxy-harness.test.mjs. These exercise real sessionEnv and loader-loaded harness exports. Production source remains untouched pending the first authorized RED run. Removed no assertions and ran no tests. Correct baseline bundle harness.env line is 376 (not 379 in the initial design note).
+
+Sage reporting attempts fethry-0001 (including same-key retry) and fethry-0002 all returned `T3 GET /api/orchestration/threads/<sage> timed out after 30s`. Delivery is unconfirmed. Queue move retry also met a Sage queue update lock (sage-333-reviewers-1024a); no bypass.
+
+Additional test-first placement: packages/business/tests/proxy-launch.test.mjs covers existing proxy model acceptance, proposed proxy account credential literal, preserved environment account forms, and rejection of mixed/literal credential strings. Pending Sage's route/account interpretation and CLEAR; no production edits or tests run.
+
+## Import audit and queue status
+
+The non-evaluating import audit uses Node vm.SourceTextModule.dependencySpecifiers, not a text-path grep, plus explicit computed-import edges from the plug-in loader to both harness modules. Source: import-run-list.mjs; output: IMPORT-RUN-LIST.txt (211 entries, including the explicitly EXCLUDED case1-accept file). This is a candidate impact list for the planned source changes, not an executed test list. Before a whole-file run, report the actual authorized subset to Sage. Parsing executes no repository modules and runs no tests. The first audit invocation had a path-depth setup error (ENOENT); corrected the audit's own repository root and regenerated successfully.
+
+At 22:28:19Z the canonical start operation returned `queue: only the owner (sage) may start row 332`. Per assignment, wait at least two minutes before repeating this same op. No queue state was edited manually.
+
+## Design correction after D9 re-read
+
+The initial route-encoding proposal (provider proxy for GPT only) is not sufficient: design D9 explicitly defines provider proxy as any model through the instance proxy. Do not implement the earlier proposal. Two viable encodings need resolving before route-dependent tests/production: exact model-id lookup in pinned pi's provider catalogs (no new business fields, but refuses proxy-only aliases/unknown models), or explicit route metadata in launch.models (additive schema, needs Sage to confirm it is within the approved brief). Recommend exact catalog membership if all intended configured model ids are in pinned pi; otherwise ask Sage to define/approve an explicit route field. Never guess by model prefix or silently choose a wire API. Independent env/preflight tests already placed remain valid.
+
+Reporting recovered: fethry-0004 was accepted by t3_send_message at approximately 22:29:51Z. It delivered the D9 route correction, route-encoding/P2-seam question, import-manifest location and no-tests status to Sage. Earlier failed-message deliveries remain unconfirmed.
+
+22:32:18Z: The start retry issued at 22:30:40Z (over two minutes after first owner refusal) also exited 2: `queue: only the owner (sage) may start row 332`. This is an ownership boundary; row was not started and no code/test execution proceeds through it. Sage's assignment must take effect before the same op can succeed. The full design report fethry-0005 again timed out; fethry-0004 is the confirmed delivered report. git diff --check passed; no test, probe, commit or push has run.
+
+## Route ruling accepted — sage-4293, 22:37Z
+
+Sage settled explicit metadata, superseding both initial encoding proposals and the catalog proposal. Exact new setting: launch.models.<selection>.route; permitted values anthropic, glm, codex, required only when provider is proxy. Nonproxy entries still allow provider/model only. Missing route refuses proxy-route-missing; present unknown/nonstring route refuses proxy-route-unknown. Both get independent code assertions; each valid value gets a test using a proxy-only model id absent from any catalog. The GPT route's generated pi provider will be mosaic-proxy-codex, never openai-codex. Its wire API remains a build-time choice after the pinned-binary probe. P2 passes only {baseUrl,key}; no route belongs to that seam.
+
+A key persistence hazard found during source inspection: launcher.mjs:571 writes bundle.env as session.harnessEnv. Adding the key to harness.env must not retain this behavior for credentials. P3 will keep generated key env transient for spawnSession and omit those credential values from serialized harnessEnv. runner.mjs:390 already inherits the spawn environment before applying nonsecret harnessEnv. Test the on-disk session/bundle boundary, not only models.json.
+
+The old launch-settings.test.mjs already uses provider proxy fixtures without route. Update those fixtures to explicit anthropic routes before any full-file run; preserve their existing authorization assertions. This is the new approved validation shape, not permission to loosen tests. No tests have run and no production edits exist.
+
+Additional test-first placement after route ruling: packages/harness/tests/proxy-bundle.test.mjs exercises real buildBundle with explicit provider proxy entries and proxy-only model ids, three generated providers, run-local file mode, environment references, recursive no-! values, no key in bundle files/manifest, fresh model/port/key on next launch. The exact GPT API assertion must be added from the authorized pinned-binary probe before this test file's first run; it deliberately makes no unverified wire-shape claim now. No skip is introduced.
+
+Canonical queue show returned owner sage and after=331 at 22:40Z; it also warned `view unknown` for the rendered table. No repair or queue bypass attempted; wait for Sage's announced batch. Queue metadata identifies shared proxy Gitea issue #1830.
+
+## STOPPED — mos-1630, 2026-10-24T22:48Z
+
+Jason's relayed crash instruction supersedes active work: no long-job restart, commit/push safe documentation only, handoff in this worktree, no other thread messages, then stop. See HANDOFF.md for complete state, next steps, uncommitted tests/audit script, and reruns needed. No tests or probes ever ran; no production implementation exists. Latest design is explicit launch.models route metadata per sage-4293; earlier catalog/GPT-only proposals are superseded. The original 211-entry import manifest predates the fourth new test file and is historical, not run authorization. Full inline resends still hit T3 timeouts. Crash commit will exclude every unrun test and the audit script.

agents/fethry/work/queue-332/HANDOFF.md

@@ -0,0 +1,51 @@
+# STOPPED — row 332 (P3), T3 crash handoff
+
+Stopped on 2026-10-24 under Mos mos-1630, relaying Jason's instruction: do not restart long jobs; commit/push safe work, leave a handoff, then stop. No further thread messages, tests, probes, queue operations, or implementation will run in this session.
+
+## Branch and completed work
+
+- Worktree: /home/jwoltje/.t3/worktrees/mosaic-stack/fethry-row332
+- Branch: fethry/row332, based on refactor c8a9bcf94. No implementation commits, rebases, merges or production source edits.
+- Read P3 brief, rules, full pi amendment, gate template, design and named source files. Detailed notes in BUILD.md beside this handoff.
+- Root npm ci --ignore-scripts --no-audit --no-fund completed in this worktree only (128 packages). No canonical node_modules used.
+- Initial test files written before implementation; none executed. Sage has not sent CLEAR. No proxy fetch, binary probe, offline turn, mutant, or suite has run.
+- No real proxy, management key, host auth directory or live instance was accessed. No production service was started/stopped.
+- Canonical queue next returned nothing during the assignment. Queue start op fethry-332-start refused on locks, then owner sage, including a retry after two minutes. Latest completed queue show still had owner sage, state briefed, after 331; it also warned that the rendered table was unknown. Did not repair or bypass it. Sage sage-4293 says an assign/after=none batch is running. Queue metadata identifies shared Gitea issue #1830.
+
+## Latest accepted design
+
+Sage sage-4293 supersedes all earlier route proposals: explicit route metadata, never catalog membership or model-prefix inference. Selected spelling: launch.models.<selection>.route = anthropic | glm | codex, required only with provider proxy. Missing route: proxy-route-missing; unknown/nonstring route: proxy-route-unknown. Other providers keep provider/model-only entries. Proposed launch.account.credential literal proxy; existing name/credential field names retained. GPT generated provider: mosaic-proxy-codex, never openai-codex. GPT wire API is still undecided pending the authorized pinned-binary requests. P2's seam stays exactly { baseUrl, key }.
+
+Important implementation finding: launcher.mjs:571 serializes bundle.env into session.harnessEnv. Harness env will contain the session key in proxy mode, so credentials must instead reach spawnSession through transient environment variables and be omitted from serialized harnessEnv. runner.mjs:390 already inherits the spawn environment. Preserve ENV_ALLOW; filter instance provider variables in proxy mode only.
+
+## Uncommitted work, intentionally left for the next session
+
+These are unrun, incomplete tests/audit code, excluded from the documentation-only crash commit:
+
+- packages/business/tests/proxy-launch.test.mjs — explicit routes and refusal codes, proxy account credential, existing nonproxy/account behavior.
+- packages/plugins/tests/proxy-harness.test.mjs — Claude env/preflight, own-key isolation, pi preflight and OAuth-only refusal.
+- packages/seat/tests/proxy-session-env.test.mjs — instance credential filtering and unchanged nonproxy env.
+- packages/harness/tests/proxy-bundle.test.mjs — real bundle generation, all three providers, key reference/no-key/no-! invariants, file modes and launch freshness. Exact GPT API assertion deliberately pending probe evidence; add before its first run.
+- agents/fethry/work/queue-332/import-run-list.mjs — non-evaluating static import audit using vm.SourceTextModule plus explicit computed loader edges. It ran successfully after correcting its own root-depth setup error. It is not a test runner.
+
+IMPORT-RUN-LIST.txt is a historical 211-entry candidate impact list, generated before proxy-bundle.test.mjs was added. It includes case1-accept as explicitly EXCLUDED (mos-1612). Regenerate the list after resuming and report the actual authorized run list inline before any whole-file run. Do not treat the historical manifest as a current run authorization.
+
+## Reporting status
+
+T3 reporting repeatedly failed during GET with a 30-second timeout. fethry-0004 was confirmed delivered. Some later short numeric keys returned reused:true unexpectedly; do not rely on them as delivery evidence. A row-scoped detailed design resend and the inline 211-line import manifest also timed out, including the manifest's same-key retry. Sage may not have those messages. This handoff and BUILD.md are being pushed so they can be read with git show; no new thread message is sent under mos-1630.
+
+## Next session, after restart authorization
+
+1. Read this handoff/BUILD.md and recover queue state from canonical checkout. Wait for owner fethry and no after, then retry the same start op. Never bypass a refusal.
+2. Recover Sage's slot status. Still NO tests or probes until Sage sends CLEAR. No job needs restarting merely to preserve current state.
+3. Review the four uncommitted test files. Add the pinned-proxy API probe and exact GPT assertion before the first relevant run. Initial RED has not happened; production implementation must follow the authorized first RED.
+4. Rebuild the import-derived run list and send it inline or in a reviewed pushed commit before runs. case1-accept remains off without Mos approval. Existing launch-settings.test.mjs proxy fixtures need explicit route metadata with their authorization assertions preserved; no old-test red has occurred.
+5. Use P1's committed fetchPinned code under an owned fresh temporary root (8.0.42 at the inspected magica/row329 revision), never live proxy assets or another seat's scratch. After CLEAR, try pi's responses and completions requests under unshare -rn against stand-in upstream, record evidence, choose one GPT API at build time. Separately prove offline GLM and record z.ai compat survival. Real Codex auth proof remains row209 phase A step7.
+6. Implement transient P2 context, model validation/route propagation, harness config, preflight, spawn env/serialization separation and tests. Named mutants: OAuth token leak; literal key in models.json. No policy or real credentials involved.
+7. Land only after 329 and 331 land, rebasing on both, Gladstone first review, Dewey landing review and Sage's required gate. No force-push or merge authority is added by the crash instruction.
+
+All future tests use a fresh shell-created short TMPDIR, absolute nice 19, and timeout -k 10 for scripts/test-*.sh. First new-test red is reportable afterward; old-test red or a second red goes to Sage before changes/reruns. No test outcomes are claimed here.
+
+## Crash commit
+
+Only documentation and the historical plain-text import manifest are committed. The final STOPPED reply records the exact pushed commit. The uncommitted files above remain deliberately available in this worktree because they have never run and test-slot authorization has not arrived.

agents/fethry/work/queue-332/IMPORT-RUN-LIST.txt

@@ -0,0 +1,211 @@
+packages/bus/tests/access-revoke.test.mjs
+packages/bus/tests/broker.test.mjs
+packages/bus/tests/channel-proof.test.mjs
+packages/bus/tests/chief-of-staff.test.mjs
+packages/bus/tests/citation-guard.test.mjs
+packages/bus/tests/citation-runtime.test.mjs
+packages/bus/tests/creative.test.mjs
+packages/bus/tests/credential-verbs.test.mjs
+packages/bus/tests/grant-scope-runtime.test.mjs
+packages/bus/tests/host-run.test.mjs
+packages/bus/tests/land.test.mjs
+packages/bus/tests/library-credential.test.mjs
+packages/bus/tests/library-lookups.test.mjs
+packages/bus/tests/library-sync.test.mjs
+packages/bus/tests/library.test.mjs
+packages/bus/tests/lifecycle-revoke.test.mjs
+packages/bus/tests/limit-checks.test.mjs
+packages/bus/tests/messages.test.mjs
+packages/bus/tests/processing-runtime.test.mjs
+packages/bus/tests/project-runtime.test.mjs
+packages/bus/tests/reload.test.mjs
+packages/bus/tests/tasks.test.mjs
+packages/bus/tests/tester-writes.test.mjs
+packages/bus/tests/tester.test.mjs
+packages/bus/tests/usage-runtime.test.mjs
+packages/bus/tests/usage.test.mjs
+packages/bus/tests/workflow-roles.test.mjs
+packages/business/tests/access-levels.test.mjs
+packages/business/tests/access.test.mjs
+packages/business/tests/agent-identity.test.mjs
+packages/business/tests/assistant.test.mjs
+packages/business/tests/business.test.mjs
+packages/business/tests/case1-business-file.test.mjs
+packages/business/tests/chief-library-credentials.test.mjs
+packages/business/tests/chief-of-staff.test.mjs
+packages/business/tests/cli.test.mjs
+packages/business/tests/credentials.test.mjs
+packages/business/tests/csuite.test.mjs
+packages/business/tests/grant-scope.test.mjs
+packages/business/tests/hard-waits.test.mjs
+packages/business/tests/hosts.test.mjs
+packages/business/tests/instance-credential-transitions.test.mjs
+packages/business/tests/instance-settings.test.mjs
+packages/business/tests/launch-settings.test.mjs
+packages/business/tests/library-projects-protected.test.mjs
+packages/business/tests/library-seats.test.mjs
+packages/business/tests/lifecycle-settings.test.mjs
+packages/business/tests/optional-tracker.test.mjs
+packages/business/tests/plugin-settings.test.mjs
+packages/business/tests/project-repo.test.mjs
+packages/business/tests/project.test.mjs
+packages/business/tests/proxy-launch.test.mjs
+packages/business/tests/record-grants.test.mjs
+packages/business/tests/reply-limits.test.mjs
+packages/business/tests/resolve.test.mjs
+packages/business/tests/role.test.mjs
+packages/business/tests/token-limit-settings.test.mjs
+packages/business/tests/vars.test.mjs
+packages/business/tests/workflow-roles.test.mjs
+packages/cli/tests/access-boot.test.mjs
+packages/cli/tests/access.test.mjs
+packages/cli/tests/app.test.mjs
+packages/cli/tests/boot-status.test.mjs
+EXCLUDED (mos-1612) packages/cli/tests/case1-accept.test.mjs
+packages/cli/tests/case1-hostcheck.test.mjs
+packages/cli/tests/case2-install.test.mjs
+packages/cli/tests/case2-persona-import.test.mjs
+packages/cli/tests/case2-unit.test.mjs
+packages/cli/tests/channel-cli.test.mjs
+packages/cli/tests/channel-recovery.test.mjs
+packages/cli/tests/cli.test.mjs
+packages/cli/tests/compactions-launch.test.mjs
+packages/cli/tests/config.test.mjs
+packages/cli/tests/credentials.test.mjs
+packages/cli/tests/federation-acceptance.test.mjs
+packages/cli/tests/follow.test.mjs
+packages/cli/tests/git-socket.test.mjs
+packages/cli/tests/grants-scope.test.mjs
+packages/cli/tests/grants.test.mjs
+packages/cli/tests/host.test.mjs
+packages/cli/tests/hosts.test.mjs
+packages/cli/tests/idle-stop-race.test.mjs
+packages/cli/tests/instances.test.mjs
+packages/cli/tests/launch-account.test.mjs
+packages/cli/tests/launch-limit-checks.test.mjs
+packages/cli/tests/launch-limits.test.mjs
+packages/cli/tests/launch-routes.test.mjs
+packages/cli/tests/launcher.test.mjs
+packages/cli/tests/lifecycle.test.mjs
+packages/cli/tests/limits-tokens.test.mjs
+packages/cli/tests/limits.test.mjs
+packages/cli/tests/mark-read.test.mjs
+packages/cli/tests/names.test.mjs
+packages/cli/tests/notifier.test.mjs
+packages/cli/tests/optional-tracker.test.mjs
+packages/cli/tests/other-tree.test.mjs
+packages/cli/tests/processing-cli.test.mjs
+packages/cli/tests/project-name-repo.test.mjs
+packages/cli/tests/project.test.mjs
+packages/cli/tests/publish-socket.test.mjs
+packages/cli/tests/reply-limits.test.mjs
+packages/cli/tests/revoke-window.test.mjs
+packages/cli/tests/session-clear.test.mjs
+packages/cli/tests/session-cli.test.mjs
+packages/cli/tests/session-launch.test.mjs
+packages/cli/tests/stack-copy.test.mjs
+packages/cli/tests/stack-instances.test.mjs
+packages/cli/tests/tester-reads.test.mjs
+packages/cli/tests/tester-threads.test.mjs
+packages/cli/tests/tester.test.mjs
+packages/cli/tests/thread-cli.test.mjs
+packages/cli/tests/thread-launch.test.mjs
+packages/cli/tests/thread-revoke.test.mjs
+packages/cli/tests/trackers-boot.test.mjs
+packages/cli/tests/transport.test.mjs
+packages/cli/tests/usage.test.mjs
+packages/cli/tests/verbs.test.mjs
+packages/control-board/tests/creative-hidden.test.mjs
+packages/control-board/tests/discord.test.mjs
+packages/control-board/tests/serve.test.mjs
+packages/conversation/tests/flows.test.mjs
+packages/harness/tests/bundle.test.mjs
+packages/harness/tests/claude-gate.test.mjs
+packages/harness/tests/claude-session.test.mjs
+packages/harness/tests/creative.test.mjs
+packages/harness/tests/gate.test.mjs
+packages/harness/tests/git-tools.test.mjs
+packages/harness/tests/library-tools.test.mjs
+packages/harness/tests/mcp-server.test.mjs
+packages/harness/tests/pi-session.test.mjs
+packages/harness/tests/raise-domain.test.mjs
+packages/harness/tests/runner.test.mjs
+packages/harness/tests/skills.test.mjs
+packages/harness/tests/spec-tools.test.mjs
+packages/harness/tests/tools.test.mjs
+packages/plugins/tests/channel.test.mjs
+packages/plugins/tests/harness-compactions.test.mjs
+packages/plugins/tests/harness.test.mjs
+packages/plugins/tests/loader.test.mjs
+packages/plugins/tests/proxy-harness.test.mjs
+packages/plugins/tests/searxng.test.mjs
+packages/processing-control/tests/task.test.mjs
+packages/seat/tests/compactions-budget.test.mjs
+packages/seat/tests/compactions-ledger.test.mjs
+packages/seat/tests/compactions.test.mjs
+packages/seat/tests/proxy-session-env.test.mjs
+packages/seat/tests/sandbox.test.mjs
+packages/seat/tests/session-workspace.test.mjs
+packages/seat/tests/session.test.mjs
+packages/tasks/tests/fields.test.mjs
+packages/webui/tests/agents-browser.test.mjs
+packages/webui/tests/agents.test.mjs
+packages/webui/tests/assistant.test.mjs
+packages/webui/tests/board-held.test.mjs
+packages/webui/tests/browser-edge.test.mjs
+packages/webui/tests/browser.test.mjs
+packages/webui/tests/bus-browser.test.mjs
+packages/webui/tests/bus.test.mjs
+packages/webui/tests/channel-chat.test.mjs
+packages/webui/tests/chat-browser.test.mjs
+packages/webui/tests/chat-instances.test.mjs
+packages/webui/tests/chat-replies-browser.test.mjs
+packages/webui/tests/chat.test.mjs
+packages/webui/tests/conversation.test.mjs
+packages/webui/tests/decide-browser.test.mjs
+packages/webui/tests/decide-sso.test.mjs
+packages/webui/tests/discord.test.mjs
+packages/webui/tests/docs-browser.test.mjs
+packages/webui/tests/editor-browser.test.mjs
+packages/webui/tests/editor.test.mjs
+packages/webui/tests/granted-user.test.mjs
+packages/webui/tests/history-return-flow.test.mjs
+packages/webui/tests/instances-browser.test.mjs
+packages/webui/tests/instances.test.mjs
+packages/webui/tests/library-cli.test.mjs
+packages/webui/tests/library-routes.test.mjs
+packages/webui/tests/limits-browser.test.mjs
+packages/webui/tests/limits-route.test.mjs
+packages/webui/tests/messages.test.mjs
+packages/webui/tests/pinned-copy.test.mjs
+packages/webui/tests/preview.test.mjs
+packages/webui/tests/processing-browser.test.mjs
+packages/webui/tests/processing.test.mjs
+packages/webui/tests/project-file.test.mjs
+packages/webui/tests/proof-cli.test.mjs
+packages/webui/tests/proof.test.mjs
+packages/webui/tests/reads.test.mjs
+packages/webui/tests/relaunch.test.mjs
+packages/webui/tests/return-flow.test.mjs
+packages/webui/tests/room-browser.test.mjs
+packages/webui/tests/room-http.test.mjs
+packages/webui/tests/routes-browser.test.mjs
+packages/webui/tests/routes.test.mjs
+packages/webui/tests/send-browser.test.mjs
+packages/webui/tests/send.test.mjs
+packages/webui/tests/serve.test.mjs
+packages/webui/tests/settings-form.test.mjs
+packages/webui/tests/settings-write.test.mjs
+packages/webui/tests/shell.test.mjs
+packages/webui/tests/sso-browser.test.mjs
+packages/webui/tests/sso.test.mjs
+packages/webui/tests/tester-browser.test.mjs
+packages/webui/tests/tester-cli.test.mjs
+packages/webui/tests/tester-listener.test.mjs
+packages/webui/tests/thread-claims-browser.test.mjs
+packages/webui/tests/thread-claims.test.mjs
+packages/webui/tests/thread-sharing.test.mjs
+packages/webui/tests/usage-browser.test.mjs
+packages/webui/tests/usage.test.mjs
+packages/webui/tests/user-option-swap.test.mjs
+packages/webui/tests/views.test.mjs

docs/SESSIONS.md

@@ -1687,3 +1687,5 @@ are never rewritten or removed; corrections are new entries.
 2026-10-24 | Fethry14f80e3c | Row328 T9 race acceptance evidence | sage4214 on06c57a7db:400 concurrent M1 attempts yield26 expected failures, fixed400/400, whole file6/6; exact restoration/clean checks and process sweep empty. All801 receipts/nice/load preserved. Manifest1e010468 one approved+4/-3 old test, no assertion/product change. Earlier aborted and serial non-repro receipts separate. Review handoff Boyd/Dewey, Sage landing gate pending.
 
 2026-10-24 | Sage 1ef1e4f8 | Landings 257, 266, 224, 328; model-proxy rows 329-333 filed | 257 73692e1bb, 266 3e5041b43, 224 5e77cdd09, 328 8bb5b3c73 landed on GREEN gates. Rows 329-333 briefed from 7fe32d722 (mos-1600/1601); 330 blocked on Jason's subdomain answer (mos-1602). Magica holds the slot for 329's builder gate.
+2026-10-24 | fethry (65673bd9-3bfa-412b-85d5-9b364187d8b6) | row332 P3 proxy harness configuration at c8a9bcf94 | Started recovery and design; npm ci in isolated worktree; tests held for Sage CLEAR; no live proxy or credentials accessed.
+2026-10-24 | fethry (65673bd9-3bfa-412b-85d5-9b364187d8b6) | row332 crash stop (mos-1630) | Documentation-only handoff on fethry/row332; four unrun test files and import audit script left uncommitted; no tests/probes/production edits; no jobs restarted or other threads messaged.

docs/plans/2026-10-24_case2-proxy-unit-brief.md

@@ -0,0 +1,82 @@
+# Brief: the Case 2 proxy unit, so a hub installs P1's proxy unit
+
+Written 2026-10-24 by Sage for Mos's mos-1616 ruling 1, which approved this row. Mos ruled that Sage
+approves the brief if it only adds P1 item 7's unit to `scripts/case2-install.sh` and
+`scripts/case2-unit.sh`: the same unit text, the same sha256 refusal and the Wants/After lines. Anything
+beyond that goes to Mos. Read the rows doc's P1 brief (`docs/plans/2026-10-24_model-proxy-rows.md`, P1
+item 7) and row 209's brief (`docs/plans/2026-10-24_row209-hub-54-window.md`, entry check 2) first. The
+rows doc's "Rules for every row" apply here unchanged. Line numbers are at origin/refactor 58b2bbb3a, and
+P1's paths are at its round 2 candidate magica/row329 86cb5c221. Check both once P1 lands.
+
+## Brief: Case 2 proxy unit in case2-unit.sh and case2-install.sh
+
+**Why.** A Case 2 hub (.54) installs through `scripts/case2-install.sh` (as the stack user) and
+`scripts/case2-unit.sh` (as root, system units). P1 adds `mosaic-proxy.service` only to the user-unit path
+(`scripts/instance.sh`, `scripts/proxy-service.sh`, `scripts/bus-service.sh`). `case2-unit.sh` writes the
+bus and Console units and nothing else (:3-5, :56-57), and its bus unit has no `Wants=` or `After=` on a
+proxy. Without this row, row 209 phase A can't run the proxy on .54.
+
+**What ships.**
+
+1. **The proxy unit, from P1's template.** `case2-unit.sh` renders a third system unit,
+   `mosaic-proxy.service`, from P1's `packages/cli/systemd/mosaic-proxy.service.in`, which this row doesn't
+   change.
+   - It uses the same render as the bus (`render()` :435): the copy for `@REPO@`, the unit PATH, `--node`
+     for `@NODE@`, and `@CONFIG_ENV@` deleted, because `case2-unit.sh` renders the default instance only.
+   - It gets the same added lines as the bus: `User=`, `Group=` and the four hardening lines, with no
+     capabilities and no `EnvironmentFile=`. `WantedBy=multi-user.target` replaces `default.target`, as for
+     the other two units.
+   - `check_unit` gets a `proxy` kind. Its fixed lines are those of P1's template: `ExecStart=` exactly
+     `<node> <copy>/packages/model-proxy/src/run.mjs`, and `NoNewPrivileges=yes`. Every check that applies to
+     both units today applies to this one too.
+   - A new test seam `CASE2_PROXY_TEMPLATE`, like `CASE2_BUS_TEMPLATE` (:44, :54).
+2. **The sha256 refusal is P1's.** The unit starts P1's `run.mjs`, which checks the binary against PIN
+   before it spawns it. This row adds no second check and no other way to start the proxy. A test runs the
+   rendered `ExecStart=` in a temp root, with a made-up config and a binary that doesn't match PIN, and
+   checks P1's refusal code and exit status.
+3. **Only when the instance has a proxy.** Root passes a new bare flag `--proxy` when the instance's config
+   has a `proxy` section.
+   - Without it, the render is byte for byte what it is today, and no proxy unit is written.
+   - With it, the bus unit gets `Wants=mosaic-proxy.service` and `After=mosaic-proxy.service`, in the place
+     where P1's `bus-service.sh` puts them, right after `Description=`. The Console unit doesn't change.
+   - Root still never imports copy code or reads the config (:16-21). A wrong flag fails closed: with no
+     proxy section, P1's runner refuses and the unit stops. With a proxy section and no flag, the proxy
+     doesn't run and P2's launch preflight refuses. BUILD.md checks both against the landed P1 and P2 code
+     and names the refusal codes.
+4. **Re-install and start.**
+   - With `--proxy`, the three installed units must name one copy, and each must equal the render once its
+     copy id is the new one, the same rule as now (:557-571).
+   - Without `--proxy`, an installed `mosaic-proxy.service` refuses the run. The script never deletes a
+     unit file.
+   - Enable all of them, then start the proxy, then the bus, then the Console. A unit that was already
+     running is reported the way the bus and Console are now (:576-610), and the message names all three as
+     the units to restart together.
+5. **case2-install.sh.** Only its closing "Next:" line (:231) changes, to tell root to add `--proxy` when the
+   config has a `proxy` section. If the builder finds that line needs no change, BUILD.md says why and the
+   file stays as it is.
+
+**Out of scope.** P1's template, runner and PIN; the user-unit path; any named-instance render; reading the
+config from root; the proxy's config or key; `mosaic proxy init`; any live host, unit or `/etc` write
+outside a test's temp root.
+
+**Tests**, in `packages/cli/tests/case2-unit.test.mjs` (and `case2-install.test.mjs` if item 5 changes the
+script):
+- with no `--proxy`, the bus and Console renders equal today's, byte for byte;
+- with `--proxy`, the proxy unit's content, and the bus unit's `Wants=` and `After=` lines;
+- each `check_unit` refusal on the proxy kind, by its message;
+- P1's PIN refusal through the rendered `ExecStart=`;
+- a re-install whose three units name two copies refuses;
+- an installed proxy unit with no `--proxy` refuses and deletes nothing;
+- the start order through the `CASE2_SYSTEMCTL` seam's log.
+
+**Gate.**
+- The builder is a new Codex gpt-6.1-sol thread and worktree off refactor (Q246, mos-1542). The row starts
+  when P1 (row 329) lands, and the builder rebases on it before any run.
+- Boyd gives the first Codex review. Webby gives the Claude review of the root-run unit boundary and the
+  landing. Sage runs the landing gate.
+- The run list for every whole-file run comes from imports and goes in the builder's report before the run.
+  `packages/cli/tests/case1-accept.test.mjs` stays off unless Mos approves (mos-1612).
+- Every touched test file runs whole. Every package suite but queue, plus every `scripts/test-*.sh`, is
+  green on Sage's landing gate.
+- Named mutants: the bus unit loses its `After=` line under `--proxy`; the proxy unit's `ExecStart=` skips
+  `run.mjs` and starts the binary directly.

docs/plans/2026-10-24_p3-pi-routes-amendment.md

@@ -0,0 +1,76 @@
+# Brief amendment: row 332 (P3), pi's GLM and GPT routes through the proxy
+
+Written 2026-10-24 by Sage. Mos approved items 4a to 4c in mos-1616 with three conditions, which are written
+into the items below. Item 4d is settled there too. This came out of mos-1615 (DECISIONS Q253): on .54 Bean
+runs GLM through a Z.ai key and Chet runs GPT through his ChatGPT/Codex login, both through the proxy. The
+P3 brief in the rows doc (`docs/plans/2026-10-24_model-proxy-rows.md`, "Brief: P3 harness config from the
+proxy", item 4) proves only the Anthropic route. Row 96 proved only that route for pi, too
+(`agents/researcher/work/i1-proxy-test/REPORT.md`, S2-pi-A).
+
+The rows doc isn't edited, because rows 329 to 333 pin its blob. This file replaces one line of P3 item 4,
+"A non-Anthropic route names that provider's base URL in the same file.", and adds to P3's Tests and Gate.
+Everything else in P3 stands. Line numbers are at origin/refactor 58b2bbb3a. Check them before you edit.
+
+## Brief: P3 amendment, pi's GLM and GPT routes
+
+**What pi 0.85.1 does today.** These facts come from the pinned pi's docs and its built-in provider data.
+- `models.json` providers take `baseUrl`, `api`, `apiKey` and `models`. A built-in provider can be
+  overridden with a `baseUrl`.
+- `apiKey` takes a literal, a `$ENV` reference, or `!command`, which pi runs as a shell command.
+- The built-in `zai` provider is `openai-completions` at `https://api.z.ai/api/coding/paas/v4`, with z.ai
+  compat fields (`thinkingFormat: "zai"`, `zaiToolStream`).
+- The built-in `openai-codex` provider speaks `openai-codex-responses` to chatgpt.com/backend-api with pi's
+  own OAuth, so it can't be pointed at the proxy.
+
+**4a. One entry per route.** `<run>/home/.pi/agent/models.json` gets one provider entry for each route the
+agent's `launch.models` names, each at the proxy's address from P3 item 1.
+- Anthropic: as P3 item 4 says now, `anthropic-messages` with no `/v1`.
+- GLM: `openai-completions` at `http://127.0.0.1:<port>/v1`, with the model id that the proxy's `/v1/models`
+  lists for the Z.ai key.
+- GPT through the Codex login: a provider of the stack's own, never `openai-codex`, at
+  `http://127.0.0.1:<port>/v1`, with the model ids that the proxy lists for the Codex credential.
+  - The builder picks `openai-responses` or `openai-completions` once, at build time, from what the pinned
+    proxy passes for pi's requests. The harness has no fallback at run time: it writes the one shape the
+    build chose.
+  - BUILD.md records the choice and its evidence: the pinned proxy version, the requests tried on each shape
+    and what came back.
+
+**4b. The key goes by reference.**
+- Every entry's `apiKey` is `"$ANTHROPIC_API_KEY"`, the reference P3 item 4 already sets. `ENV_ALLOW`
+  (`packages/seat/src/session.mjs`:242) doesn't change.
+- In proxy mode that variable holds only the session's own proxy key, because P3 item 2 drops the instance's
+  provider variables.
+- `models.json` never holds a key value, and no value in it starts with `!`.
+
+**4c. Tests.** These add to P3's Tests list:
+- the `models.json` content for each of the three routes;
+- every `apiKey` in `models.json` is the `$ANTHROPIC_API_KEY` reference;
+- no key value appears anywhere in the file;
+- no value in the file starts with `!`;
+- an offline pi turn through the pinned proxy under `unshare -rn` for the GLM route, against a stand-in
+  upstream, the way row 96 and P1's acceptance run did. It runs from a script outside the gate's
+  `scripts/test-*.sh` set, and its output goes in BUILD.md as plain text.
+
+The Codex route can't run offline without a real auth file, and no agent touches one. Its first real turn is
+row 209 phase A step 7 (`docs/plans/2026-10-24_row209-hub-54-window.md`). BUILD.md says so.
+
+BUILD.md also records whether the z.ai compat fields survive through the proxy, or whether the proxy drops
+them, from the offline GLM turn.
+
+**4d. One proxy per user (settled, mos-1616).** Unless P2 item 7 finds that the pinned proxy can limit a
+client key to some models, Bean's key can reach Chet's ChatGPT login through the same proxy, and Chet's key
+can reach Bean's Z.ai key. Mos accepted that for .54. Q249 sets one proxy per user and their agents, so both
+agents and both accounts on .54 are Melanie's. If P1 found no per-key model limit, the bundle's model choice
+stays the guard. If P1 found one, P2 narrows each key as P2 item 7 says. This row changes neither.
+
+**Gate additions.** One more named mutant: `models.json` gets the key value instead of the
+`$ANTHROPIC_API_KEY` reference. The 4c tests must kill it. The rest of P3's Gate stands: Gladstone's first
+Codex review, Dewey's landing review, every touched test file whole, every package suite but queue plus
+every `scripts/test-*.sh` green on Sage's landing gate, and the mutant where proxy mode still passes
+`CLAUDE_CODE_OAUTH_TOKEN`.
+
+**Start and landing (mos-1616 ruling 5).** P3 may start now on a new Codex gpt-6.1-sol thread and worktree,
+building against P2's interface `{ baseUrl, key }` (P3 item 1). It lands only after P1 (row 329) and P2
+(row 331) land, and after its own gate (mos-1351). It rebases on both before that gate. The run list for
+every whole-file run comes from imports and goes in the builder's report before the run.
+`packages/cli/tests/case1-accept.test.mjs` stays off unless Mos approves (mos-1612).

docs/plans/2026-10-24_row209-hub-54-window.md

@@ -0,0 +1,109 @@
+# Brief: row 209, the .54 window with its own proxy
+
+Written 2026-10-24 by Sage for Mos's mos-1615, which carries Jason's "Q54: yes" (DECISIONS Q253). Q253:
+.54 waits for its own model proxy. Bean's Z.ai key and Chet's ChatGPT/Codex login both go in through the P4
+Console proxy page. Chet runs GPT through his Codex login for 10-27, not GLM, which replaces Q186.
+
+This brief replaces row 209's old brief (`docs/plans/2026-10-20_federation-r1-r2-r5.md`, "Brief: FED R8, the
+hub window on 10.1.1.54"). That section isn't edited. Phase D below runs it unchanged. Read the model-proxy
+design (`docs/plans/2026-10-24_stack-model-proxy.md`, sections 1, 5, 9 and 10), the rows doc
+(`docs/plans/2026-10-24_model-proxy-rows.md`) and the P4 brief (`docs/plans/2026-10-24_proxy-page-brief.md`)
+first. Line numbers are at origin/refactor 95d4991d2. Check them before you rely on them.
+
+## Brief: row 209, the .54 window: proxy, Bean's and Chet's accounts, then FED R8
+
+**What this row is.** A live window on 10.1.1.54, not a code row. Jason and Mos run it. Nothing here
+authorizes a step on any host. Each step waits for the window's go, and Console start and restart stay
+with Jason or Mos (Q173).
+
+**Secrets.** The rows doc's rules apply on .54 too. No agent reads `<configDir>/secrets/proxy-management.key`
+or anything under .54's `<dataRoot>/proxy/` (`config.yaml`, `auth/`, `logs/`), and no agent reads Hermes's
+auth files or Chet's login in any form (D6, mos-1600 ruling 2). Agents read only what a command prints:
+hashes, unit state, refusal codes and the proxy page's allowlisted fields.
+
+### Entry checks, all before phase A
+
+1. P1 (row 329), P2 (331), P3 (332) and P4 (330) have landed and passed Sage's landing gate. P3 carries the
+   amendment for pi's GLM and GPT routes that Mos rules on (sage-4285). Without it P3 proves only the
+   Anthropic route.
+2. **Gap to close first.** `.54` installs through `scripts/case2-install.sh` and `scripts/case2-unit.sh`.
+   P1 adds `mosaic-proxy.service` to `scripts/instance.sh` only (rows doc P1 item 7). `case2-unit.sh` writes
+   no model-proxy unit today, and its bus unit has no `Wants=` or `After=` on one. A code row has to add the
+   proxy unit to the Case 2 install, with the same sha256 refusal, before phase A. Sage files it once Mos
+   rules (sage-4285).
+3. The .54 stack copy is re-pinned to a commit that holds rows 329 to 332 and the item 2 row.
+4. .54's Console signs Jason in through Authentik (Q218). The proxy page's writes need a signed-in owner
+   (P4 item 8).
+5. Phase B has a recorded result, or Chet's login waits for phase C as phase B says.
+
+### Phase A: the proxy on .54
+
+Design section 9, for .54 as the `mosaic` user under `/srv/mosaic` (D1).
+
+1. **Fetch.** P1's pinned fetch runs on .54. Sage compares the printed sha256 values with PIN.
+2. **Config and key.** Jason adds the `proxy` section to .54's `config.json` in an editor (J2), runs
+   `mosaic proxy init` in his own terminal (J3) and starts the proxy unit.
+3. **Bean's key.** Jason pastes Bean's Z.ai API key into .54's proxy page (J4, P4 item 4) and sets its
+   priority. The page never shows it again.
+4. **Chet's login.** Only after phase B passes. Jason signs the proxy in to Chet's ChatGPT/Codex account
+   through the page's own OAuth flow (P4 item 3). The proxy holds a sign-in of its own. Nobody copies
+   Hermes's auth file.
+5. **Business settings.** Bean's and Chet's `launch.models` name provider `proxy` (P3 item 5): Bean on his
+   GLM model, Chet on his GPT model, with the model ids the proxy's `/v1/models` lists. The edit goes in
+   through the human path that P3's BUILD.md names.
+6. **Restart.** Jason or Mos restarts the bus and Console. The bus reconciles, issues a key for each agent
+   (P2) and runs D17's preflight for each one. Any refusal stops phase A. The fix is to remove the section
+   and restart.
+7. **One real turn per route.** The tester actor launches one pi session for Bean (GLM through the Z.ai key)
+   and one for Chet (GPT through the Codex login). Each makes one real turn through the proxy. Jason
+   watches the proxy page's usage section and confirms each request landed on the account he expects (J5).
+   The result goes into the row's record with who ran it.
+8. **Unit cleanup.** Once both turns pass, the bus unit drops the provider env file per design section 9
+   step 7. The file stays for the 7-day rollback window.
+
+Rollback at any point: remove the `proxy` section and restart.
+
+### Phase B: two clients on one ChatGPT login
+
+Hermes holds Chet's ChatGPT login until #423 step 5. Before that login goes into the .54 proxy (phase A
+step 4), a check has to show that two clients on one ChatGPT login don't revoke each other's refresh tokens
+(mos-1615 item 3). Row 229's brief named the same risk for a copied token.
+
+- Two separate sign-ins, never a copied file: Hermes keeps its own, and the proxy gets its own through the
+  page.
+- Pass: each client goes through at least one token refresh, and afterwards Hermes still answers on Chet's
+  login and the proxy page still lists the account as active. Fail: either one drops out or needs a new
+  sign-in.
+- The check is Jason's. It uses the real account, and no agent reads either client's token or auth file.
+  Agents record what Jason reports and what the page lists.
+- **Open before the window.** I don't know how to make each client refresh on demand without someone reading
+  a token, or how long ChatGPT's access tokens last. Researcher answers from the pinned 8.0.42 docs and
+  Hermes's docs: how each side refreshes, whether either can be made to refresh, and how long the check has
+  to run. The answer goes in this row's record.
+- If the check fails, or there's no safe way to run it, Chet's login goes in after #423 step 5, when Hermes
+  has let go of it. Phase A step 7's GPT turn waits for that, and Chet doesn't go live on GPT until it passes.
+
+### Phase C: Case 2 go-live, then Hermes stops
+
+Bean and Chet go live in Case 2 on the proxy (#416). Hermes stops after that (#423 step 5, mos-1615), and
+that stays Melanie's choice (`docs/plans/2026-10-20_case2-rows.md`:1231). If phase B didn't pass, Chet's login goes into the proxy here and phase A step 7's GPT turn
+runs before Chet goes live.
+
+### Phase D: FED R8
+
+The old brief, unchanged: entry checks, build notes N1 and N2, and its done condition
+(`docs/plans/2026-10-20_federation-r1-r2-r5.md`, "Brief: FED R8, the hub window on 10.1.1.54").
+
+### Done when
+
+Phase A's two real turns are recorded, each on the account Jason expected. Phase B's result is recorded
+along with who ran it. Bean and Chet are live on the proxy. FED R8's own done condition holds.
+
+### Out of scope
+
+- Any code change. The item 2 gap and the P3 amendment are code rows of their own.
+- The dragon-lin default instance and .53. Their cutovers are P7 and row 246.
+- Hermes's server and profiles, beyond Jason's phase B check.
+- The 8317 host proxy and `~/.local/opt/EasyCLIProxyAPI`.
+- Row 229 (Vikunja 428). The proxy route supersedes it, and the queue parks it with that reason. Its live
+  check is phase B.