feat+docs+release(v0.4.3): D76 — README install-path overhaul + OLP_BIND env + AI-install prompt + ADR 0011 amendment (#48 )

10 README install gaps catalogued and fixed in one D-day after v0.4.2's PI231 E2E session exposed that the v0.4.0-v0.4.2 README Quick Start was fictional (npm package isn't published; olp setup/start commands don't exist). F5 (OLP_BIND env) ships in the same patch so the documented LAN onboarding flow actually works. AI-driven install prompt added per Phase 4 charter brainstorm Top-5 inheritance candidate #2 (D64-D67 built the doctor framework; D76 closes the README half). ## G1-G7: README Quick Start now real Rewrote § "Manual install" from placeholder text to the empirically-verified sequence: - Prerequisites (Node >= 18 + provider CLI install matrix) - git clone + npm test verify - olp-keys keygen --owner FIRST (allow_anonymous=false default needs a key) - Per-provider OAuth (claude setup-token / codex login --device-auth / MISTRAL_API_KEY) - ~/.olp/config.json with the minimum that actually serves traffic - npm start - Smoke-test via curl + olp doctor - IDE pointing ## G8 / F5: OLP_BIND env shipped server.mjs: - const BIND = process.env.OLP_BIND ?? '127.0.0.1' (safe default unchanged) - server.listen(PORT, BIND, ...) replaces hard-coded '127.0.0.1' - New startup warn anonymous_key_advertised_with_lan_bind fires when OLP_BIND is non-loopback AND auth.advertise_anonymous_key: true (operator visibility into trust-context overlap) Pre-D76 the server only accepted loopback connections, so the documented olp-connect <ip> family-onboarding flow was unreachable from LAN without SSH tunneling. F5 makes ADR 0011 operational instead of aspirational. ## G10: AI-driven install prompt README § "Install with your AI (the fast path)" — verbatim prompt the operator pastes into Claude Code / Cursor / Copilot / Aider. The AI follows README + uses olp doctor --json next_action.ai_executable[] for self-repair, stopping only when human_required[] is non-empty (provider OAuth dances). Closes the Phase 4 brainstorm #2 inheritance candidate. ## Opening compressed § "Why OLP" (3 paragraphs of Anthropic 2026-06-15 billing history) removed from the top. The OCP-trigger context moved to § "Migration from OCP" at the bottom, condensed into a single paragraph. New users land on value-prop + § "What you get" + install paths without needing to digest 2026-05-14 billing history first. OCP users get a one-line pointer at the top. ## Configuration + Env Variables sections updated - § Configuration: placeholder replaced with full ~/.olp/config.json schema documentation, every field cross-referenced to its ADR - § Environment Variables: added OLP_BIND, OLP_API_KEY, OLP_OWNER_TOKEN, OLP_PROXY_URL rows that were used in the manual-install flow but previously undocumented ## ADR 0011 § Deployment configurations amendment Codifies the three deployment trust contexts: - 127.0.0.1 (loopback only) — safe with any auth posture - RFC1918 / tailnet / specific LAN IP — anonymous_key OK (the documented trusted-LAN zero-config family onboarding flow) - Public IP — incompatible with advertise_anonymous_key: true Documents the new anonymous_key_advertised_with_lan_bind startup warn event. Closes ADR 0011's pre-D76 dangling reference to a non-existent BIND_ADDRESS concept. ## Test count 714 (v0.4.2) -> 717 (v0.4.3). +3 D76 regression tests in Suite 36 (36s/36t/36u) pinning OLP_BIND wiring + safety warn + ADR amendment. ## Process learning Every D-day reviewer rubric should add "open README §-Quick-Start and verify the commands literally exist + work in the current repo" — would have caught G1-G7 at v0.4.0 close. Combined with D74 (review-against-spec) + D75 (review-without-deployment), D76 (review-without-following-README) codifies the third tier of review discipline. ## Out of D76 scope (deferred) - F6 (doctor client-side vs server-side check separation) — needs design ADR for --remote mode. Phase 5. - D75 reviewer P2-1 (ADR 0004 per-hop schema amendment) + P2-2 (defensive typeof hopModel === 'string') — both genuine follow-ups, neither blocking. - scripts/migrate-from-ocp.mjs — Phase 7. Co-authored-by: dtzp555 <dtzp555@gmail.com> Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
fix+release(v0.4.2): D75 — codex CLI v0.133.0 schema + per-hop model override (#47 )
2026-07-22 13:35:10 +00:00 · 2026-05-26 13:32:02 +10:00 · 2026-05-26 12:50:41 +10:00 · 2026-05-26 10:43:12 +10:00
11 changed files with 1257 additions and 84 deletions
@@ -6,6 +6,72 @@ All notable changes to OLP land here. Per `CLAUDE.md` release_kit overlay, this
 (empty — Phase 5 entries land here once Phase 5 opens)
 ## v0.4.3 — 2026-05-26
 ### D76 — README install-path overhaul + `OLP_BIND` env + AI-driven install prompt + ADR 0011 amendment
 Patch release closing the install-experience gap. v0.4.0–v0.4.2 README's Quick Start was placeholder text with fictional commands (`npm install -g @dtzp555-max/olp` — package isn't published; `olp setup` / `olp start` — don't exist). 10 real gaps catalogued + fixed in one D-day; `OLP_BIND` env wired so the documented LAN onboarding flow actually works; AI-driven install prompt added per the Phase 4 charter brainstorm's #2 OCP inheritance candidate (was deferred at D64-D67 to the doctor framework only; D76 closes the README half).
 - **G1-G7 (README "Quick Start" was fictional)** — rewrote § "Manual install" with the real sequence: prerequisites (Node ≥ 18 + provider CLI install matrix) → `git clone` → `npm test` verify → `olp-keys keygen --owner` first → provider OAuth (claude/codex/mistral per-CLI flows) → write `~/.olp/config.json` with the minimum that actually serves traffic → `npm start` → smoke-test → IDE pointing. Each step empirically verified against the PI231 + Mac mini E2E session (2026-05-26).
 - **G8 (LAN unreachable — F5)** — added `OLP_BIND` env (default `127.0.0.1`). Operators set `OLP_BIND=0.0.0.0` (or a specific LAN IP) to accept LAN connections so `olp-connect <ip>` can actually reach the server. Pre-D76 the server was hard-coded to `server.listen(PORT, '127.0.0.1', ...)`, making the documented LAN-onboarding flow only usable through an SSH tunnel. ADR 0011's original wording referenced a `BIND_ADDRESS` concept that didn't exist; D76 makes it operational.
 - **G10 (no AI-install pattern)** — README § "Install with your AI (the fast path)" added. Verbatim prompt that the operator pastes into Claude Code / Cursor / Copilot / Aider; the AI follows the README + uses `olp doctor --json` machine-readable `next_action.ai_executable[]` (D64-D67) for self-repair, stopping only when `human_required[]` is non-empty (the provider OAuth dances). This closes the Phase 4 brainstorm Top-5 inheritance candidate #2 — the OCP "paste this prompt" pattern that D64-D67 only half-built.
 - **Opening compressed** — § "Why OLP" (3 paragraphs of OCP billing history) removed from the top. The OCP-trigger context moved to § "Migration from OCP" at the bottom, condensed into a single paragraph. New users land on value-prop + § "What you get" + § "Install with your AI" / § "Manual install" without needing to digest 2026-05-14 / 2026-06-15 Anthropic billing history first. OCP users get a one-line pointer at the top.
 - **§ "Configuration" full schema documentation** — replaced the placeholder with the actual `~/.olp/config.json` schema including every field that v0.4.x reads. Cross-references ADR 0004/0007/0010/0011.
 - **§ "Environment Variables" extended** — added `OLP_BIND`, `OLP_API_KEY`, `OLP_OWNER_TOKEN`, `OLP_PROXY_URL` rows that were used throughout the manual-install flow but undocumented.
 **ADR 0011 § "Deployment configurations" amendment.** Codifies the three deployment trust contexts (`127.0.0.1` loopback / RFC1918 + tailnet LAN / `0.0.0.0` public — with `advertise_anonymous_key: true` only safe in the first two). Documents the new `anonymous_key_advertised_with_lan_bind` startup warn event. Closes ADR 0011's pre-D76 dangling reference to a non-existent `BIND_ADDRESS`.
 **Test count:** 714 (v0.4.2) → 717 (v0.4.3). +3 D76 regression tests in Suite 36 (36s/36t/36u) pinning `OLP_BIND` wiring + safety warn + ADR amendment.
 **Out of D76 scope (deferred):**
 - F6 (doctor client-side vs server-side check separation) — needs design ADR for a `--remote` mode. Phase 5.
 - D75 reviewer P2-1 (ADR 0004 amendment for per-hop schema) + P2-2 (defensive `typeof hopModel === 'string'`) — both genuine follow-ups, neither blocking.
 - `scripts/migrate-from-ocp.mjs` — Phase 7.
 **Authority:** PI231 + Mac mini E2E session (2026-05-26, post-v0.4.2 verification revealed the 10 README gaps); ADR 0011 amendment self-cites; Phase 4 charter (ADR 0010) Top-5 inheritance candidate #2 (AI-driven self-repair). Process learning: every D-day reviewer rubric should add "open README in §-Quick-Start and verify the commands literally exist + work in the current repo" — would have caught G1-G7 at v0.4.0.
 ## v0.4.2 — 2026-05-26
 ### Post-v0.4.1 hotfix batch (D75) — real-machine E2E findings
 Patch release fixing 5 bugs caught by **real-machine E2E testing on PI231 + Mac mini (2026-05-26 session)** — bugs that prior D-day reviewers AND the post-v0.4.0 maintainer review both missed because they reviewed against spec text and against the local OLP install's `~/.codex/auth.json` shape (cached from an older codex CLI version), not against real provider CLIs running on a remote operator host that did `npm install -g @openai/codex` for the first time on 2026-05-26 and got codex CLI v0.133.0.
 **Root cause of the missed-bug class.** D6 (codex plugin authoring) explicitly documented three unpinned assumptions (A3 = access-token field name, A4 = NDJSON event schema, A2-adjacent = trusted-directory sandbox). D6 noted "D7 E2E will pin." D7 then shipped without performing real-codex-CLI E2E (the E2E gating mark was carried but the actual run was deferred). Every subsequent D-day reviewer trusted the D6/D7 codex plugin code unchanged because the static review couldn't see that the v0.133.0 CLI had moved the auth-token field, the event schema, AND added a new trusted-directory sandbox flag. The D74 maintainer review focused on `/health` / `/cache/stats` / `/v0/management/dashboard-data` payload shapes — none of which exercise the codex plugin's spawn path. F7 (per-hop model override) is a different class of miss — every reviewer read `executeHopFn(provider, model, ir)` and saw `model` consumed for cache key + audit ctx, but none traced through to confirm `model` is ALSO substituted into the IR passed to `provider.spawn()`. The function signature implied per-hop semantics that the body never fully delivered.
 - **[F1] codex auth.json schema pin — codex CLI v0.133.0 nests the access token under `tokens.access_token`** (verified empirically on PI231 / Mac mini, 2026-05-26). Pre-D75 `readAuthArtifact()` read only top-level `creds.access_token` / `creds.token` / `creds.accessToken` — all undefined under v0.133.0 → returned `null` → OLP reported "auth artifact missing" via `/health` and `olp doctor` AND refused to spawn codex even when the user had fully completed `codex login`. Fix: prepend `creds?.tokens?.access_token` to the precedence chain at BOTH call sites (`OPENAI_CODEX_AUTH_PATH` override branch + default `$CODEX_HOME/auth.json` branch). Legacy top-level fields preserved as fallback for backward compat with older codex CLI versions.
 - **[F2] codex spawn args — codex CLI v0.133.0 trusted-directory sandbox requires `--skip-git-repo-check`.** v0.133.0 refuses with `"Not inside a trusted directory and --skip-git-repo-check was not specified."` when spawned outside a git repo, exits non-zero with zero NDJSON output → OLP surfaces `SPAWN_FAILED` with no usable chunks → the fallback engine advances to next hop unnecessarily even when codex is configured and authenticated. OLP's typical deploy CWD (`~/olp/`) is NOT a git repo on operator hosts. Fix: add `'--skip-git-repo-check'` to the args array before `--model`. OLP is the trusted caller (operator's own server invoking the operator's own subscription via documented `codex exec` automation); the sandbox safeguards interactive shells, not pre-authorized automation.
 - **[F3] codex NDJSON event shape pin — codex CLI v0.133.0 emits `item.completed` + `turn.completed` + `turn.failed`**, not the D6-assumed `content`/`delta`/`text` + `type:'stop'`/`done:true` shapes. Real v0.133.0 stream (verified empirically): `{"type":"thread.started",...}` → `{"type":"turn.started"}` → `{"type":"item.completed","item":{"id":"item_0","type":"agent_message","text":"<response>"}}` → `{"type":"turn.completed","usage":{...}}`. Pre-D75, every chunk was silently dropped by `codexChunkToIR()` → response body had `content: null`. Fix: prepend three new recognizers (`item.completed` with `item.type === 'agent_message'` → IR delta; `turn.completed` → IR stop; `turn.failed` → IR error). Legacy D6 defensive recognizers preserved below as forward/backward compat fallbacks.
 - **[F4] `olp status` reads `body.stats.cache.size` (not OCP-era `body.cache.entries`).** Same class as D74 P2-3 (which fixed `cmdUsage` + `cmdCache`); D74 missed the parallel bug in `cmdStatus`. Server payload nests cache stats as `body.stats.cache.{hits, misses, size, inflightCount}` per `server.mjs handleManagementStatus`, and `CacheStore.stats()` has no `entries` field per `lib/cache/store.mjs`. Pre-D75 output showed `entries=?`. Fix: read `c.size` for entries display; also surface `inflightCount` when present.
 - **[F7] per-hop chain `model` field now overrides IR model in `provider.spawn()`.** Pre-D75 `executeHopFn(hopProvider, hopModel, irReq)` used `hopModel` for cache key + audit ctx but passed the ORIGINAL `irReq` (with `irReq.model` = user's original request) to `hopProviderPlugin.spawn(irReq, authContext)`. A chain config `[{provider:anthropic, model:claude-X}, {provider:openai, model:gpt-5.5}]` would always spawn BOTH plugins with `--model claude-X` — openai rejected the unknown model and the chain died. This broke the core OLP value prop (cross-provider fallback with provider-appropriate model substitution per hop). Fix: build a per-hop IR variant with `{...irReq, model: hopModel}` and pass that to spawn. Conditional skips clone when `hopModel === irReq.model` (common case: single-provider chains, or single-hop chains where the chain config repeats the request model). Applied to BOTH the buffered path (`executeHopFn`) AND the streaming path (`sourceFactory` for `getOrComputeStreaming`). **Authority:** ADR 0004 § Chain advancement step 1 (per-hop config supplies provider AND model — the contract was always specified, but the code didn't complete it).
 **Phase 5 process learning recorded.** Every provider plugin's D-day must include a real-CLI E2E ON A REMOTE OPERATOR HOST before merging — not on the maintainer workstation (which may have an older CLI cached from a prior install, hiding new field renames / new sandbox flags / new event shapes). The D6/D7 codex E2E was deferred and that deferral compounded across 3 layers (D6 = unpinned, D7 = pinning deferred, D8+ = trusted D6/D7 unchanged). F7 reinforces a separate lesson: when a function signature takes `(provider, model, ir)`, reviewers must check that `model` is consumed everywhere downstream, not just at the call site they happened to look at.
 **Out of D75 scope (deferred to Phase 5 explicit ADR amendments):**
 - F5 (server bind 127.0.0.1 / `OLP_BIND` env) — needs `lib/keys.mjs` anonymous-key trust boundary review before binding to non-loopback by default
 - F6 (`olp doctor` client-vs-server-side limit detection) — needs design ADR amendment for trigger taxonomy
 - **Test count delta:** 704 (v0.4.1) → 714 (v0.4.2). +10 D75 regression tests in Suite 36 (36i through 36r).
 - **Files touched:** `lib/providers/codex.mjs` (F1+F2+F3), `bin/olp.mjs` (F4 cmdStatus), `server.mjs` (F7 buffered + streaming spawn sites), `test-features.mjs` (Suite 36 extension), `package.json` (version), `CHANGELOG.md` (this entry).
 - **Authority:** ADR 0002 (provider contract — codex plugin), ADR 0004 (fallback engine — per-hop model contract), `lib/providers/codex.mjs` D6 assumption A2/A3/A4 docstrings (which all said "D7 will pin" and D7 never did); codex CLI v0.133.0 on-disk schema + `codex exec --help` output verified empirically on PI231 (2026-05-26 E2E session); Iron Rule 第二律 evidence-over-should-work; CLAUDE.md `release_kit.phase_rolling_mode` cross-Phase discipline.
 ## v0.4.1 — 2026-05-26
 ### Post-Phase-4 hotfix batch (D74) — maintainer-review findings
 Patch release fixing 5 issues caught by maintainer post-v0.4.0 independent review. Every finding was a real runtime bug that the per-D-day fresh-context opus reviewers all missed because they reviewed against spec text, not against the runtime contract (default `auth.allow_anonymous: false`, real `/health` payload shape, real `/cache/stats` payload shape, real `/v0/management/dashboard-data` payload shape). **Phase 4 lesson: future implementation D-days MUST include at least one test that boots the server with the default production config and exercises the new feature end-to-end** — not just stub-mocked codepaths.
 - **[P1-1] `olp doctor` no longer false-negatives on auth-required `/health`.** `lib/doctor.mjs` now accepts an `authHeaders` option (threaded from `bin/olp.mjs` `cmdDoctor` via the existing `authHeaders()` chain) and passes it to the `server.running` + `server.version` probes. The `server.running` check now distinguishes 401/403 ("server up but bearer token missing/invalid — set `OLP_API_KEY`") from "server unreachable" — so the `kind` discriminator routes to a clean fix-auth path instead of `fix_server` when the operator just forgot to export the env var.
 - **[P1-2] `bin/olp-connect` validates token shape + shell-quotes rc writes.** New `validate_olp_token <key> <source>` helper enforces the `^olp_[A-Za-z0-9_-]{43}$` regex (per ADR 0007 § 3 token format) at all 3 input sites: `--key` arg, `/health.anonymousKey` server-advertised consumption, and the interactive prompt fallback. New `shell_quote <value>` helper wraps rc-file writes (`export OPENAI_BASE_URL=$(shell_quote ...)`) so even a hypothetical bypass of the validator can't inject shell metacharacters into a sourced rc. systemd `environment.d/olp.conf` write additionally rejects embedded newlines. Hostile or malformed keys can no longer persist as shell startup injection.
 - **[P2-3] `olp usage` + `olp cache` human formatter rewritten against the real payload shape.** `cmdUsage` previously read `body.usage_24h.requests` / `body.providers` / `body.top_fallback_chains` — all undefined under the actual server payload shape — so users saw "requests: ?" + missing per-provider quota + missing top-chains. Now reads `body.window_24h.request_count` / `body.cache_hit_24h.hit_rate` / `body.quota` / `body.top_fallback_chains_24h` per `server.mjs:2027` + `lib/audit-query.mjs`. `cmdCache` previously read `body.entries` / `body.bytes` / `body.maxBytes` (OCP-era field names). Now reads `body.size` / `body.inflightCount` per `CacheStore.stats()` and computes hit rate from `hits + misses`.
 - **[P2-4] `olp-plugin/` `fmtHealth` iterates `providers.status` correctly.** Previously walked `Object.entries(body.providers)` which surfaced `enabled` / `available` / `status` as pseudo-providers (chat output showed `🟢 status` instead of `🟢 anthropic`). Now extracts the real provider map from `body.providers.status` and renders enabled/available counts in a header line + per-provider names with `activeSpawns` when present. Falls back to flat `body.providers.*` for the older OCP shape (backwards compat).
 - **[P3-5] Stale v0.3.0-era doc strings updated.** README header status line + Implementation Status § now reflect v0.4.0 shipped + Phase 5 open. `server.mjs` startup banner no longer hardcodes "Phase 1 in progress" (now just lists version + provider count — derives accurate state from `VERSION` without future maintenance touch-ups).
 **Phase 4 process learning recorded.** Per Iron Rule 第二律 (evidence over "should work"), every D-day review pass must include at least one runtime smoke against the default production config. The D-day reviewer rubric is updated implicitly — D74 Suite 36 tests pin the wire-contract shape so a future D-day refactoring server payloads can't silently re-break the CLI / plugin / docs.
 - **Test count delta:** 696 (v0.4.0) → 704 (v0.4.1). +8 D74 regression tests in Suite 36.
 - **Files touched:** `lib/doctor.mjs` (P1-1), `bin/olp.mjs` (P1-1 + P2-3), `bin/olp-connect` (P1-2), `olp-plugin/index.js` (P2-4), `server.mjs` (P3-5 banner), `README.md` (P3-5), `test-features.mjs` (Suite 36 regression), `package.json` (version), `CHANGELOG.md` (this entry).
 - **Authority:** maintainer independent review of `main` / `v0.4.0` / commit `ee4d945` (2026-05-26 session); Iron Rule 第二律 evidence-over-should-work; CLAUDE.md `release_kit.phase_rolling_mode` cross-Phase discipline ("hotfix to a shipped Phase N deliverable → bump patch, tag, release before next push").
 ## v0.4.0 — 2026-05-26
 ### Phase 4 — Operator + Client UX (D60 → D73)
@@ -1,55 +1,204 @@
 # OLP — Open LLM Proxy
-A personal- and family-scale multi-provider LLM proxy. One HTTP endpoint, many subscriptions behind it, automatic routing, automatic fallback, content-addressed caching — so your IDEs and family clients keep working as long as *any* of your subscriptions has quota left.
+A personal- and family-scale multi-provider LLM proxy. One HTTP endpoint, many subscriptions behind it, automatic routing + fallback + content-addressed caching. Your IDEs and family clients keep working as long as **any** of your subscriptions has quota left.
-> **Status:** v0.3.0 shipped (2026-05-25) — Phase 1 multi-provider proxy core (v0.1.0 + v0.1.1) + Phase 2 multi-key auth + audit + owner gating + keygen CLI (v0.2.0) + Phase 3 Dashboard + audit query layer + daily audit rotation (v0.3.0). Phase 4 (per-key per-provider auth + audit retention + SQLite hybrid + provider-cost weights) is the next planned milestone. Sections marked _placeholder_ land alongside the relevant phase of work (see [phase plan](#phase-plan)).
+> **Status:** v0.4.3 shipped, 714+ tests. Phase 4 (Operator + Client UX) closed; Phase 5 scope is open. Coming from [OCP](https://github.com/dtzp555-max/ocp)? See [§ Migration from OCP](#migration-from-ocp).
 ---
-## Why OLP
+## What you get
-On 2026-05-14, Anthropic announced (effective 2026-06-15) that `claude -p`, the Agent SDK, and third-party agent traffic move out of the Pro/Max subscription pool into a separate fixed monthly Agent SDK Credit pool. [OCP](https://github.com/dtzp555-max/ocp), OLP's predecessor, was a proxy around a single CLI — its core assumption was *"subscription = unlimited within rate limits"*. That assumption breaks for Anthropic on the effective date.
+- **OpenAI-compatible** `/v1/chat/completions` endpoint — any IDE that speaks OpenAI (Cline / Continue.dev / Cursor / Aider) plugs in
-
+- **Multi-provider chain** — primary fails / quota dies → automatically falls back to the next provider (anthropic ↔ codex ↔ mistral by default; risk-tier framework guards which ones get enabled)
-The structural response is to stop relying on one provider's subscription terms remaining favourable. OLP spreads risk across multiple providers whose subscriptions still include CLI/programmatic use, routes intelligently between them, and caches aggressively so every request that does spawn a CLI counts.
+- **Content-addressed cache** — repeat requests don't re-spawn the CLI; streaming requests dedup via singleflight tee
-
+- **Multi-key auth** — owner key with full visibility, family-member keys with per-key audit log + per-provider scoping
-OLP is **not**: a commercial multi-tenant SaaS; an enterprise gateway competing with LiteLLM / OpenCode / CLIProxyAPI on breadth; a model-capability router ("route to the smartest model" — you pick the model); a conversation-state store (your client handles that).
+- **Telegram / Discord** `/olp` slash commands (read-only — for "is OLP up?" checks from anywhere)
-
+- **AI-driven self-repair** — `olp doctor --json` emits machine-readable `next_action.ai_executable[]` so a Claude Code / Cursor / Copilot session can fix install issues for you (see [§ Install with your AI](#install-with-your-ai-the-fast-path))
-See [`ALIGNMENT.md`](./ALIGNMENT.md) for OLP's constitution and [`docs/adr/`](./docs/adr/) for the founding ADRs.
+- **Observability** — owner-only `/dashboard` (quota / 24h stats / 30d spend trend / top fallback chains)
 ---
-## Quick Start
+## Install with your AI (the fast path)
-_placeholder — lands with Phase 1._
+If the manual steps feel like a lot, paste this verbatim into your AI coding assistant (Claude Code / Cursor / Copilot / Aider). It walks you through everything:
-Anticipated shape:
+```
 I want to install OLP (Open LLM Proxy) on this machine. The repo is at
 https://github.com/dtzp555-max/olp and ships these tools that you can use:
-```bash
+1. `git clone` the repo to ~/olp
-# install
+2. README.md § "Manual install" has the sequenced steps. Follow them in order.
-npm install -g @dtzp555-max/olp
+3. After EACH step, run `node ~/olp/bin/olp.mjs doctor --json` (NOT `npx olp`
   — the package isn't on npm). Parse the JSON. The `kind` field tells you
   the state: noop / fresh_install / fix_server / fix_oauth / fix_provider /
   fix_config.
 4. If `kind != noop`, run the commands listed in `next_action.ai_executable[]`
   verbatim. Then re-run doctor to verify.
 5. STOP and ask me only when `next_action.human_required[]` is non-empty.
   That's where I need to do a browser OAuth flow you can't do for me.
-# run setup (writes ~/.olp/config.json, asks which providers to enable)
+The provider CLIs OLP spawns (claude / codex / vibe) need their own one-time
-olp setup
+OAuth — those are the only steps I personally have to do (Claude.ai login,
 ChatGPT login, Mistral API key). Everything else (clone, npm install of the
 provider CLIs, owner-key generation, config.json bootstrap, server start) is
 in your `ai_executable[]` and you should run it without asking.
-# start the proxy (default port 4567 since v0.4.0 — moved off OCP's 3456 so
+Begin.
 # OLP and OCP can co-host on the same machine. Set OLP_PORT=3456 if you have
 # no OCP on the machine and want the old default.)
 olp start
 # point your IDE at http://localhost:4567/v1/chat/completions with the OLP API key from `olp keys list`.
 ```
-**Family-on-LAN onboarding (D68-D70).** For other devices on the same network, run on the client device:
+Then sit back and respond when it asks for OAuth confirmation. This pattern works because `olp doctor` is purpose-built for AI consumption — every failure mode has a shell-executable repair command AND a human-required step listed separately.
 ---
 ## Manual install (5-10 min)
 ### 0. Prerequisites
 - **Node.js ≥ 18.** Verify: `node --version`
 - **The provider CLIs you want OLP to spawn.** Install whichever you'll actually use:
  | Provider | Install | Subscription |
  |---|---|---|
  | `anthropic` (`claude -p`) | `npm install -g @anthropic-ai/claude-code` | Claude Pro/Max (OAuth) |
  | `openai` (`codex exec`) | `npm install -g @openai/codex` | ChatGPT Plus/Pro (OAuth) or OpenAI API key |
  | `mistral` (`vibe --prompt`) | follow the `vibe` install docs | Le Chat Pro API key |
  You only need to install the ones you'll route to. Single-provider OLP works fine.
 ### 1. Clone and verify the test suite
 ```bash
-# Detects Cline / Continue.dev / Cursor / Aider / OpenClaw installed locally
+git clone https://github.com/dtzp555-max/olp.git ~/olp
-# and writes per-tool config pointing at the OLP host. Requires `python3`.
+cd ~/olp
-olp-connect <olp-host-ip>
+npm test    # 714+ tests, ~5s, no external deps
 ```
-If the OLP host has `auth.advertise_anonymous_key: true` AND a key was created with `olp-keys keygen --anonymous --advertise`, `olp-connect` picks up the token from `/health.anonymousKey` — zero out-of-band token paste required. See [ADR 0011](./docs/adr/0011-anonymous-key-deployment-context.md) for the trusted-LAN-only invariant.
+(If `npm test` fails here, stop — that means your Node version or the repo state is broken. Don't proceed to step 2.)
-Per-IDE setup details: [`docs/integrations/`](./docs/integrations/README.md).
+### 2. Bootstrap the owner key
 The owner key is what you (and `olp-connect`) use to authenticate to OLP. Default config has `auth.allow_anonymous: false`, so you need a key BEFORE the server starts accepting requests.
 ```bash
 node ~/olp/bin/olp-keys.mjs keygen --owner --name=$(whoami)-laptop
 # Prints the plaintext token ONCE. Copy it now — you can't recover it later.
 # Example: olp_l23-PN46tDljmPATV94-KfOgOBO0Ed8theVjTdAgQoY
 ```
 Export it so the CLI subcommands can use it:
 ```bash
 export OLP_API_KEY=olp_l23-PN46...   # paste your real token
 ```
 (Add to `~/.bashrc` / `~/.zshrc` to persist.)
 ### 3. Authenticate the providers (one-time OAuth)
 Run each provider's own login flow. OLP's anthropic / openai / mistral plugins spawn these CLIs and reuse their cached credentials — OLP itself never touches the OAuth dance.
 ```bash
 # Anthropic (Claude Pro/Max subscription)
 claude setup-token
 # Opens a TUI / prints a URL. Authorize in browser. Paste the returned code.
 # Result: ~/.claude/.credentials.json
 # OpenAI (ChatGPT subscription)
 codex login --device-auth
 # Prints a https://auth.openai.com/codex/device URL + 10-char code.
 # Open URL in browser, enter code, authorize.
 # Result: ~/.codex/auth.json
 # Mistral (Le Chat API key)
 export MISTRAL_API_KEY=sk-...   # add to ~/.bashrc to persist
 ```
 ### 4. Write a minimum config
 `~/.olp/config.json`:
 ```json
 {
  "auth": {
    "allow_anonymous": false,
    "owner_only_endpoints": [
      "/health",
      "/v0/management/dashboard-data",
      "/v0/management/quota",
      "/v0/management/status",
      "/cache/stats",
      "/dashboard"
    ],
    "fallback_detail_header_policy": "owner_only"
  },
  "providers": {
    "enabled": { "anthropic": true, "openai": true }
  },
  "routing": {
    "chains": {
      "claude-sonnet-4-6": [
        { "provider": "anthropic", "model": "claude-sonnet-4-6" },
        { "provider": "openai", "model": "gpt-5.5" }
      ],
      "gpt-5.5": [{ "provider": "openai", "model": "gpt-5.5" }]
    }
  },
  "streaming": { "heartbeat_interval_ms": 15000 }
 }
 ```
 (Enable only the providers you actually authenticated in step 3. Chains map `<your-IDE's-requested-model>` → ordered list of `{provider, model}` hops; the chain's per-hop `model` is what gets passed to that provider's CLI.)
 ### 5. Start the server
 ```bash
 cd ~/olp
 npm start
 # OLP v0.4.3 listening on :4567 (2 providers enabled)
 ```
 ### 6. Smoke-test
 ```bash
 curl -H "Authorization: Bearer $OLP_API_KEY" http://localhost:4567/health | jq
 # Expect: {ok: true, providers: {enabled: 2, status: {anthropic: {ok: true...}, openai: {ok: true...}}}}
 node ~/olp/bin/olp.mjs doctor
 # Expect: "9 of 9 checks passed", kind=noop
 ```
 ### 7. Point your IDE at OLP
 ```
 OPENAI_BASE_URL=http://localhost:4567/v1
 OPENAI_API_KEY=$OLP_API_KEY
 ```
 Per-IDE configuration details: [`docs/integrations/`](./docs/integrations/README.md).
 ---
 ## Family / LAN setup
 To let other devices on your home network use the same OLP server, you need TWO things:
 1. **Bind to the LAN interface** (not just loopback). On the SERVER:
   ```bash
   OLP_BIND=0.0.0.0 npm start   # or your specific LAN IP, e.g. 192.168.1.10
   ```
   Default is `127.0.0.1` (loopback only). See [ADR 0011 § Deployment configurations](./docs/adr/0011-anonymous-key-deployment-context.md#deployment-configurations-d76-amendment-2026-05-26) for the trust-context table — **never set `OLP_BIND=0.0.0.0` on a public-internet-facing host** (use a tunnel like Tailscale instead).
 2. **Onboard each family member's device** from THEIR machine:
   ```bash
   bash <(curl -fsSL https://raw.githubusercontent.com/dtzp555-max/olp/main/bin/olp-connect) <olp-host-ip>
   ```
   Detects Cline / Continue.dev / Cursor / Aider / OpenClaw locally and writes per-tool config pointing at your OLP host. Requires `python3` on the client. Prompts for the OLP API key — OR, if the server has `auth.advertise_anonymous_key: true` AND a key was created with `olp-keys keygen --anonymous --advertise`, picks the token up from `/health.anonymousKey` (zero out-of-band paste). See [ADR 0011](./docs/adr/0011-anonymous-key-deployment-context.md) for the trusted-LAN-only invariant.
 Per-IDE setup details: [`docs/integrations/`](./docs/integrations/README.md). Telegram / Discord `/olp` slash command setup: [§ Telegram / Discord Usage](#telegram--discord-usage).
 ---
@@ -80,12 +229,19 @@ OLP distinguishes **Candidate Providers** (declared as intended, not yet pinned)
 ## Configuration
-_placeholder — full configuration reference lands with Phase 4 (fallback engine)._
+OLP reads `~/.olp/config.json` at startup. § "[Manual install § Step 4](#4-write-a-minimum-config)" above has a working minimum example. The full schema:
 OLP reads its config from `~/.olp/config.json`. The minimum useful shape:
 ```json
 {
  "auth": {
    "allow_anonymous": false,
    "owner_only_endpoints": ["/health", "/dashboard", "/v0/management/..."],
    "advertise_anonymous_key": false,
    "fallback_detail_header_policy": "owner_only"
  },
  "providers": {
    "enabled": { "<provider-key>": true }
  },
  "routing": {
    "chains": {
      "<requested-model>": [
@@ -96,13 +252,25 @@ OLP reads its config from `~/.olp/config.json`. The minimum useful shape:
    "soft_triggers": {
      "<provider-key>": { "<trigger>": <threshold> }
    }
  },
  "streaming": {
    "heartbeat_interval_ms": 0
  }
 }
 ```
-> **Note:** `routing.soft_triggers` thresholds are parsed and stored but have **no runtime effect at v0.1** — the quota polling path (`quotaStatus()` per hop) is deferred to v1.x per [ADR 0004 Amendment 2](./docs/adr/0004-fallback-engine.md#amendment-2--2026-05-24-soft-triggers-deferred-to-v1x-d22). The evaluation logic exists and is tested; only the production data ingestion path is deferred.
+Field guide:
-Trigger types, fallback safety, idempotency rules, and the full example config land here when Phase 4 ships. See [ADR 0004 (Fallback Engine Semantics & Safety)](./docs/adr/0004-fallback-engine.md) for the design.
+- **`auth.allow_anonymous`** — default `false`. When false, every request needs a Bearer token; when true, anonymous-tier requests succeed (ADR 0007 § 7). Production posture is `false`.
 - **`auth.owner_only_endpoints`** — list of endpoints that REQUIRE owner-tier auth (non-owner returns 401). The defaults above are minimum sane for production.
 - **`auth.advertise_anonymous_key`** — default `false`. When true (+ `allow_anonymous: true` + a key created with `olp-keys keygen --anonymous --advertise`), `/health.anonymousKey` exposes the plaintext token so `olp-connect <ip>` is zero-config. **Trusted-LAN only** — see [ADR 0011](./docs/adr/0011-anonymous-key-deployment-context.md).
 - **`auth.fallback_detail_header_policy`** — controls `X-OLP-Fallback-Detail` response header emission. `owner_only` (default) only shows tuples to owner identity; debug surface to LAN family without leaking to anonymous.
 - **`providers.enabled`** — flip a provider plugin on. Only enable providers whose CLI you've authenticated; OLP doesn't do its own OAuth.
 - **`routing.chains`** — keyed by the model name your IDE / client requests. Each entry is an ordered list of fallback hops; each hop's `model` is what gets passed to that provider's CLI. F7 fix (D75) — the hop-level `model` field finally overrides the IR's request model during cross-provider fallback.
 - **`routing.soft_triggers`** — parsed and stored but **inert at v0.4.x** — the `quotaStatus()` polling data path is deferred to v1.x per [ADR 0004 Amendment 2](./docs/adr/0004-fallback-engine.md#amendment-2--2026-05-24-soft-triggers-deferred-to-v1x-d22). Startup emits a warn if non-empty so the inert state is visible.
 - **`streaming.heartbeat_interval_ms`** — default `0` (disabled). Set > 0 (e.g. `15000`) to emit SSE keepalive frames during silent windows. Required behind reverse proxies (nginx / Cloudflare Tunnel / Tailscale Funnel) with 60s idle aborts.
 See [ADR 0004 (Fallback Engine)](./docs/adr/0004-fallback-engine.md), [ADR 0007 (Multi-key auth)](./docs/adr/0007-multi-key-auth.md), [ADR 0010 (Phase 4 charter)](./docs/adr/0010-phase-4-charter-operator-and-client-ux.md), [ADR 0011 (Anonymous-key deployment)](./docs/adr/0011-anonymous-key-deployment-context.md).
 ---
@@ -127,6 +295,10 @@ _placeholder — full table lands per-phase as variables are introduced._
 | Variable | Default | Description |
 |---|---|---|
 | `OLP_PORT` | `4567` | HTTP listener port. Moved off `3456` at D60 / v0.4.0 to co-host with OCP — set `OLP_PORT=3456` to restore the pre-D60 default. |
 | `OLP_BIND` | `127.0.0.1` | HTTP listener bind address. **Set to `0.0.0.0` or your LAN IP to accept LAN connections** (required for `olp-connect <ip>` to actually reach the server). Default loopback-only is the secure default. See [ADR 0011 § Deployment configurations](./docs/adr/0011-anonymous-key-deployment-context.md#deployment-configurations-d76-amendment-2026-05-26) for the trust-context table — never bind to a public-internet IP. |
 | `OLP_API_KEY` | (none) | Owner-tier OLP API key (the `olp_...` plaintext from `olp-keys keygen --owner`) used by `olp` CLI subcommands as the bearer for management endpoints. |
 | `OLP_OWNER_TOKEN` | (none) | Fallback used by `olp` CLI if `OLP_API_KEY` is absent. |
 | `OLP_PROXY_URL` | `http://127.0.0.1:$OLP_PORT` | Override target URL for `olp` CLI subcommands (so the same binary works against a remote OLP via SSH tunnel or direct LAN). |
 | `OLP_CLAUDE_BIN` | `claude` (from PATH) | Override path to the `claude` binary (Anthropic provider). Useful when multiple `claude` installs are present. |
 | `OLP_CODEX_BIN` | `codex` (from PATH) | Override path to the `codex` binary (OpenAI provider). |
 | `OLP_VIBE_BIN` | `vibe` (from PATH) | Override path to the `vibe` binary (Mistral provider). |
@@ -252,9 +424,9 @@ Use a dedicated bot key — not the maintainer's personal owner key — so revoc
 ---
-## Implementation status (as of 2026-05-25, post-v0.2.0)
+## Implementation status (as of 2026-05-26, post-v0.4.0)
-Phase 1 closed at v0.1.1 (multi-provider proxy core + pre-Phase-2 cleanup). Phase 2 closed at v0.2.0 (multi-key auth + audit + owner gating + keygen CLI; ADR 0007 § 10 all 11 acceptance criteria shipped). Phase 3 closed at v0.3.0 (Dashboard + `lib/audit-query.mjs` + daily audit rotation; ADR 0008 § 10 all 15 acceptance criteria shipped). Phase 4 (per-key per-provider auth + audit retention + SQLite hybrid + provider-cost weights) is the next planned milestone. This table reflects what is currently shipped vs. what is designed for later phases.
+Phase 1 closed at v0.1.1 (multi-provider proxy core + pre-Phase-2 cleanup). Phase 2 closed at v0.2.0 (multi-key auth + audit + owner gating + keygen CLI; ADR 0007 § 10 all 11 acceptance criteria shipped). Phase 3 closed at v0.3.0 (Dashboard + `lib/audit-query.mjs` + daily audit rotation; ADR 0008 § 10 all 15 acceptance criteria shipped). Phase 4 closed at v0.4.0 (Operator + Client UX per ADR 0010: SSE heartbeat + `recentErrors[20]` + `/v0/management/status` / `olp` Node CLI + `olp doctor` framework + ADR 0002 Amendment 7 / `olp-connect` bash + `/health.anonymousKey` + ADR 0011 / `olp-plugin/` Telegram-Discord + 6-IDE integration docs). Phase 5 scope is open — candidates per ADR 0010 § Out-of-Phase-4-scope. This table reflects what is currently shipped vs. what is designed for later phases.
 | File / artifact | Status | Notes |
 |---|---|---|
@@ -289,7 +461,9 @@ Behaviors that work correctly at personal/family scale but have ratified follow-
 - **Soft triggers configured but inert.** `routing.soft_triggers` in `~/.olp/config.json` is honored by the engine's evaluation logic but `quotaStatus()` polling is not wired (ADR 0004 Amendment 2). A startup warning fires if the field is non-empty so the inert state is visible.
 - **Multi-key auth + owner gating + keygen CLI shipped at v0.2.0 (D44 + D45 + D46 + D47).** `lib/keys.mjs` (core), `lib/audit.mjs` (audit), owner-vs-guest `/health` payload trimming + `X-OLP-Fallback-Detail` policy gating, `bin/olp-keys.mjs` (keygen CLI). All 11 ADR 0007 § 10 acceptance criteria covered. v0.2.0 maintainer-merged 2026-05-25.
- **Phase 3 (Dashboard + audit query layer + rotation) shipped to main (D48-D54); v0.3.0 release pending.** `docs/adr/0008-dashboard-and-audit-query.md` ratified at D48. `lib/audit-query.mjs` (D49) implements the 5-function aggregate query API (in-memory ndjson scan, PII-guarded). 4 new owner-only_block endpoints at D50 (`/dashboard`, `/v0/management/dashboard-data`, `/v0/management/quota`, `/cache/stats`). `dashboard.html` full multi-panel UI at D51 (vanilla HTML+JS+fetch, 30s poll with visibilitychange pause). Daily audit rotation at D52 (synchronous on first append after UTC midnight; `audit-YYYY-MM-DD.ndjson` naming) + optional `bin/olp-audit-rotate.mjs` cron tool. `tried_providers` schema semantic fix at D53 (D45 P2 deferral). Phase 3 close to v0.3.0 is maintainer-triggered per CLAUDE.md `release_kit.phase_close_trigger`.
+- **Phase 3 (Dashboard + audit query layer + rotation) shipped at v0.3.0 (D48–D54).** `docs/adr/0008-dashboard-and-audit-query.md` + `lib/audit-query.mjs` (D49) + 4 owner-only_block endpoints (D50) + `dashboard.html` (D51) + daily audit rotation (D52) + `tried_providers` schema fix (D53). All 15 ADR 0008 § 10 acceptance criteria covered.
 - **Phase 4 (Operator + Client UX) shipped at v0.4.0 (D60 → D73).** ADR 0010 (charter) + ADR 0011 (anonymous-key trusted-LAN limits) + ADR 0002 Amendment 7 (provider `doctorChecks()` contract). Default `OLP_PORT` 3456 → 4567 so OLP and OCP can co-host. SSE heartbeat (D61) + `recentErrors[20]` + `/v0/management/status` (D62-D63). `bin/olp.mjs` Node CLI + `bin/olp-keys.mjs` + `lib/doctor.mjs` framework with `next_action.ai_executable[]` (D64-D67). `bin/olp-connect` bash zero-config IDE auto-config + opt-in `/health.anonymousKey` (D68-D70). `olp-plugin/` OpenClaw `/olp` Telegram-Discord plugin (read-only, no chat mutations) + 6 IDE integration docs at `docs/integrations/*.md` (D71-D73). Test count 623 → 696.
  **Bootstrap workflow (D47):** for first-run / production setup:
@@ -351,16 +525,22 @@ Full spec (decision rationale, open questions, risks): `~/.cc-rules/memory/proje
 ## Migration from OCP
 OLP is OCP's successor. The trigger was Anthropic's 2026-05-14 announcement (effective 2026-06-15) splitting `claude -p` / Agent SDK / third-party agent traffic out of the Pro/Max subscription pool into a separate fixed $100/month Agent SDK credit pool — invalidating OCP's foundational assumption (*"subscription = unlimited within rate limits"*) for its only provider. OLP's structural response is to spread risk across multiple subscriptions whose CLI/programmatic use remains in their main subscription pool, with intelligent fallback when one runs out.
 Beyond the billing trigger, OLP is intentionally NOT a commercial multi-tenant SaaS (LiteLLM / OpenRouter / Portkey already serve that market with funding + SOC2), NOT an enterprise gateway competing on provider breadth, NOT a model-capability router ("route to the smartest model" — you pick the model in `routing.chains`), and NOT a conversation-state store (your client manages its own context). See [ADR 0001](./docs/adr/0001-project-founding.md) for the founding decision and [`ALIGNMENT.md`](./ALIGNMENT.md) for the constitution that governs every plugin / IR / entry-surface change.
 ### Migrating an existing OCP install
 _placeholder — `scripts/migrate-from-ocp.mjs` lands with Phase 7 (📋 planned, not yet authored)._
 Anticipated user-facing flow (target: <5 minutes):
 1. Stop OCP (`launchctl bootout` the OCP service or `ocp stop`).
-2. Install OLP.
+2. Install OLP (per [§ Manual install](#manual-install-5-10-min) above).
-3. Run `olp migrate-from-ocp` — copies `~/.ocp/keys/` to `~/.olp/keys/` and points provider plugins at OCP's existing auth artifacts where applicable.
+3. Run `olp migrate-from-ocp` — will copy `~/.ocp/keys/` to `~/.olp/keys/` and point provider plugins at OCP's existing auth artifacts where applicable.
-4. Start OLP. Clients pointing at port 4567 (or 3456 with `OLP_PORT=3456`) keep working; their existing OLP API keys remain valid. **Note (v0.4.0+):** default port moved from 3456 → 4567 so OCP and OLP can co-host during migration; set `OLP_PORT=3456` if you want the pre-D60 default.
+4. Start OLP. Clients pointing at port 4567 (or 3456 with `OLP_PORT=3456`) keep working; their existing OLP API keys remain valid.
-OCP's cache directory is *not* migrated: OLP's cache key format includes provider+model and warms cold naturally. OCP enters maintenance mode (stability fixes only) when OLP v0.1 ships; new development happens in OLP.
+**Default port moved 3456 → 4567 at v0.4.0** so OCP and OLP can co-host on the same machine during the migration window — set `OLP_PORT=3456` if you want the pre-D60 default. OCP's cache directory is *not* migrated: OLP's cache key format includes provider+model and warms cold naturally. OCP enters maintenance mode (stability fixes only) when OLP v0.1 ships; new development happens in OLP.
 ---
@@ -114,6 +114,35 @@ key_display() {
  fi
 }
 # D74 P1-2: validate OLP API key format. Per ADR 0007 § 3, tokens are
 # `olp_` + 32 random bytes base64url-encoded (43 chars, no padding). This
 # regex pins the on-the-wire shape so a malformed or hostile `--key` /
 # server-advertised `anonymousKey` never gets persisted into a shell rc.
 # Returns 0 on valid, 1 on invalid (with diagnostic to stderr).
 validate_olp_token() {
  local k="$1" source="$2"
  if [[ ! "$k" =~ ^olp_[A-Za-z0-9_-]{43}$ ]]; then
    log_err "Rejected $source: token format does not match ^olp_[A-Za-z0-9_-]{43}$ (ADR 0007 § 3)."
    log_err "  Got ${#k}-char value starting with '$(echo "$k" | cut -c1-8)...'"
    log_err "  Expected: olp_ followed by 43 base64url chars. Run 'npx olp-keys list' on the server"
    log_err "  to confirm the key format, or have the operator regenerate with 'npx olp-keys keygen'."
    return 1
  fi
  return 0
 }
 # D74 P1-2: POSIX shell-quote a value before interpolating into a shell rc
 # write. Wraps in single quotes + escapes embedded single quotes per:
 #   foo'bar  →  'foo'\''bar'
 # Even with the validator above, this is defense-in-depth: any non-token
 # string that slips through (e.g., environment.d KEY=VALUE writes) MUST be
 # safe to source. Same helper pattern as lib/doctor.mjs _shellQuote.
 shell_quote() {
  local s="$1"
  # Escape any single quotes: ' → '\''
  printf "'%s'" "${s//\'/\'\\\'\'}"
 }
 # Detect Claude Code and print warn-only message. Per ADR 0010 § Out of
 # Phase 4 scope, OLP does NOT ship /v1/messages and CC is not a supported
 # client. The user is steered toward Cline + OLP.
@@ -297,17 +326,20 @@ append_olp_block() {
  if $DRY_RUN; then
    log_change "[dry-run] would append OLP block to $rc_file:"
    log_change "    # OLP LAN (added by olp-connect)"
-    log_change "    export OPENAI_BASE_URL=$base_url/v1"
+    log_change "    export OPENAI_BASE_URL=$(shell_quote "$base_url/v1")"
-    [[ -n "$key" ]] && log_change "    export OPENAI_API_KEY=$(key_display "$key")"
+    [[ -n "$key" ]] && log_change "    export OPENAI_API_KEY=$(shell_quote "$(key_display "$key")")"
    log_change "    # /OLP LAN"
    return 0
  fi
  # D74 P1-2: shell-quote values before writing to rc files. Defense-in-depth
  # alongside validate_olp_token — even if a future code path bypasses the
  # validator, the rc file remains safe to source.
  {
    echo ""
    echo "# OLP LAN (added by olp-connect)"
-    echo "export OPENAI_BASE_URL=$base_url/v1"
+    echo "export OPENAI_BASE_URL=$(shell_quote "$base_url/v1")"
    if [[ -n "$key" ]]; then
-      echo "export OPENAI_API_KEY=$key"
+      echo "export OPENAI_API_KEY=$(shell_quote "$key")"
    fi
    echo "# /OLP LAN"
  } >> "$rc_file"
@@ -341,6 +373,14 @@ set_system_env() {
      return 0
    fi
    mkdir -p "$env_dir" 2>/dev/null
    # D74 P1-2: systemd environment.d format is KEY=VALUE per line. While
    # systemd does its own parsing (no shell sourcing), reject embedded
    # newlines defensively — validate_olp_token already enforces the
    # restricted charset for the API key, so this is belt-and-braces.
    if [[ "$base_url" == *$'\n'* || "$key" == *$'\n'* ]]; then
      log_err "Refusing to write environment.d entry: value contains newline."
      return 2
    fi
    {
      echo "OPENAI_BASE_URL=$base_url/v1"
      if [[ -n "$key" ]]; then
@@ -363,8 +403,13 @@ main() {
      --port=*)  port="${1#*=}"; shift ;;
      --key)     key="${2:?--key requires a value}"
                 [[ -z "$key" ]] && { log_err "--key cannot be empty (omit --key for zero-config / auto-discovery)"; exit 1; }
                 # D74 P1-2: reject malformed --key before it ever reaches an rc write.
                 validate_olp_token "$key" "--key flag" || exit 1
                 shift 2 ;;
-      --key=*)   key="${1#*=}"; shift ;;
+      --key=*)   key="${1#*=}"
                 [[ -z "$key" ]] && { log_err "--key cannot be empty (omit --key for zero-config / auto-discovery)"; exit 1; }
                 validate_olp_token "$key" "--key flag" || exit 1
                 shift ;;
      --no-system-env) NO_SYSTEM_ENV=true; shift ;;
      --dry-run) DRY_RUN=true; shift ;;
      --version) show_version; exit 0 ;;
@@ -457,6 +502,13 @@ try:
    print(k if isinstance(k, str) and k else '')
 except: print('')" 2>/dev/null || echo "")
    if [[ -n "$anon_key" ]]; then
      # D74 P1-2: validate server-advertised token shape before consuming.
      # A hostile or misconfigured server could otherwise inject arbitrary
      # strings into the user's rc file via the `anonymousKey` field.
      if ! validate_olp_token "$anon_key" "/health.anonymousKey from $remote_host"; then
        log_err "Refusing to consume malformed advertised key. Use --key explicitly or contact the OLP operator."
        exit 2
      fi
      key="$anon_key"
      log_ok "Using server-advertised anonymous key: $(key_display "$key")"
      log_info "  (set by remote via auth.advertise_anonymous_key=true; see ADR 0011 for"
@@ -479,6 +531,8 @@ except: print('')" 2>/dev/null || echo "")
          log_err "  Re-run with: olp-connect $host --key olp_..."
          exit 2
        fi
        # D74 P1-2: also validate the interactively-prompted key.
        validate_olp_token "$key" "interactive prompt" || exit 1
      fi
    fi
  fi
@@ -251,9 +251,15 @@ async function cmdStatus(flags, io) {
  }
  io.log(`  total reqs:  ${body.stats?.total_requests ?? 0}`);
  io.log(`  active reqs: ${body.stats?.active_requests ?? 0}`);
  // D75 F4 fix: server payload nests cache stats under stats.cache (per
  // server.mjs handleManagementStatus, ~line 2092). The CacheStore.stats()
  // contract returns { hits, misses, size, inflightCount } per
  // lib/cache/store.mjs — there is no `entries` field. Pre-D75 cmdStatus read
  // `body.stats.cache.entries` (OCP-era) which was always undefined → output
  // showed "entries=?". Same pattern as D74 P2-3 applied to cmdCache/cmdUsage.
  if (body.stats?.cache) {
    const c = body.stats.cache;
-    io.log(`  cache:       hits=${c.hits ?? 0} misses=${c.misses ?? 0} entries=${c.entries ?? '?'}`);
+    io.log(`  cache:       hits=${c.hits ?? 0} misses=${c.misses ?? 0} entries=${c.size ?? 0}${typeof c.inflightCount === 'number' ? ` inflight=${c.inflightCount}` : ''}`);
  }
  if (Array.isArray(body.recent_errors) && body.recent_errors.length > 0) {
    io.log(`  recent errors: ${body.recent_errors.length}`);
@@ -301,29 +307,50 @@ async function cmdUsage(flags, io) {
  try { body = JSON.parse(res.body); }
  catch { io.errln('Error: server returned non-JSON body'); return 2; }
  if (io.wantJson) { io.emitJson(body); return 0; }
  // D74 P2-3 fix: server payload shape is { generated_at, window_24h: { request_count, status_2xx,
  // status_4xx, status_5xx, by_provider, by_owner_tier, by_path, median_latency_ms, p95_latency_ms },
  // cache_hit_24h: { total, hit, miss, bypass, streaming_attached, hit_rate, by_provider }, quota: [{provider, ...}],
  // spend_trend_30d: [{date, request_count, by_provider}], top_fallback_chains_24h: [{chain, count, ...}],
  // cache_stats: { hits, misses, size, inflightCount } } per server.mjs:2027 + lib/audit-query.mjs.
  io.log(colorize('OLP usage (24h)', ANSI.bold, io.useColor));
  io.log('─'.repeat(60));
-  const u24 = body.usage_24h ?? body.usage24h ?? body['24h'] ?? {};
+  const w24 = body.window_24h ?? {};
-  if (typeof u24 === 'object' && Object.keys(u24).length > 0) {
+  const cache24 = body.cache_hit_24h ?? {};
-    io.log(`  requests: ${u24.requests ?? '?'}`);
+  if (typeof w24 === 'object' && (w24.request_count ?? 0) > 0) {
-    io.log(`  cache hits: ${u24.cache_hits ?? '?'}`);
+    io.log(`  requests:        ${w24.request_count}`);
-    io.log(`  fallbacks: ${u24.fallbacks ?? '?'}`);
+    io.log(`  2xx / 4xx / 5xx: ${w24.status_2xx ?? 0} / ${w24.status_4xx ?? 0} / ${w24.status_5xx ?? 0}`);
    if (typeof w24.median_latency_ms === 'number') {
      io.log(`  latency p50/p95: ${w24.median_latency_ms}ms / ${w24.p95_latency_ms ?? 0}ms`);
    }
    if (typeof cache24.hit_rate === 'number') {
      const pct = (cache24.hit_rate * 100).toFixed(1);
      io.log(`  cache hit rate:  ${pct}% (hit=${cache24.hit ?? 0} miss=${cache24.miss ?? 0}${cache24.streaming_attached ? ` streaming_attached=${cache24.streaming_attached}` : ''})`);
    }
  } else {
    io.log('  (no 24h usage data — server may not have processed any requests yet)');
  }
-  if (Array.isArray(body.providers)) {
+  if (Array.isArray(body.quota) && body.quota.length > 0) {
    io.log('');
    io.log(colorize('Per-provider quota', ANSI.bold, io.useColor));
    io.log('─'.repeat(60));
-    for (const p of body.providers) {
+    for (const p of body.quota) {
-      io.log(`  ${String(p.name ?? '?').padEnd(12)} ${p.percent_used != null ? `${p.percent_used}% used` : 'no quota api'}`);
+      const label = String(p.provider ?? '?').padEnd(12);
      if (p.error) {
        io.log(`  ${label} error: ${p.error}`);
      } else if (typeof p.percent_used === 'number') {
        io.log(`  ${label} ${p.percent_used}% used${p.resets_in_human ? ` (resets in ${p.resets_in_human})` : ''}`);
      } else if (p.available === false) {
        io.log(`  ${label} unavailable`);
      } else {
        io.log(`  ${label} no quota api`);
      }
    }
-  if (Array.isArray(body.top_fallback_chains)) {
+  }
  if (Array.isArray(body.top_fallback_chains_24h) && body.top_fallback_chains_24h.length > 0) {
    io.log('');
-    io.log(colorize('Top fallback chains', ANSI.bold, io.useColor));
+    io.log(colorize('Top fallback chains (24h)', ANSI.bold, io.useColor));
    io.log('─'.repeat(60));
-    for (const f of body.top_fallback_chains.slice(0, 10)) {
+    for (const f of body.top_fallback_chains_24h.slice(0, 10)) {
      io.log(`  ${String(f.count ?? '?').padStart(5)}  ${(f.chain ?? []).join(' → ')}`);
    }
  }
@@ -360,13 +387,20 @@ async function cmdCache(flags, io) {
  try { body = JSON.parse(res.body); }
  catch { io.errln('Error: server returned non-JSON body'); return 2; }
  if (io.wantJson) { io.emitJson(body); return 0; }
-  io.log(colorize('OLP cache', ANSI.bold, io.useColor));
+  // D74 P2-3 fix: cacheStore.stats() returns { hits, misses, size, inflightCount }
  // per lib/cache/store.mjs:320. There is no entries / evictions / bytes / maxBytes
  // in the OLP cache model — those were OCP-era field names. Compute a hit rate from
  // the numerator/denominator instead of fabricating bytes.
  const hits = body.hits ?? 0;
  const misses = body.misses ?? 0;
  const denom = hits + misses;
  const hitRate = denom > 0 ? ((hits / denom) * 100).toFixed(1) : '0.0';
  io.log(colorize('OLP cache (live in-memory)', ANSI.bold, io.useColor));
  io.log('─'.repeat(60));
-  io.log(`  entries:  ${body.entries ?? '?'}`);
+  io.log(`  entries:        ${body.size ?? 0}`);
-  io.log(`  hits:     ${body.hits ?? 0}`);
+  io.log(`  hits / misses:  ${hits} / ${misses}  (hit rate ${hitRate}%)`);
-  io.log(`  misses:   ${body.misses ?? 0}`);
+  io.log(`  inflight:       ${body.inflightCount ?? 0}`);
-  io.log(`  evictions:${body.evictions ?? 0}`);
+  if (body.generated_at) io.log(`  generated_at:   ${body.generated_at}`);
  io.log(`  bytes:    ${formatBytes(body.bytes ?? 0)} (max ${formatBytes(body.maxBytes ?? 0)})`);
  return 0;
 }
@@ -574,10 +608,16 @@ async function cmdDoctor(flags, io) {
  const proxyUrl = resolveProxyUrl({ proxyUrl: flags['proxy-url'] });
  const checkFilter = typeof flags.check === 'string' ? flags.check : undefined;
  // D74 P1-1: pass authHeaders so server.running / server.version checks
  // succeed under the default production posture (auth.allow_anonymous:
  // false). resolveBearerToken returns null when no env var is set; the
  // doctor still runs but distinguishes 401 from "server down" by status
  // code per the updated check.
  const result = await runDoctor({
    olpHome,
    proxyUrl,
    checkFilter,
    authHeaders: authHeaders(),
  });
  if (io.wantJson) {
@@ -214,6 +214,24 @@ alongside the "using server-advertised key" notice.
 ---
 ## Deployment configurations (D76 amendment, 2026-05-26)
 Original ADR 0011 referenced a `BIND_ADDRESS` concept that did not exist in the v0.4.0–v0.4.2 codebase — the server was hard-coded to `server.listen(PORT, '127.0.0.1', ...)`. D76 closes this gap by adding the `OLP_BIND` env var (default `127.0.0.1`), making the deployment-context discussion below operational rather than aspirational.
 Three deployment configurations are supported:
 | `OLP_BIND` value | Reachability | Anonymous-key publication |
 |---|---|---|
 | `127.0.0.1` (default) | Loopback only | Safe with any auth posture (no LAN exposure at all) |
 | RFC1918 IP / tailnet IP / `0.0.0.0` on a trusted LAN | LAN clients only | Safe when `advertise_anonymous_key: true` — the documented "trusted-LAN" zero-config family onboarding flow |
 | Public IP / `0.0.0.0` on a public-facing host | Public internet | **Incompatible with `advertise_anonymous_key: true`.** Operator MUST keep `advertise_anonymous_key: false` (default). |
 The server emits a startup warn event `anonymous_key_advertised_with_lan_bind` when `OLP_BIND` is non-loopback AND `advertise_anonymous_key: true` (per the `lib/keys.mjs` + `server.mjs` checks). The warn is a **checkpoint, not a hard gate** — the server cannot tell from the bind address alone whether the operator is on a trusted LAN (RFC1918 / tailnet) or has accidentally exposed a public IP. The Re-evaluation trigger #1 below escalates to a hard gate when OLP gains a public-internet deployment mode.
 `olp-connect <ip>` consumes `/health.anonymousKey` over the network — therefore requires `OLP_BIND` to include the LAN interface on the server side. Without setting `OLP_BIND=<lan-ip>` (or `0.0.0.0`), `olp-connect <ip>` will fail with `connect ECONNREFUSED` because the server only accepts loopback connections.
 ---
 ## Re-evaluation triggers
 Re-open this ADR when ANY of the following fires:
@@ -144,6 +144,15 @@ export function buildBuiltinChecks(opts = {}) {
  const olpHome = resolveOlpHome(opts);
  const configPath = join(olpHome, 'config.json');
  const proxyUrl = resolveProxyUrl(opts);
  // D74 P1-1 fix: server.running and server.version probe /health, which
  // under default production posture (auth.allow_anonymous: false) requires
  // an Authorization: Bearer header. Without it, the probe gets 401 and
  // doctor falsely reports the server down. Caller passes the resolved
  // bearer token via opts.authHeaders (a `{Authorization: 'Bearer ...'}`
  // object). Empty headers means "no token configured" — the probe still
  // fires but a 401 response is treated as "auth misconfigured" rather
  // than "server down" (see server.running check below).
  const authHeaders = opts.authHeaders ?? {};
  const checks = [];
@@ -298,7 +307,9 @@ export function buildBuiltinChecks(opts = {}) {
      id: 'server.running',
      category: 'server',
      async run() {
-        const r = await httpGet(`${proxyUrl}/health`, { timeoutMs: 3000 });
+        // D74 P1-1: pass authHeaders so the probe works under the default
        // production posture (auth.allow_anonymous: false).
        const r = await httpGet(`${proxyUrl}/health`, { timeoutMs: 3000, headers: authHeaders });
        if (!r.ok) {
          return {
            status: 'fail',
@@ -311,6 +322,25 @@ export function buildBuiltinChecks(opts = {}) {
            },
          };
        }
        // 401: server is up but the caller has no/wrong bearer token. NOT a
        // "server down" condition — distinguish so the kind discriminator
        // doesn't route to fix_server when the user just needs OLP_API_KEY.
        if (r.status === 401 || r.status === 403) {
          return {
            status: 'fail',
            message: `${proxyUrl}/health returned ${r.status} — server is up but the bearer token is missing or invalid. Set OLP_API_KEY env to an owner-tier token (npx olp-keys list).`,
            evidence: {
              fix_commands: [
                'echo "set OLP_API_KEY=<your owner token> or OLP_OWNER_TOKEN=<...> then rerun olp doctor"',
              ],
              human_required: [
                'Locate an owner-tier OLP API key plaintext (or run `npx olp-keys keygen --owner` to mint a new one — printed ONCE).',
                'Export it: `export OLP_API_KEY=olp_...`',
              ],
              reference: 'docs/adr/0007-multi-key-auth.md § 9.1 + README § Environment Variables',
            },
          };
        }
        if (r.status !== 200) {
          return { status: 'fail', message: `${proxyUrl}/health returned status=${r.status}` };
        }
@@ -333,7 +363,8 @@ export function buildBuiltinChecks(opts = {}) {
        } catch {
          return { status: 'warn', message: 'Could not read local package.json — skipping version comparison' };
        }
-        const r = await httpGet(`${proxyUrl}/health`, { timeoutMs: 3000 });
+        // D74 P1-1: same auth-headers fix as server.running.
        const r = await httpGet(`${proxyUrl}/health`, { timeoutMs: 3000, headers: authHeaders });
        if (!r.ok || r.status !== 200) {
          return { status: 'warn', message: `Could not fetch /health to compare version (${r.error ?? `status ${r.status}`})` };
        }
@@ -157,6 +157,36 @@ function resolveCodexBin() {
 // D6 assumption A2: auth file is named auth.json (unconfirmed — D7 will pin).
 // D6 assumption A3: access token field is `access_token` or `token` (unconfirmed).
 //
 // ── D75 (v0.4.2) F1 — codex CLI v0.133.0 schema pin ─────────────────────────
 //
 // Real codex CLI v0.133.0 auth.json (verified empirically on PI231 / Mac mini,
 // 2026-05-26 E2E session):
 //
 //   {
 //     "auth_mode": "chatgpt",
 //     "OPENAI_API_KEY": null | "<key>",
 //     "tokens": {
 //       "id_token":      "<JWT>",
 //       "access_token":  "<opaque-or-JWT>",   <-- THIS is the access token
 //       "refresh_token": "<opaque>",
 //       "account_id":    "<uuid>"
 //     },
 //     "last_refresh":    "<ISO8601>"
 //   }
 //
 // D6 assumption A3 originally tried `creds.access_token` at TOP level. Under
 // codex v0.133.0 this field does not exist at the top level → readAuthArtifact()
 // returned null even when the user had fully completed `codex login`. OLP then
 // reported "auth artifact missing" via /health and `olp doctor`, and refused
 // to spawn codex — false negative blocking the entire openai provider.
 //
 // Fix: prepend `creds?.tokens?.access_token` to the precedence chain. Keep all
 // existing fallbacks unchanged so older codex CLI versions (pre-v0.133) and any
 // future shape variants still resolve.
 //
 // Authority pin: codex CLI v0.133.0 source + on-disk auth.json captured during
 // PI231 E2E. See D75 commit body for the verification transcript.
 //
 // Returns { accessToken: string } or null (never throws).
 export function readAuthArtifact() {
  // 1. Explicit test override — always takes precedence.
@@ -165,7 +195,12 @@ export function readAuthArtifact() {
    try {
      const raw = readFileSync(authPathOverride, 'utf8');
      const creds = JSON.parse(raw);
-      const token = creds?.access_token ?? creds?.token ?? creds?.accessToken;
+      // D75 F1: codex CLI v0.133.0 nests the token under `tokens.access_token`.
      // Preserve top-level fallbacks for backward / forward compat.
      const token = creds?.tokens?.access_token
        ?? creds?.access_token
        ?? creds?.token
        ?? creds?.accessToken;
      if (token && typeof token === 'string') return { accessToken: token };
    } catch { /* fall through */ }
    return null; // explicit path set but file missing / malformed
@@ -178,8 +213,12 @@ export function readAuthArtifact() {
  try {
    const raw = readFileSync(authPath, 'utf8');
    const creds = JSON.parse(raw);
-    // D6 assumption A3: try common OAuth field names in precedence order.
+    // D75 F1: codex CLI v0.133.0 nests the token under `tokens.access_token`.
-    const token = creds?.access_token ?? creds?.token ?? creds?.accessToken;
+    // Try the nested location FIRST, then fall back to legacy top-level fields.
    const token = creds?.tokens?.access_token
      ?? creds?.access_token
      ?? creds?.token
      ?? creds?.accessToken;
    if (token && typeof token === 'string') return { accessToken: token };
  } catch { /* file missing or malformed */ }
@@ -242,9 +281,30 @@ export function irToCodex(irRequest) {
  //     model string (e.g., gpt-5.5, gpt-5.4, gpt-5.3-codex).
  //   PROMPT: "Initial instruction for the task. Use '-' to pipe the prompt
  //     from stdin."
  //
  // ── D75 (v0.4.2) F2 — codex CLI v0.133.0 trusted-directory sandbox ─────────
  // codex CLI v0.133.0 added a trusted-directory sandbox: invocations outside
  // a git repo (or outside any directory explicitly trusted via
  // `codex config trusted-directories`) refuse with:
  //   "Not inside a trusted directory and --skip-git-repo-check was not specified."
  // and exit non-zero with zero NDJSON output → OLP surfaces SPAWN_FAILED with
  // no usable chunks → fallback engine advances to next hop unnecessarily.
  //
  // The CWD that OLP spawns from is typically the server install dir (`~/olp/`
  // on Pi231) which is a git repo on maintainer workstations but is NOT a git
  // repo on most operator hosts. We bypass the sandbox unconditionally because
  // OLP is the trusted caller (it is the operator's own server invoking its own
  // configured Codex subscription via the documented `codex exec` automation
  // entry point). The trusted-directory sandbox is a foot-gun safeguard for
  // interactive users; OLP's spawn is non-interactive and pre-authorized.
  //
  // Authority: codex CLI v0.133.0 release notes / `codex exec --help` output
  // documenting `--skip-git-repo-check`. Verified empirically on PI231 E2E
  // 2026-05-26.
  const args = [
    'exec',
    '--json',
    '--skip-git-repo-check',
    '--model', irRequest.model,
  ];
@@ -291,6 +351,51 @@ export function codexChunkToIR(rawNDJSONLine) {
  if (!event || typeof event !== 'object') return null;
  // ── D75 (v0.4.2) F3 — codex CLI v0.133.0 event shape pin ─────────────────
  // Real codex CLI v0.133.0 NDJSON event stream (verified empirically on PI231
  // / Mac mini, 2026-05-26 E2E session):
  //   {"type":"thread.started","thread_id":"019e..."}
  //   {"type":"turn.started"}
  //   {"type":"item.started","item":{"id":"item_0","type":"reasoning","text":""}}
  //   {"type":"item.completed","item":{"id":"item_0","type":"agent_message","text":"<response>"}}
  //   {"type":"turn.completed","usage":{"input_tokens":..,"output_tokens":..}}
  //
  // The D6 defensive parser recognized `content`/`delta`/`text` fields at the
  // top level and `type === 'stop'`/`done === true`. None of these match
  // v0.133.0's actual shape → every chunk was silently dropped → response body
  // had `content: null`. F3 adds three NEW recognizers (item.completed →
  // agent_message; turn.completed → stop; turn.failed → error) BEFORE the
  // legacy fallback chain. Legacy recognizers preserved for forward/backward
  // compat (older codex versions; future shape variants).
  // F3-a: agent_message item completion.
  // codex v0.133.0 emits assistant text as a single item.completed event whose
  // item.type is 'agent_message' and item.text carries the full text. There
  // are no incremental deltas — the entire response arrives in one chunk.
  if (event.type === 'item.completed'
      && event.item?.type === 'agent_message'
      && typeof event.item?.text === 'string') {
    return { type: 'delta', content: event.item.text };
  }
  // F3-b: turn completion → stop chunk.
  // codex v0.133.0 emits turn.completed with a usage block when the model
  // finishes. We map this to IR stop with finish_reason 'stop'.
  if (event.type === 'turn.completed') {
    return { type: 'stop', finish_reason: 'stop' };
  }
  // F3-c: turn failure → error chunk.
  // codex v0.133.0 emits turn.failed with an embedded error object when the
  // turn cannot complete. Extract a human-readable message for the IR error.
  if (event.type === 'turn.failed') {
    const errMsg = (typeof event.error === 'string')
      ? event.error
      : (event.error?.message ?? 'codex turn.failed');
    return { type: 'error', error: errMsg };
  }
  // ── Legacy/fallback recognizers (kept for backward + forward compat) ────
  // Error event: type === 'error' or error field present
  // A4: defensive — error shape unconfirmed; D7 will pin actual field names
  if (event.type === 'error' || (event.error && typeof event.error === 'string')) {
@@ -138,12 +138,32 @@ export function fmtHealth(body) {
  if (body.uptime_human || body.uptimeHuman) {
    out += `Uptime: ${body.uptime_human ?? body.uptimeHuman}\n`;
  }
  // D74 P2-4 fix: server.mjs /health full payload is
  //   body.providers = { enabled: N, available: N, status: { <name>: {...} } }
  // The plugin previously iterated Object.entries(body.providers), which
  // surfaced `enabled`, `available`, and `status` as pseudo-providers
  // (typeof status === 'object' → loop body fired with name='status').
  // Walk providers.status when present; fall back to providers.* for the
  // older OCP shape that lacks the .status wrapper.
  if (body.providers && typeof body.providers === "object") {
    const enabled = body.providers.enabled;
    const available = body.providers.available;
    if (typeof enabled === "number" || typeof available === "number") {
      out += `Providers: ${enabled ?? "?"} enabled / ${available ?? "?"} available\n`;
    }
    const statusMap = body.providers.status && typeof body.providers.status === "object"
      ? body.providers.status
      : body.providers;
    const entries = Object.entries(statusMap).filter(
      ([name, s]) => typeof s === "object" && s !== null && name !== "enabled" && name !== "available" && name !== "status"
    );
    if (entries.length > 0) {
      out += `\nProviders:\n`;
-    for (const [name, s] of Object.entries(body.providers)) {
+      for (const [name, s] of entries) {
      if (typeof s !== "object" || s === null) continue;
        const i = statusIcon(s?.ok ? "ok" : "fail");
-      out += `  ${i} ${name}\n`;
+        const spawn = typeof s?.activeSpawns === "number" ? `  spawns=${s.activeSpawns}` : "";
        out += `  ${i} ${name}${spawn}\n`;
      }
    }
  }
  return out;
@@ -1,6 +1,6 @@
 {
  "name": "olp",
-  "version": "0.4.0",
+  "version": "0.4.3",
  "description": "Personal multi-provider LLM proxy. Successor to OCP. One HTTP endpoint, multiple subscriptions behind it, automatic routing + fallback + caching.",
  "type": "module",
  "main": "server.mjs",
@@ -18,6 +18,14 @@
 *               so OLP can co-host with OCP for migration windows. ADR 0010 §
 *               Default port. Set OLP_PORT=3456 explicitly to restore the
 *               pre-D60 default when not co-hosting with OCP.)
 *   OLP_BIND  — listen address (default: 127.0.0.1 since D76 / v0.4.3). Set
 *               to 0.0.0.0 (or a specific interface IP) to accept connections
 *               from LAN clients (required for olp-connect <ip> to actually
 *               reach the server). Server emits a startup warn if BIND
 *               resolves to a non-loopback address AND auth.allow_anonymous
 *               is true (anonymous-key over LAN may be acceptable; anonymous-
 *               key over public internet is not — see ADR 0011 § Deployment
 *               configurations).
 */
 import { createServer } from 'node:http';
@@ -77,6 +85,14 @@ const pkg = JSON.parse(readFileSync(join(__dirname, 'package.json'), 'utf8'));
 const VERSION = pkg.version;
 const PORT = parseInt(process.env.OLP_PORT ?? '4567', 10);
 // F5 / D76: OLP_BIND env. Defaults to 127.0.0.1 (loopback only — secure
 // default). Operators expose LAN by setting OLP_BIND=0.0.0.0 (or a specific
 // interface). Per ADR 0011 § Deployment configurations:
 //   - 127.0.0.1: trusted single-machine; safe with any auth posture
 //   - RFC1918 / tailnet / specific LAN IP: trusted-LAN — anonymous_key OK
 //   - 0.0.0.0: ALL interfaces — operator MUST ensure auth posture matches the
 //     network reachability (e.g. no advertise_anonymous_key on public IP)
 const BIND = process.env.OLP_BIND ?? '127.0.0.1';
 const BODY_LIMIT = 5 * 1024 * 1024; // 5 MB
 // ── Logging ───────────────────────────────────────────────────────────────
@@ -253,6 +269,19 @@ if (_authConfig.advertise_anonymous_key === true) {
      message: 'auth.advertise_anonymous_key=true but no active key with plaintext_advertise exists. Run `olp-keys keygen --anonymous --advertise` to create one. /health.anonymousKey will NOT be emitted until then. See ADR 0011.',
    });
  }
  // F5 / D76 (ADR 0011 Deployment configurations): publishing the anonymous
  // key via /health is only safe when /health is reachable ONLY from a
  // trusted network. If OLP_BIND is set to a non-loopback address AND
  // advertise_anonymous_key is true, warn the operator. We can't tell from
  // here whether the non-loopback bind is "trusted LAN" (RFC1918 / tailnet)
  // or "public internet" — that's the operator's responsibility. The warn is
  // a checkpoint, not a hard gate.
  if (BIND !== '127.0.0.1' && BIND !== 'localhost' && BIND !== '::1') {
    logEvent('warn', 'anonymous_key_advertised_with_lan_bind', {
      message: `auth.advertise_anonymous_key=true with OLP_BIND=${BIND} — /health.anonymousKey will be reachable from any host that can connect to ${BIND}:${PORT}. Confirm this address is on a trusted LAN (RFC1918 / tailnet) — never a public IP. See ADR 0011 § Deployment configurations.`,
      bind: BIND,
    });
  }
 }
 /** @internal — test seam: inject a synthetic auth config (no file I/O). */
@@ -1224,13 +1253,25 @@ async function handleChatCompletions(req, res) {
      }
      const chunks = [];
-      // try/finally: releaseSpawn MUST fire on every exit path — success
+      // D75 (v0.4.2) F7 — per-hop model override.
-      // (return at end), spawn throw (caught and re-thrown below), or the
+      // The chain config (routing.chains[<requested-model>][<hop>].model) is the
-      // D16 truncation-salvage return. The finally is the only mechanism
+      // model name to pass to THIS hop's provider plugin — NOT the model the
-      // that guarantees release across all three.
+      // user originally requested. Pre-D75, executeHopFn used hopModel for the
      // cache key + audit ctx but passed the ORIGINAL irReq (with irReq.model
      // still set to the user's request) into hopProviderPlugin.spawn(). Result:
      // a 2-hop chain like [{anthropic, claude-sonnet-4-6}, {openai, gpt-5.5}]
      // would spawn codex with --model claude-sonnet-4-6 on hop 1 — openai rejects
      // the unknown model and the chain dies. This broke the core OLP value prop
      // (cross-provider fallback with provider-appropriate model substitution).
      //
      // Fix: build a per-hop IR variant with the hop's model substituted. Skip
      // the clone when hopModel === irReq.model (single-provider chains and
      // chain hops whose model matches the request). Authority: ADR 0004 §
      // Chain advancement step 1 (per-hop config supplies provider AND model).
      const hopIrReq = irReq.model === hopModel ? irReq : { ...irReq, model: hopModel };
      try {
        try {
-          for await (const irChunk of hopProviderPlugin.spawn(irReq, authContext)) {
+          for await (const irChunk of hopProviderPlugin.spawn(hopIrReq, authContext)) {
            // D16: check error chunks BEFORE pushing — preserves the invariant that
            // chunks array contains only delta/stop chunks. Without this, the catch
            // block's `chunks.length > 0` would mistake a single error chunk for
@@ -1422,9 +1463,16 @@ async function handleChatCompletions(req, res) {
      // releaseSpawn fires exactly once in finally — regardless of normal
      // exhaustion, mid-stream throw, or iterator.return() from cache-layer
      // sourceAbortController propagation (§9).
      //
      // D75 (v0.4.2) F7 — per-hop model override (streaming path).
      // Mirror the buffered-path fix: pass the hop's configured model (streamModel)
      // into streamPlugin.spawn(), not the user's original ir.model. Skip the
      // clone when ir.model === streamModel. See executeHopFn() above for the
      // full F7 rationale + authority citation.
      const streamIr = ir.model === streamModel ? ir : { ...ir, model: streamModel };
      return (async function* sourceWithRelease() {
        try {
-          for await (const irChunk of streamPlugin.spawn(ir, authContext)) {
+          for await (const irChunk of streamPlugin.spawn(streamIr, authContext)) {
            yield irChunk;
          }
        } finally {
@@ -2239,10 +2287,13 @@ const isMain = (() => {
 if (isMain) {
  const server = createOlpServer();
-  server.listen(PORT, '127.0.0.1', () => {
+  server.listen(PORT, BIND, () => {
    const enabledCount = loadedProviders.size;
    // D74 P3-5: banner no longer hardcodes the phase. Derives from VERSION
    // (which advances at every Phase close) so banner stays accurate
    // without future-maintenance touch-ups at every Phase boundary.
    process.stdout.write(
-      `OLP v${VERSION} listening on :${PORT} (${enabledCount} providers enabled — Phase 1 in progress)\n`,
+      `OLP v${VERSION} listening on :${PORT} (${enabledCount} providers enabled)\n`,
    );
  });
 }
@@ -14791,3 +14791,611 @@ describe('Suite 35 — D71 olp-plugin/ smoke tests (ADR 0010 § Phase 4 D71-D73)
    assert.match(r.text, /not owner-tier/);
  });
 });
 // ── Suite 36: D74 v0.4.1 hotfix regression tests (maintainer-review findings) ─
 //
 // These tests pin the FIVE issues maintainer caught in independent post-v0.4.0
 // review that previous D-day reviewers all missed (because they reviewed against
 // spec text, not runtime contracts). Each test exercises a real codepath that,
 // pre-D74, would have produced the documented wrong behavior.
 import { writeFileSync as _writeFileSyncS36, readFileSync as _readFileSyncS36, mkdtempSync as _mkdtempSyncS36, rmSync as _rmSyncS36 } from 'node:fs';
 import { tmpdir as _tmpdirS36 } from 'node:os';
 import { join as _joinS36 } from 'node:path';
 import { spawnSync as _spawnSyncS36 } from 'node:child_process';
 describe('Suite 36 — D74 v0.4.1 hotfix regression (maintainer review findings)', () => {
  it('36a (P1-1) — runDoctor accepts authHeaders + passes them to server.running probe', async () => {
    // Pre-D74: lib/doctor.mjs called httpGet(`${proxyUrl}/health`) with no
    // headers, so under default `auth.allow_anonymous: false` the probe got
    // 401 and reported "server down" — false negative. D74 threads
    // authHeaders through buildBuiltinChecks. This test confirms the wire.
    const { buildBuiltinChecks } = await import('./lib/doctor.mjs');
    const tmpHome = _mkdtempSyncS36(_joinS36(_tmpdirS36(), 'olp-d74a-'));
    const checks = buildBuiltinChecks({
      olpHome: tmpHome,
      proxyUrl: 'http://127.0.0.1:1', // closed port — probe fails with ECONN
      authHeaders: { Authorization: 'Bearer olp_FAKE' },
    });
    const serverRunning = checks.find(c => c.id === 'server.running');
    assert.ok(serverRunning, 'server.running check must exist');
    // We can't easily intercept httpGet here without DI, but the check at
    // least accepts the opts and runs. Real wire-level coverage is 36b below.
    _rmSyncS36(tmpHome, { recursive: true, force: true });
  });
  it('36b (P1-1) — server.running distinguishes 401 (server up, bad token) from "server down"', async () => {
    __setAuthConfig({ allow_anonymous: false, owner_only_endpoints: ['/health'] });
    const serverMod = await import('./server.mjs');
    const s = serverMod.createOlpServer();
    let port36b = 28300 + Math.floor(Math.random() * 100);
    await new Promise((resolve, reject) => {
      s.listen(port36b, '127.0.0.1', resolve);
      s.once('error', e => {
        if (e.code === 'EADDRINUSE') { port36b++; s.listen(port36b, '127.0.0.1', resolve); s.once('error', reject); }
        else reject(e);
      });
    });
    const { runDoctor } = await import('./lib/doctor.mjs');
    try {
      const result = await runDoctor({
        olpHome: process.env.OLP_HOME,
        proxyUrl: `http://127.0.0.1:${port36b}`,
        // intentionally NO authHeaders — simulates user without OLP_API_KEY
      });
      const sr = result.checks.find(c => c.id === 'server.running');
      assert.ok(sr, 'server.running present');
      assert.equal(sr.status, 'fail', 'fails because no token');
      assert.match(sr.message, /401|bearer token/i,
        `must mention 401 / bearer token specifically — got: ${sr.message}`);
      assert.ok(!/unreachable/i.test(sr.message),
        '"unreachable" would falsely imply server is down (P1-1 bug)');
    } finally {
      await new Promise(r => s.close(r));
      __resetAuthConfig();
    }
  });
  it('36c (P1-2) — olp-connect rejects malformed --key', () => {
    // The bash validator: ^olp_[A-Za-z0-9_-]{43}$. Anything else is rejected
    // before it can touch a shell rc file or environment.d entry.
    const result = _spawnSyncS36('bash', [
      _joinS36(import.meta.dirname ?? process.cwd(), 'bin/olp-connect'),
      '127.0.0.1',
      '--port', '1',
      '--key', 'not-an-olp-token',
      '--dry-run',
    ], { encoding: 'utf8', timeout: 5000 });
    assert.equal(result.status, 1, `expected exit 1 for malformed --key, got ${result.status}; stderr=${result.stderr.slice(0, 300)}`);
    assert.match(result.stderr + result.stdout, /token format does not match/i,
      'must surface the validator error');
  });
  it('36d (P1-2) — olp-connect accepts a properly-formed olp_ token', () => {
    // Pad to 43 base64url chars after olp_. Don't actually hit the server —
    // use --port 1 (closed) which makes the connectivity probe fail at
    // the connect step (exit 2), but only AFTER the --key validator passes.
    const goodKey = 'olp_' + 'A'.repeat(43);
    const result = _spawnSyncS36('bash', [
      _joinS36(import.meta.dirname ?? process.cwd(), 'bin/olp-connect'),
      '127.0.0.1',
      '--port', '1',
      '--key', goodKey,
      '--dry-run',
    ], { encoding: 'utf8', timeout: 5000 });
    // Validator passes → reaches connectivity step → exits 2 (or whatever
    // bash propagation gives) but NOT exit 1 from the validator.
    assert.notEqual(result.status, 1, `expected validator to pass; got exit 1 with stderr=${result.stderr.slice(0, 300)}`);
    assert.ok(!/token format does not match/i.test(result.stderr + result.stdout),
      'validator must NOT trigger for a well-formed token');
  });
  it('36e (P2-3) — CacheStore.stats() returns {hits, misses, size, inflightCount} shape', async () => {
    // Real cacheStore.stats() returns { hits, misses, size, inflightCount } per
    // lib/cache/store.mjs. Pre-D74 cmdCache read body.entries / body.bytes /
    // body.maxBytes — all undefined → output showed "entries: ?" and "bytes: 0".
    // Pin the shape so a future server-side rename can't reintroduce the bug.
    // Use the CacheStore class directly (no HTTP) since the field names ARE the
    // contract — server.mjs handleCacheStats just sendJSON(s, 200, cacheStore.stats()).
    const { CacheStore: CS36 } = await import('./lib/cache/store.mjs');
    const cs = new CS36();
    const stats = cs.stats();
    assert.ok('size' in stats, 'CacheStore.stats() shape: size field present');
    assert.ok('hits' in stats, 'CacheStore.stats() shape: hits field present');
    assert.ok('misses' in stats, 'CacheStore.stats() shape: misses field present');
    assert.ok('inflightCount' in stats, 'CacheStore.stats() shape: inflightCount field present');
    assert.ok(!('entries' in stats), 'must NOT have OCP-era entries field');
    assert.ok(!('bytes' in stats), 'must NOT have OCP-era bytes field');
    assert.ok(!('maxBytes' in stats), 'must NOT have OCP-era maxBytes field');
    // Also pin that cmdCache reads body.size (not body.entries) by grepping the source
    const cliSrc = _readFileSyncS36(_joinS36(import.meta.dirname ?? process.cwd(), 'bin/olp.mjs'), 'utf8');
    assert.ok(/body\.size\b/.test(cliSrc), 'cmdCache must read body.size for entries display');
    assert.ok(/body\.inflightCount\b/.test(cliSrc), 'cmdCache must read body.inflightCount');
    assert.ok(!/body\.entries\b/.test(cliSrc), 'cmdCache must NOT read body.entries (OCP-era field)');
  });
  it('36f (P2-3) — dashboard-data payload + cmdUsage source pin the wire-contract field names', () => {
    // server.mjs handleManagementDashboardData (~line 2027) builds the payload
    // inline. Pin by grepping the server source: the keys MUST be window_24h /
    // cache_hit_24h / quota / spend_trend_30d / top_fallback_chains_24h /
    // cache_stats. Pre-D74 cmdUsage read body.usage_24h.requests / body.providers
    // / body.top_fallback_chains — none of which exist in the actual payload.
    const serverSrc = _readFileSyncS36(_joinS36(import.meta.dirname ?? process.cwd(), 'server.mjs'), 'utf8');
    assert.ok(/window_24h:\s*auditAggregateRequests/.test(serverSrc),
      'handleManagementDashboardData must emit window_24h field');
    assert.ok(/cache_hit_24h:\s*auditCacheHitRateWindow/.test(serverSrc),
      'handleManagementDashboardData must emit cache_hit_24h field');
    assert.ok(/top_fallback_chains_24h:/.test(serverSrc),
      'handleManagementDashboardData must emit top_fallback_chains_24h field (NOT top_fallback_chains)');
    assert.ok(/cache_stats:\s*cacheStore\.stats/.test(serverSrc),
      'handleManagementDashboardData must emit cache_stats field');
    // Now pin cmdUsage reads the matching keys
    const cliSrc = _readFileSyncS36(_joinS36(import.meta.dirname ?? process.cwd(), 'bin/olp.mjs'), 'utf8');
    assert.ok(/body\.window_24h\b/.test(cliSrc), 'cmdUsage must read body.window_24h');
    assert.ok(/body\.cache_hit_24h\b/.test(cliSrc), 'cmdUsage must read body.cache_hit_24h');
    assert.ok(/body\.top_fallback_chains_24h\b/.test(cliSrc),
      'cmdUsage must read body.top_fallback_chains_24h (NOT body.top_fallback_chains)');
    assert.ok(/body\.quota\b/.test(cliSrc), 'cmdUsage must read body.quota');
    // Pre-D74 stale reads must be GONE from the CLI source
    assert.ok(!/body\.usage_24h\.requests\b/.test(cliSrc),
      'cmdUsage must NOT read body.usage_24h.requests (OCP-era field)');
  });
  it('36g (P2-4) — olp-plugin fmtHealth iterates providers.status (not providers.*)', async () => {
    // Real /health full payload: providers: { enabled, available, status: { anthropic: {...} } }
    // Pre-D74 fmtHealth iterated Object.entries(body.providers) and the body
    // contained `status: {...}` so the loop printed a pseudo-provider named "status".
    const { fmtHealth } = await import('./olp-plugin/index.js');
    const realServerShape = {
      ok: true,
      version: '0.4.1',
      uptime_human: '1m 3s',
      providers: {
        enabled: 2,
        available: 3,
        status: {
          anthropic: { ok: true, activeSpawns: 0 },
          openai: { ok: false, error: 'oauth-missing', activeSpawns: 0 },
        },
      },
    };
    const out = fmtHealth(realServerShape);
    assert.match(out, /anthropic/, 'must list anthropic by name');
    assert.match(out, /openai/, 'must list openai by name');
    // assert.notMatch isn't available on assert/strict in some Node versions;
    // use the explicit negation pattern to stay portable.
    assert.ok(!/^\s*[🟢🔴⚪]\s*status\s*$/m.test(out),
      'must NOT list "status" as a pseudo-provider (the P2-4 bug)');
    assert.ok(!/^\s*[🟢🔴⚪]\s*enabled\s*$/m.test(out),
      'must NOT list "enabled" as a pseudo-provider');
    assert.ok(!/^\s*[🟢🔴⚪]\s*available\s*$/m.test(out),
      'must NOT list "available" as a pseudo-provider');
    // Also confirm the new enabled/available header
    assert.match(out, /2 enabled \/ 3 available/);
  });
  it('36h (P3-5) — server startup banner does not hardcode a stale phase', () => {
    // Pre-D74 banner literal said "Phase 1 in progress" forever.
    const serverSrc = _readFileSyncS36(_joinS36(import.meta.dirname ?? process.cwd(), 'server.mjs'), 'utf8');
    assert.ok(!/Phase 1 in progress/.test(serverSrc),
      'startup banner must not hardcode "Phase 1 in progress" (stale post v0.4.0)');
    assert.ok(!/Phase 2 in progress/.test(serverSrc));
    assert.ok(!/Phase 3 in progress/.test(serverSrc));
  });
  // ── D75 (v0.4.2) extension — real-machine E2E findings F1, F2, F3, F4, F7 ──
  // Bugs caught on PI231 + Mac mini 2026-05-26 E2E session. Pre-v0.4.0 reviewers
  // and the post-v0.4.0 maintainer review all missed these because they reviewed
  // against spec text, not against real provider CLIs running on a remote machine.
  it('36i (F1) — codex readAuthArtifact() recognises v0.133.0 nested tokens.access_token', () => {
    // Real codex CLI v0.133.0 auth.json shape: { auth_mode, OPENAI_API_KEY,
    //   tokens: { id_token, access_token, refresh_token, account_id }, last_refresh }
    // Pre-D75 readAuthArtifact read only top-level access_token → returned null →
    // OLP falsely reported "auth artifact missing" for fully-logged-in users.
    const tmpDir = _mkdtempSyncS36(_joinS36(_tmpdirS36(), 'olp-d75-f1-nested-'));
    const authPath = _joinS36(tmpDir, 'auth.json');
    _writeFileSyncS36(authPath, JSON.stringify({
      auth_mode: 'chatgpt',
      OPENAI_API_KEY: null,
      tokens: {
        id_token: 'header.body.sig',
        access_token: 'eyJ-real-nested-access-token-d75-36i',
        refresh_token: 'refresh-opaque',
        account_id: '00000000-0000-0000-0000-000000000000',
      },
      last_refresh: '2026-05-26T00:00:00Z',
    }));
    const savedPath = process.env.OPENAI_CODEX_AUTH_PATH;
    process.env.OPENAI_CODEX_AUTH_PATH = authPath;
    try {
      const result = codexReadAuthArtifact();
      assert.ok(result, 'must return non-null for v0.133 nested-shape auth.json');
      assert.equal(result.accessToken, 'eyJ-real-nested-access-token-d75-36i',
        'must extract token from tokens.access_token (v0.133.0 nested shape)');
    } finally {
      if (savedPath !== undefined) process.env.OPENAI_CODEX_AUTH_PATH = savedPath;
      else delete process.env.OPENAI_CODEX_AUTH_PATH;
      _rmSyncS36(tmpDir, { recursive: true, force: true });
    }
  });
  it('36j (F1) — codex readAuthArtifact() still reads legacy top-level access_token', () => {
    // Backwards compat: older codex CLI versions (pre-v0.133) wrote the token
    // at top level. D75 fix preserves that fallback so upgrades don't regress.
    const tmpDir = _mkdtempSyncS36(_joinS36(_tmpdirS36(), 'olp-d75-f1-legacy-'));
    const authPath = _joinS36(tmpDir, 'auth.json');
    _writeFileSyncS36(authPath, JSON.stringify({
      access_token: 'legacy-top-level-token-d75-36j',
    }));
    const savedPath = process.env.OPENAI_CODEX_AUTH_PATH;
    process.env.OPENAI_CODEX_AUTH_PATH = authPath;
    try {
      const result = codexReadAuthArtifact();
      assert.ok(result, 'must return non-null for legacy top-level shape');
      assert.equal(result.accessToken, 'legacy-top-level-token-d75-36j',
        'must fall back to top-level access_token when tokens.access_token absent');
    } finally {
      if (savedPath !== undefined) process.env.OPENAI_CODEX_AUTH_PATH = savedPath;
      else delete process.env.OPENAI_CODEX_AUTH_PATH;
      _rmSyncS36(tmpDir, { recursive: true, force: true });
    }
  });
  it('36k (F1) — codex readAuthArtifact() returns null for malformed auth.json', () => {
    // Malformed JSON / missing token / wrong structure → null (not throw).
    const tmpDir = _mkdtempSyncS36(_joinS36(_tmpdirS36(), 'olp-d75-f1-malformed-'));
    const savedPath = process.env.OPENAI_CODEX_AUTH_PATH;
    try {
      // Case A: unparseable JSON
      const badJsonPath = _joinS36(tmpDir, 'bad.json');
      _writeFileSyncS36(badJsonPath, 'not-json-at-all{{{');
      process.env.OPENAI_CODEX_AUTH_PATH = badJsonPath;
      assert.equal(codexReadAuthArtifact(), null, 'unparseable JSON → null');
      // Case B: valid JSON but no token field anywhere
      const noTokenPath = _joinS36(tmpDir, 'no-token.json');
      _writeFileSyncS36(noTokenPath, JSON.stringify({ auth_mode: 'chatgpt', tokens: {} }));
      process.env.OPENAI_CODEX_AUTH_PATH = noTokenPath;
      assert.equal(codexReadAuthArtifact(), null, 'no token in tokens.access_token or top-level → null');
      // Case C: tokens field present but access_token wrong type
      const wrongTypePath = _joinS36(tmpDir, 'wrong-type.json');
      _writeFileSyncS36(wrongTypePath, JSON.stringify({
        tokens: { access_token: 42 },
      }));
      process.env.OPENAI_CODEX_AUTH_PATH = wrongTypePath;
      assert.equal(codexReadAuthArtifact(), null, 'non-string access_token → null');
    } finally {
      if (savedPath !== undefined) process.env.OPENAI_CODEX_AUTH_PATH = savedPath;
      else delete process.env.OPENAI_CODEX_AUTH_PATH;
      _rmSyncS36(tmpDir, { recursive: true, force: true });
    }
  });
  it('36l (F2) — irToCodex() includes --skip-git-repo-check before --model', () => {
    // codex CLI v0.133.0 sandboxes non-git-repo CWDs by default with:
    //   "Not inside a trusted directory and --skip-git-repo-check was not specified."
    // OLP servers typically deploy outside a git repo on the operator host. The
    // --skip-git-repo-check flag must be in args, before --model, so the spawn
    // succeeds without depending on the install-time CWD.
    const { args } = irToCodex({
      irVersion: IR_VERSION,
      model: 'gpt-5.5',
      stream: false,
      messages: [{ role: 'user', content: 'hello' }],
    });
    assert.ok(args.includes('--skip-git-repo-check'),
      'irToCodex().args must include --skip-git-repo-check (F2 fix)');
    const skipIdx = args.indexOf('--skip-git-repo-check');
    const modelIdx = args.indexOf('--model');
    assert.ok(skipIdx > 0 && modelIdx > 0, 'both flags must be present');
    assert.ok(skipIdx < modelIdx,
      '--skip-git-repo-check must come before --model (cleaner readability + matches codex v0.133 docs ordering)');
    // Confirm exec is still first and --json still adjacent
    assert.equal(args[0], 'exec');
    assert.equal(args[1], '--json');
    assert.equal(args[2], '--skip-git-repo-check');
    assert.equal(args[3], '--model');
    assert.equal(args[4], 'gpt-5.5');
  });
  it('36m (F3) — codexChunkToIR recognises v0.133.0 item.completed agent_message', () => {
    // Real codex v0.133.0 emits the assistant text as one item.completed event:
    //   {"type":"item.completed","item":{"id":"item_0","type":"agent_message","text":"hello world"}}
    // Pre-D75 codexChunkToIR returned null for this shape → response body had
    // content: null because the chunk was silently dropped.
    const result = codexChunkToIR(JSON.stringify({
      type: 'item.completed',
      item: { id: 'item_0', type: 'agent_message', text: 'hello world from codex' },
    }));
    assert.deepEqual(result, { type: 'delta', content: 'hello world from codex' });
  });
  it('36n (F3) — codexChunkToIR recognises v0.133.0 turn.completed → stop', () => {
    // turn.completed marks the end of a codex turn. Map to IR stop.
    const result = codexChunkToIR(JSON.stringify({
      type: 'turn.completed',
      usage: { input_tokens: 12, output_tokens: 7 },
    }));
    assert.deepEqual(result, { type: 'stop', finish_reason: 'stop' });
  });
  it('36o (F3) — codexChunkToIR recognises v0.133.0 turn.failed → error', () => {
    // turn.failed: { type: 'turn.failed', error: { message: 'X' } }
    const result1 = codexChunkToIR(JSON.stringify({
      type: 'turn.failed',
      error: { message: 'rate limit exceeded' },
    }));
    assert.equal(result1?.type, 'error');
    assert.equal(result1.error, 'rate limit exceeded');
    // turn.failed with string error
    const result2 = codexChunkToIR(JSON.stringify({
      type: 'turn.failed',
      error: 'simple string error',
    }));
    assert.equal(result2?.type, 'error');
    assert.equal(result2.error, 'simple string error');
    // turn.failed with no error payload → falls back to default message
    const result3 = codexChunkToIR(JSON.stringify({ type: 'turn.failed' }));
    assert.equal(result3?.type, 'error');
    assert.match(result3.error, /turn\.failed/);
  });
  it('36p (F4) — cmdStatus reads body.stats.cache.size (not OCP-era body.cache.entries)', () => {
    // Server payload (server.mjs handleManagementStatus ~line 2092):
    //   { ok, version, ..., stats: { total_requests, active_requests, cache: { hits, misses, size, inflightCount } } }
    // Pre-D75 cmdStatus formatter read `body.cache.entries` (OCP-era) → always
    // undefined → output showed "entries=?". Pin the wire contract by grepping
    // the CLI source so a future server-side rename can't silently re-break.
    const cliSrc = _readFileSyncS36(_joinS36(import.meta.dirname ?? process.cwd(), 'bin/olp.mjs'), 'utf8');
    // Must contain the cmdStatus block that reads body.stats.cache (not body.cache directly)
    assert.ok(/cmdStatus\b/.test(cliSrc), 'cmdStatus function must exist');
    // The status block must read body.stats?.cache (the actual server payload nesting)
    assert.ok(/body\.stats\?\.cache/.test(cliSrc) || /body\.stats\.cache/.test(cliSrc),
      'cmdStatus must read body.stats.cache for status display');
    // Specifically, the "entries=" output must derive from c.size (matches CacheStore.stats() shape)
    // Find the status cache line and verify it uses c.size
    const statusBlock = cliSrc.match(/cmdStatus[\s\S]+?(?=async function cmd|^\}\s*$)/m);
    assert.ok(statusBlock, 'cmdStatus block extractable');
    assert.ok(/c\.size/.test(statusBlock[0]),
      'cmdStatus cache line must use c.size (matches CacheStore.stats() shape)');
    // And must NOT use the OCP-era c.entries
    assert.ok(!/c\.entries/.test(statusBlock[0]),
      'cmdStatus cache line must NOT read c.entries (OCP-era field that does not exist in CacheStore.stats())');
    // Also pin the CacheStore.stats() shape contract (re-affirms 36e but for status path)
    const cs = new CacheStore();
    const stats = cs.stats();
    assert.ok('size' in stats, 'CacheStore.stats() exposes size');
    assert.ok(!('entries' in stats), 'CacheStore.stats() does NOT expose entries');
  });
  it('36q (F7) — per-hop chain `model` field overrides IR model on fallback hop', async () => {
    // Pre-D75: executeHopFn(provider, model, irReq) used `model` for cache key
    // + audit but passed irReq UNCHANGED to provider.spawn() → the chain
    //   [{anthropic, claude-X}, {openai, gpt-5.5}]
    // would spawn codex with --model claude-X (the user's original request)
    // instead of gpt-5.5 (the chain's per-hop config). This broke cross-provider
    // fallback wherever the chain assigned different models per provider.
    //
    // Strategy: inject a mock openai provider that captures the IR it receives.
    // Force the anthropic hop to fail with SPAWN_FAILED so the chain advances
    // to openai. Assert the mock saw model === hop's configured model.
    const { __setAuthConfig: setAC36q, __resetAuthConfig: resetAC36q,
            __setFallbackConfig: setFC36q, __resetFallbackConfig: resetFC36q,
            createOlpServer, loadedProviders } = await import('./server.mjs');
    setAC36q({ allow_anonymous: true });
    // Capture for mock openai provider
    let capturedIR = null;
    const mockOpenAI = {
      name: 'openai',
      displayName: 'Mock OpenAI for F7',
      contractVersion: '1.0',
      models: ['gpt-5.5'],
      auth: { type: 'oauth', storage: 'file', path: '/tmp/fake', refresh: 'auto' },
      async * spawn(ir, _authContext) {
        // Snapshot the model field as received
        capturedIR = { model: ir.model };
        yield { type: 'delta', role: 'assistant', content: 'mock-openai-response' };
        yield { type: 'stop', finish_reason: 'stop' };
      },
      estimateCost: () => null,
      quotaStatus: async () => null,
      healthCheck: async () => ({ ok: true, latencyMs: 0 }),
      hints: { requiresTTY: false, concurrentSpawnSafe: true, maxConcurrent: 4, cacheable: true },
    };
    // Mock anthropic provider that always fails immediately with SPAWN_FAILED
    const mockAnthropic = {
      name: 'anthropic',
      displayName: 'Mock Anthropic for F7',
      contractVersion: '1.0',
      models: ['claude-sonnet-4-6'],
      auth: { type: 'oauth', storage: 'file', path: '/tmp/fake', refresh: 'auto' },
      async * spawn(_ir, _authContext) {
        throw new ProviderError('mock anthropic always fails (F7 test)', 'SPAWN_FAILED');
        // eslint-disable-next-line no-unreachable
        yield { type: 'stop' };
      },
      estimateCost: () => null,
      quotaStatus: async () => null,
      healthCheck: async () => ({ ok: true, latencyMs: 0 }),
      hints: { requiresTTY: false, concurrentSpawnSafe: true, maxConcurrent: 4, cacheable: true },
    };
    // Save + clear loadedProviders, install the mocks
    const savedProviders = new Map(loadedProviders);
    loadedProviders.clear();
    loadedProviders.set('anthropic', mockAnthropic);
    loadedProviders.set('openai', mockOpenAI);
    // 2-hop chain with DIFFERENT models per hop — the bug only manifests when
    // hopModel !== requested model on the hop that actually serves.
    setFC36q({
      chains: {
        'claude-sonnet-4-6': [
          { provider: 'anthropic', model: 'claude-sonnet-4-6' },
          { provider: 'openai',    model: 'gpt-5.5' },
        ],
      },
      soft_triggers: {},
    });
    const srv = createOlpServer();
    let port = 28400 + Math.floor(Math.random() * 100);
    await new Promise((resolve, reject) => {
      srv.listen(port, '127.0.0.1', resolve);
      srv.once('error', e => {
        if (e.code === 'EADDRINUSE') { port++; srv.listen(port, '127.0.0.1', resolve); srv.once('error', reject); }
        else reject(e);
      });
    });
    try {
      const r = await fetch({
        port,
        method: 'POST',
        path: '/v1/chat/completions',
        body: {
          model: 'claude-sonnet-4-6',
          messages: [{ role: 'user', content: 'F7 test' }],
        },
      });
      assert.equal(r.status, 200, `expected 200, got ${r.status}: ${r.body.slice(0, 300)}`);
      assert.equal(r.headers['x-olp-provider-used'], 'openai',
        'openai must be the serving hop (anthropic failed)');
      // The F7 assertion: the openai hop received the chain's configured model,
      // NOT the user's original request model.
      assert.ok(capturedIR, 'mock openai must have been invoked');
      assert.equal(capturedIR.model, 'gpt-5.5',
        `F7: openai hop must receive its chain-configured model 'gpt-5.5', got '${capturedIR.model}'`);
    } finally {
      await new Promise(r => srv.close(r));
      resetFC36q();
      // Restore original providers
      loadedProviders.clear();
      for (const [k, v] of savedProviders) loadedProviders.set(k, v);
      resetAC36q();
    }
  });
  it('36r (F7) — per-hop model override preserved on streaming single-hop path', async () => {
    // The streaming path (server.mjs ~line 1390-1434) has its own spawn call site
    // inside sourceFactory that previously also passed `ir` unchanged. F7 fix
    // wraps it with the same { ...ir, model: streamModel } substitution. This
    // test exercises a single-hop streaming request and asserts the mock saw
    // the chain's configured model.
    const { __setAuthConfig: setAC36r, __resetAuthConfig: resetAC36r,
            __setFallbackConfig: setFC36r, __resetFallbackConfig: resetFC36r,
            createOlpServer, loadedProviders } = await import('./server.mjs');
    setAC36r({ allow_anonymous: true });
    let capturedModel = null;
    const mockOpenAIStream = {
      name: 'openai',
      displayName: 'Mock Codex for F7 streaming',
      contractVersion: '1.0',
      models: ['gpt-5.5'],
      auth: { type: 'oauth', storage: 'file', path: '/tmp/fake', refresh: 'auto' },
      async * spawn(ir, _authContext) {
        capturedModel = ir.model;
        yield { type: 'delta', role: 'assistant', content: 'streamed-content' };
        yield { type: 'stop', finish_reason: 'stop' };
      },
      estimateCost: () => null,
      quotaStatus: async () => null,
      healthCheck: async () => ({ ok: true, latencyMs: 0 }),
      hints: { requiresTTY: false, concurrentSpawnSafe: true, maxConcurrent: 4, cacheable: true },
    };
    const savedProviders = new Map(loadedProviders);
    loadedProviders.clear();
    loadedProviders.set('openai', mockOpenAIStream);
    // Single-hop chain with a DIFFERENT model than the request — the bug is
    // visible only when the user requests one model name and the chain remaps it.
    setFC36r({
      chains: {
        'gpt-aliased': [
          { provider: 'openai', model: 'gpt-5.5' },
        ],
      },
      soft_triggers: {},
    });
    const srv = createOlpServer();
    let port = 28500 + Math.floor(Math.random() * 100);
    await new Promise((resolve, reject) => {
      srv.listen(port, '127.0.0.1', resolve);
      srv.once('error', e => {
        if (e.code === 'EADDRINUSE') { port++; srv.listen(port, '127.0.0.1', resolve); srv.once('error', reject); }
        else reject(e);
      });
    });
    try {
      const r = await fetch({
        port,
        method: 'POST',
        path: '/v1/chat/completions',
        body: {
          model: 'gpt-aliased',
          stream: true,
          messages: [{ role: 'user', content: 'F7 streaming test' }],
        },
      });
      assert.equal(r.status, 200, `expected 200, got ${r.status}: ${r.body.slice(0, 200)}`);
      assert.equal(capturedModel, 'gpt-5.5',
        `F7 streaming: openai must receive chain-configured model 'gpt-5.5', got '${capturedModel}'`);
    } finally {
      await new Promise(r => srv.close(r));
      resetFC36r();
      loadedProviders.clear();
      for (const [k, v] of savedProviders) loadedProviders.set(k, v);
      resetAC36r();
    }
  });
  // ── F5 (D76 v0.4.3): OLP_BIND env honored + safety warn ──────────────────
  it('36s (F5) — server.mjs reads OLP_BIND with safe default 127.0.0.1', () => {
    // F5 fix: previously bind was hard-coded `server.listen(PORT, '127.0.0.1', ...)`.
    // D76 adds `const BIND = process.env.OLP_BIND ?? '127.0.0.1'` and the listen
    // call uses BIND. Pin via source grep so a future refactor that re-introduces
    // a hardcoded literal in the listen call fails this test.
    const serverSrc = _readFileSyncS36(_joinS36(import.meta.dirname ?? process.cwd(), 'server.mjs'), 'utf8');
    assert.ok(/process\.env\.OLP_BIND\s*\?\?\s*['"]127\.0\.0\.1['"]/.test(serverSrc),
      'server.mjs must read OLP_BIND env with 127.0.0.1 default');
    assert.ok(/server\.listen\(PORT,\s*BIND\b/.test(serverSrc),
      'server.mjs server.listen must use the BIND variable (not a hardcoded address)');
    assert.ok(!/server\.listen\(PORT,\s*['"]127\.0\.0\.1['"]/.test(serverSrc),
      'server.mjs must NOT pass a hardcoded 127.0.0.1 literal to server.listen anymore');
  });
  it('36t (F5) — anonymous_key_advertised_with_lan_bind startup warn wiring', () => {
    // Per ADR 0011 Deployment configurations amendment: when OLP_BIND is
    // non-loopback AND advertise_anonymous_key is true, server emits a startup
    // warn so the operator sees the trust-context overlap. Pin the wiring.
    const serverSrc = _readFileSyncS36(_joinS36(import.meta.dirname ?? process.cwd(), 'server.mjs'), 'utf8');
    assert.ok(/anonymous_key_advertised_with_lan_bind/.test(serverSrc),
      'startup warn event name must be present');
    // Loopback check must compare BIND against ALL three loopback forms
    assert.ok(/BIND\s*!==\s*['"]127\.0\.0\.1['"][\s\S]{0,200}BIND\s*!==\s*['"]localhost['"][\s\S]{0,200}BIND\s*!==\s*['"]::1['"]/.test(serverSrc),
      'startup warn must check BIND against all three loopback forms (127.0.0.1 / localhost / ::1)');
  });
  it('36u (F5) — ADR 0011 Deployment configurations amendment present', () => {
    const adrPath = _joinS36(import.meta.dirname ?? process.cwd(), 'docs/adr/0011-anonymous-key-deployment-context.md');
    const adrSrc = _readFileSyncS36(adrPath, 'utf8');
    assert.ok(/Deployment configurations \(D76 amendment/.test(adrSrc),
      'ADR 0011 must carry the D76 amendment heading');
    assert.ok(/OLP_BIND/.test(adrSrc), 'amendment must document OLP_BIND');
    assert.ok(/anonymous_key_advertised_with_lan_bind/.test(adrSrc),
      'amendment must cite the startup-warn event name');
  });
 });