planr 1.6.0 → 1.7.1

package/README.md

@@ -24,7 +24,7 @@ Flat todo lists break down the moment real work has structure. Planr models work
 - **State survives sessions.** Markdown plans hold scope and acceptance criteria; the SQLite graph holds live status across handoffs, restarts, and agent switches.
 - **Failure is structured.** Stale picks, timeouts, and retries are detectable and recoverable (`planr recover sweep`).
 
-Three layers make that work: **Plans** (reviewable Markdown packages), the **Map** (live dependency graph with picks, reviews, logs), and **Agent loops** (skills, CLI, and MCP workflows for every major coding agent). Full model: [Task Graph Model](docs/TASK_GRAPH_MODEL.md) and [Operating Model](docs/OPERATING_MODEL.md).
+Three layers make that work: **Plans** (reviewable Markdown packages), the **Map** (live dependency graph with picks, reviews, logs), and **Agent loops** (skills, CLI, and MCP workflows for every major coding agent). Full model: [Task Graph Model](https://planr.so/docs/concepts/graph-and-readiness) and [Operating Model](https://planr.so/docs/guides/daily-worker-loop).
 
 ## Install
 
@@ -50,7 +50,7 @@ Then initialize a project. When selected, Claude Code and Cursor also receive st
 planr project init "My Product" --client all
 ```
 
-Manual downloads, from-source builds, and client wiring details: [Install Guide](docs/INSTALL.md).
+Manual downloads, from-source builds, and client wiring details: [Install Guide](https://planr.so/docs/getting-started/installation).
 
 ## Install The Plugin (Skills)
 
@@ -93,7 +93,7 @@ planr install cursor            # writes .cursor/mcp.json, .cursor/agents/, and
 planr install cursor --no-mcp   # project skills, subagents, and hooks; no MCP config
 ```
 
-The dry-run also prints a one-click `cursor://` deeplink for user-level MCP install. Marketplace listing is pending review. Multitasking with Cursor subagents: [Cursor guide](docs/CURSOR.md).
+The dry-run also prints a one-click `cursor://` deeplink for user-level MCP install. Marketplace listing is pending review. Multitasking with Cursor subagents: [Cursor guide](https://planr.so/docs/integrations/cursor).
 
 </details>
 
@@ -110,6 +110,28 @@ planr prompt cli
 
 </details>
 
+## Plugins
+
+Planr plugins extend coding-agent setup around the same local-first graph. They do not move ownership of Planr Core: maps, picks, logs, reviews, approvals, and closure evidence still live in Planr, while optional integrations own their own install, generated files, and uninstall lifecycle.
+
+Switchloom is an optional external routing plugin for repository-local model-routing declarations. Use the corrected current quickstart command with the exact verified package version:
+
+```bash
+npx switchloom@0.3.2 compile balanced --host codex-openai --integration planr --output balanced-planr-codex.json
+npx switchloom@0.3.2 apply balanced-planr-codex.json --repository .
+planr agents check
+planr agents list --json
+```
+
+Planr consumes the resulting `.planr/agents.toml`, `.planr/policy.toml`, and route evidence; Codex consumes generated native roles after the host reloads its repository config. Switchloom remains responsible for its external lifecycle, including uninstall:
+
+```bash
+npx switchloom@0.3.2 uninstall --repository .
+planr agents check
+```
+
+References: [Plugins docs](https://planr.so/docs/plugins/switchloom), [Switchloom v0.3.2 release](https://github.com/instructa/switchloom/releases/tag/v0.3.2), [current corrected Switchloom quickstart](https://github.com/instructa/switchloom#setup-from-the-website), [v0.3.2 tagged quickstart](https://github.com/instructa/switchloom/blob/v0.3.2/README.md#setup-from-the-website), and [v0.3.2 lifecycle docs](https://github.com/instructa/switchloom/blob/v0.3.2/docs/preset-composition.md#repository-lifecycle-commands). The tagged v0.3.2 README quickstart preserves stale `0.3.1` command examples, so use the explicit `switchloom@0.3.2` commands above for the verified Planr contract.
+
 ## Tell Your Agent
 
 Remember one public entry point: `$planr`. It routes ordinary planning and status work from live Planr state. For long autonomous runs, use the explicit two-step workflow: `$planr-goal` prepares durable state, then `$planr-loop` executes the resulting plan.
@@ -136,7 +158,7 @@ with log evidence, all reviews are closed complete, and a live verification log
 the feature working in the browser. Iteration budget: 10.
 ```
 
-Mid-project work (a new feature, refactor, or fix on an existing project) works the same — it gets its own feature-scoped plan and extends the existing map. Both journeys with example prompts: [Two Journeys](docs/SKILLS.md#two-journeys-new-project-vs-existing-project). Coding agents inspect progress with the compact default `planr map show` or, preferably, `planr map show --json`. The tree preserves exact dependency vocabulary while marking satisfied edges as `blocks✓`; active `blocks` stay red. The boxed `planr map show --view diagram` renderer is exclusively for human supervision and uses neutral `then` routes once those dependencies are satisfied. Agents must not invoke it. Humans can add `--full` for complete status, title, worker, critical-lane, and pressure details. Interactive map output colors states automatically; `--no-color` and `NO_COLOR` keep it plain.
+Mid-project work (a new feature, refactor, or fix on an existing project) works the same — it gets its own feature-scoped plan and extends the existing map. Both journeys with example prompts: [Prompt Recipes](https://planr.so/docs/agents/prompt-recipes). Coding agents inspect progress with the compact default `planr map show` or, preferably, `planr map show --json`. The tree preserves exact dependency vocabulary while marking satisfied edges as `blocks✓`; active `blocks` stay red. The boxed `planr map show --view diagram` renderer is exclusively for human supervision and uses neutral `then` routes once those dependencies are satisfied. Agents must not invoke it. Humans can add `--full` for complete status, title, worker, critical-lane, and pressure details. Interactive map output colors states automatically; `--no-color` and `NO_COLOR` keep it plain.
 
 To supervise an agent from a second terminal, leave the agent running in terminal A and watch its scoped graph in terminal B:
 
@@ -152,30 +174,32 @@ The watcher is likewise a human-only observer. It defaults to the condensed diag
 
 ## What's new
 
-- **1.6.0 — Human map observation:** Added a condensed boxed diagram, live two-terminal watching, accessible state colors, and clearer satisfied dependency routes. These views are intentionally for human supervision; agents keep using the default tree or JSON snapshots. See [Task Graph Model](docs/TASK_GRAPH_MODEL.md), [CLI Reference](docs/CLI_REFERENCE.md), and the [1.6.0 changelog](CHANGELOG.md#160---2026-07-21).
-- **1.5.2 — Standalone core, optional Switchloom:** Planr consumes provider-neutral repository declarations and route evidence only; it works without any routing files, and requested-only routing metadata is not execution proof. Optional model-routing lifecycle is external, with [Switchloom v0.2.1](https://github.com/instructa/switchloom/releases/tag/v0.2.1) verified as the repository-local handoff outside Planr. Start with [Model Routing](docs/MODEL_ROUTING.md), [Switchloom](https://switchloom.ai), the [Switchloom repository](https://github.com/instructa/switchloom), its tagged [setup quickstart](https://github.com/instructa/switchloom/blob/v0.2.1/README.md#setup-from-the-website) and [lifecycle docs](https://github.com/instructa/switchloom/blob/v0.2.1/docs/preset-composition.md#repository-lifecycle-commands), and the [Changelog](CHANGELOG.md).
+- **1.7.1 — Leaner agent guidance and safer local releases:** Slimmed the hot-path Planr skills while preserving their execution and review contracts, moved maintainer benchmark inputs and results outside the public repository, added a fail-closed local release-evidence gate without API keys in CI, and verified the optional external Switchloom v0.3.2 integration. The public 1.7 eval CLI remains available in this patch. See the [1.7.1 changelog](CHANGELOG.md#171---2026-07-25) and [release guidance](https://planr.so/docs/operations/release).
+- **1.7.0 — Evidence-backed evaluations:** Added durable eval suites, runs, comparisons, invalidation and rescoring, correctness/quality/performance gates, cost per verified success, and effort recommendations. The complete workflow is available through the CLI; MCP only mirrors selected surfaces and is optional. Security gates now cover repository leaks, vulnerable dependencies, workflow hardening, privacy, and forbidden staged files. See the [Eval Contract](docs/contracts/EVAL_CONTRACT_V1.md), [CLI Reference](https://planr.so/docs/reference/cli), and the [1.7.0 changelog](CHANGELOG.md#170---2026-07-22).
+- **1.6.0 — Human map observation:** Added a condensed boxed diagram, live two-terminal watching, accessible state colors, and clearer satisfied dependency routes. These views are intentionally for human supervision; agents keep using the default tree or JSON snapshots. See [Task Graph Model](https://planr.so/docs/concepts/graph-and-readiness), [CLI Reference](https://planr.so/docs/reference/cli), and the [1.6.0 changelog](CHANGELOG.md#160---2026-07-21).
+- **1.5.2 — Standalone core, optional Switchloom:** Planr consumes provider-neutral repository declarations and route evidence only; it works without any routing files, and requested-only routing metadata is not execution proof. Optional model-routing lifecycle is external, with [Switchloom v0.3.2](https://github.com/instructa/switchloom/releases/tag/v0.3.2) verified as the current repository-local handoff outside Planr. Start with [Plugins](https://planr.so/docs/plugins), [Switchloom](https://switchloom.ai), the [Switchloom repository](https://github.com/instructa/switchloom), the [current corrected quickstart](https://github.com/instructa/switchloom#setup-from-the-website), the [v0.3.2 tagged quickstart](https://github.com/instructa/switchloom/blob/v0.3.2/README.md#setup-from-the-website), [v0.3.2 lifecycle docs](https://github.com/instructa/switchloom/blob/v0.3.2/docs/preset-composition.md#repository-lifecycle-commands), and the [Changelog](CHANGELOG.md). The tagged v0.3.2 README quickstart keeps stale `0.3.1` command examples; use explicit `switchloom@0.3.2` commands when following Planr's verified contract.
 - **1.4.0 — Verified presets:** Added policy-driven composition, evaluation, signed registry evidence, and the public catalog. See the [1.4.0 release notes](https://github.com/instructa/planr/releases/tag/v1.4.0).
-- **1.3.0 — Native host hooks:** Added automatic session-state injection and loop recovery for supported hosts. See the [Hooks guide](docs/HOOKS.md) and [1.3.0 release notes](https://github.com/instructa/planr/releases/tag/v1.3.0).
+- **1.3.0 — Native host hooks:** Added automatic session-state injection and loop recovery for supported hosts. See the [Integrations guide](https://planr.so/docs/integrations) and [1.3.0 release notes](https://github.com/instructa/planr/releases/tag/v1.3.0).
 
 For the complete release history, see the [Changelog](CHANGELOG.md).
 
 ## Docs
 
-- [Install](docs/INSTALL.md)
-- [Skills](docs/SKILLS.md)
-- [Long-Running Goals](docs/GOALS.md)
-- [Model Routing](docs/MODEL_ROUTING.md) · [Worked Example: Web App](docs/EXAMPLE_WEBAPP.md)
-- [Host Hooks](docs/HOOKS.md)
-- [CLI Reference](docs/CLI_REFERENCE.md)
-- [MCP Guide](docs/MCP_GUIDE.md)
-- [Codex](docs/CODEX.md) · [Claude Code](docs/CLAUDE_CODE.md) · [Cursor](docs/CURSOR.md)
-- [Operating Model](docs/OPERATING_MODEL.md)
-- [Task Graph Model](docs/TASK_GRAPH_MODEL.md)
-- [Architecture](docs/ARCHITECTURE.md)
-- [Testing](docs/TESTING.md)
-- [Troubleshooting](docs/TROUBLESHOOTING.md)
-- [Specification Package](docs/planr-spec/README.md)
-- More: [Changelog](CHANGELOG.md), [Import](docs/IMPORT.md), [Security](docs/SECURITY.md), [Handoffs And Stories](docs/HANDOFFS_AND_STORIES.md), [npm Package](docs/NPM.md)
+Full documentation lives at [planr.so/docs](https://planr.so/docs).
+
+- [Install](https://planr.so/docs/getting-started/installation)
+- [Skills](https://planr.so/docs/agents/skills) · [Prompt Recipes](https://planr.so/docs/agents/prompt-recipes)
+- [Plugins and Model Routing](https://planr.so/docs/plugins) · [Recipes](https://planr.so/docs/guides/recipes)
+- [Integrations and Host Hooks](https://planr.so/docs/integrations)
+- [CLI Reference](https://planr.so/docs/reference/cli) · [MCP Reference](https://planr.so/docs/reference/mcp)
+- [Codex](https://planr.so/docs/integrations/codex) · [Claude Code](https://planr.so/docs/integrations/claude-code) · [Cursor](https://planr.so/docs/integrations/cursor)
+- [Daily Worker Loop](https://planr.so/docs/guides/daily-worker-loop)
+- [Task Graph Model](https://planr.so/docs/concepts/graph-and-readiness)
+- [Architecture](https://planr.so/docs/contributing/architecture)
+- [Testing](https://planr.so/docs/contributing/testing)
+- [Troubleshooting](https://planr.so/docs/troubleshooting)
+- [Specification Package](.planr/plans/product/planr/README.md)
+- More: [Changelog](CHANGELOG.md), [Packages and Reuse](https://planr.so/docs/guides/packages-and-reuse), [Security and Privacy](https://planr.so/docs/contributing/security-and-privacy), [Handoff and Resume](https://planr.so/docs/guides/handoff-and-resume)
 
 ## License
 

package/docs/ARCHITECTURE.md

@@ -8,7 +8,8 @@ Planr V1 is a single Rust binary with explicit module ownership. The crate stays
 - `tests/e2e.rs`: real CLI, MCP, HTTP, import, review-gate, run-log, and concurrent-pick tests.
 - `plugins/planr/`: the installable plugin payload — all ten skills, independent Claude/Cursor worker and reviewer role assets, and the per-host plugin manifests. Planr does not ship model-pinned Codex roles.
 - `.agents/plugins/marketplace.json`, `.claude-plugin/marketplace.json`: marketplace manifests pointing Codex and Claude Code at `plugins/planr`.
-- `docs/`: user and contributor guides; `docs/planr-spec/` is the production specification package for Planr V1.
+- `docs/`: user and contributor guides; `docs/contracts/` holds the frozen product contracts that gate CI.
+- `.planr/plans/product/planr/`: the production specification package for Planr V1, stored as a normal Planr product plan package. It is the only committed `.planr` path; all other runtime state stays local.
 - `examples/real-world-flow.md`: executable real-world operator flow.
 - `scripts/`: installer and release packaging scripts.
 - `npm/`: the npm wrapper package.
@@ -49,6 +50,16 @@ Planr V1 is a single Rust binary with explicit module ownership. The crate stays
 - `src/rolefiles.rs`: static host workflow roles and Cursor skill payloads. It does not select or pin models; externally generated routing artifacts stay outside Planr ownership.
 - `src/util.rs`: small CLI-boundary utilities. Owns ids, timestamps, path helpers, output formatting, and safe file writes.
 
+## Eval Contract V1/V1.1 Ownership
+
+The frozen product contract lives in `docs/contracts/EVAL_CONTRACT_V1.md` until implementation promotes it into code. Its V1.1 efficiency-evidence amendment is additive and keeps the same owner split:
+
+- repository EvalSuite manifests and fixtures are authored inputs;
+- the suite loader owns validation, safe path resolution, normalization, canonical ordering, and digests;
+- SQLite owns immutable suite snapshots, runs, case results, samples, attempt lineage, metering-basis provenance, comparisons, invalidations, rescoring provenance, and eval evidence references;
+- the comparison engine owns verdicts, reason codes, matched effective-treatment compatibility, and derived failure-inclusive efficiency metrics;
+- existing map/log/review/approval state remains authoritative for work closure, so eval evidence may support a review but must never close or reopen items by itself.
+
 ## Boundary Rules
 
 - Command parsing belongs in `src/cli.rs`; process startup belongs in `src/main.rs`; command execution belongs under `src/app/`.

package/docs/RELEASE.md

@@ -10,28 +10,59 @@ The v1 repository-owned public install order is:
 4. npm (`npm install -g planr`) with bundled platform binaries.
 5. Cargo/source builds for maintainers and contributors.
 
-Published npm versions bundle platform-native binaries; see `docs/NPM.md`.
+Published npm versions bundle platform-native binaries; see <https://planr.so/docs/operations/release>.
 
 ## Version Bump
 
-`scripts/release.sh` is the only supported release path. The version lives in one source (`Cargo.toml`) and four distribution manifests must carry it: `Cargo.toml`, `package.json`, `plugins/planr/.codex-plugin/plugin.json`, and `plugins/planr/.claude-plugin/plugin.json`. Manual tagging skips the manifest sync and ships stale plugin versions.
+`scripts/release.sh` is the only supported release path. The version lives in
+`Cargo.toml`; `package.json`, both plugin manifests under `plugins/planr/`, and
+`.cursor-plugin/plugin.json` must match it. Manual tagging skips this sync and
+ships stale versions.
 
 ```bash
+export PLANR_RELEASE_EVAL_SUITE="$HOME/projects/planr-evals/suites/planr-lean-skills-dogfood.suite.json"
+export PLANR_RELEASE_EVAL_RECEIPT=/path/to/sanitized-release-eval-receipt.json
+export PLANR_RELEASE_EVAL_DB=/path/to/planr-evals/results/eval.sqlite
 scripts/release.sh 1.2.0 "one-line release summary"
 ```
 
+Maintainer benchmarks, baselines, model/effort runs, and results live outside
+the public repository in `~/projects/planr-evals`; that workspace and its exact
+layout are not a Planr runtime contract. All three paths above are explicit so a
+release cannot silently use the product repository's ordinary `.planr` database
+or a stale bundled suite. The receipt is a short-lived local pointer containing
+only `schema_version`, comparison and candidate-run identities, suite and
+candidate-revision digests, and creation/expiry timestamps. Prompts,
+completions, credentials, personal paths, raw runs, reports, databases, and the
+receipt itself are never committed to Planr.
+
+Generate the candidate revision with
+`node scripts/verify-release-eval-receipt.mjs --print-candidate-revision`. At
+release time the candidate binary canonicalizes the explicitly supplied suite,
+requires a Planr-validated effective route observation (host report, telemetry
+receipt, process exit, or local observation), recomputes the comparison from its
+stored baseline/candidate/policy identities, and gates that fresh result.
+Requested-only values and policy or binding metadata are never
+effective-treatment proof.
+
 The script enforces, in order:
 
 1. branch is `main`, worktree is clean, `CHANGELOG.md` already has a committed `## [x.y.z]` section, and the tag does not exist;
-2. the version is written into all four manifests plus `Cargo.lock`;
-3. gates: `cargo test` (includes the manifest drift guard in `tests/e2e.rs`), `npm pack --dry-run`, and `scripts/security-local.sh` (betterleaks + trivy leak gate);
-4. one mechanical commit `release x.y.z: <summary>`, an annotated `vx.y.z` tag carrying that summary, and a single push of branch plus tag.
+2. the version is written into all synchronized manifests plus `Cargo.lock`;
+3. the candidate binary validates the sanitized receipt, observed effective treatment, candidate binding, and existing Planr comparison/gate before any Git mutation;
+4. deterministic gates: `cargo test` (including manifest drift), `npm pack --dry-run`, and `scripts/security-local.sh` (betterleaks + trivy);
+5. one mechanical commit `release x.y.z: <summary>`, an annotated `vx.y.z` tag carrying that summary, and a single push of branch plus tag.
 
 Two independent gates back the script:
 
 - `cargo test` fails on every push when any manifest version drifts from `Cargo.toml`.
 - The release workflow's `Verify release versions are consistent` step refuses the tag when the tag, any manifest, or the `CHANGELOG.md` section disagree.
 
+Public CI runs `npm run verify:release-eval-gate` with a synthetic suite, fake
+binary, and temporary database. It verifies the fail-closed mechanism without a
+provider call, private benchmark, API key, or release receipt. Model-backed
+quality decisions remain a local maintainer preflight.
+
 ## Alpha Channel (Pre-Releases)
 
 Pre-release versions use the same script and pipeline with a semver pre-release suffix:
@@ -55,7 +86,7 @@ Pushing a tag `vX.Y.Z` runs `.github/workflows/release.yml`:
 1. `create-release` verifies the tag against `Cargo.toml`, all distribution manifests, and the changelog section, then creates a draft GitHub Release.
 2. `build` compiles and packages `planr-<os>-<arch>.tar.gz` for `darwin-arm64`, `darwin-x86_64`, `linux-x86_64`, and `linux-arm64`, then uploads each asset to the draft release.
 3. `finalize` downloads all uploaded assets, writes one aggregated `SHA256SUMS` covering every tarball, uploads it, and publishes the release.
-4. `npm-publish` downloads the release assets, verifies them against `SHA256SUMS`, bundles the four platform binaries into `npm/native/`, smoke-tests the wrapper, and publishes to npm via Trusted Publishing (OIDC). Runs only when the repository variable `NPM_PUBLISH_ENABLED` is `true`; requires the one-time Trusted Publisher setup described in `docs/NPM.md`.
+4. `npm-publish` downloads the release assets, verifies them against `SHA256SUMS`, bundles the four platform binaries into `npm/native/`, smoke-tests the wrapper, and publishes to npm via Trusted Publishing (OIDC). Runs only when the repository variable `NPM_PUBLISH_ENABLED` is `true`; requires the one-time Trusted Publisher setup described at <https://planr.so/docs/operations/release>.
 5. `homebrew-tap` regenerates `Formula/planr.rb` with `scripts/generate-formula.sh` and pushes it to `instructa/homebrew-tap` (installed as `brew install instructa/tap/planr`).
 
 ## Changelog
@@ -115,7 +146,6 @@ The package must include:
 
 - `npm/bin/planr.js`
 - `docs/`
-- `docs/MCP_CONTRACT.md`
 - `docs/fixtures/mcp-contract.json`
 - `plugins/`
 - `README.md`

package/docs/SWITCHLOOM_COMPATIBILITY.md

@@ -0,0 +1,46 @@
+# Switchloom Compatibility
+
+This report records Planr-side compatibility evidence for the exact public `switchloom@0.3.2` package. It is intentionally narrow: Planr verifies the package identity, repository-local declaration boundary, and its own consumption/proof semantics. It does not turn Switchloom internals, generated semantic role names, routes, doctor output, or runtime telemetry into a future contract.
+
+## Exact v0.3.2 Behavior Verified
+
+- Public npm metadata for `switchloom@0.3.2` resolved from the npm registry:
+  - `dist.integrity`: `sha512-g96AZIFKXpG1toAO+Gri1sjD8q0SxFxtRSLAcRcSVRGDCZ/dUtERepsOB+cSHHH7hUsT0jSKZYPfNqiLvfKk9Q==`
+  - `dist.shasum`: `d7d72c74ac3ecd5a3e355edd8e297284cba04403`
+  - `dist.tarball`: `https://registry.npmjs.org/switchloom/-/switchloom-0.3.2.tgz`
+- `npm pack switchloom@0.3.2 --pack-destination /private/tmp --json` returned a 9-entry package with the expected native binaries, wrapper, provenance file, README, license, and package manifest.
+- The packed tarball at `/private/tmp/switchloom-0.3.2.tgz` had SHA256 `0c04e94fc4372845edf395b3ea51139b8a4b46f34404940e06b3f4ec3ce22d20`.
+- The reviewed oracle contract expects the v0.3.2 Planr integration bundle `balanced-codex-openai@1.0.0+2.0.0`, bundle SHA256 `bf48f502080ff444ccb67bc4eeacc9391e77dbf5f0f8f277814e9abc2443e6c8`, 10 managed artifacts, 7 Codex-native roles, and 5 Planr work-type routes.
+- Repository docs now document the safe external operator flow with explicit `switchloom@0.3.2` commands, no normal-guidance `apply --yes`, and a caveat that the v0.3.2 tagged README preserves stale `0.3.1` examples.
+- The immutable live oracle used isolated source clone `/private/tmp/planr-switchloom-source.6gbzx2/source` and completed with `SWITCHLOOM_SOURCE_ROOT=/private/tmp/planr-switchloom-source.6gbzx2/source SWITCHLOOM_TARBALL=/private/tmp/switchloom-0.3.2.tgz PLANR_ORACLE_TEMP_PARENT=/private/tmp npm run verify:switchloom-cross-product`, exit 0. The live root is `/private/tmp/planr-switchloom-cross-product-Lbluca`, with oracle receipt `/private/tmp/planr-switchloom-cross-product-Lbluca/oracle-receipt.json`.
+- The retained replay of the same root and isolated source clone exited 0 and wrote `/private/tmp/planr-switchloom-cross-product-Lbluca/replay-receipt.json`. Replay first asserts the current source fingerprint matches the retained live receipt, then separately verifies the source remains unchanged during replay.
+- The live and replay receipts bind the same Switchloom source fingerprint before and after each mode: HEAD `8ff05776085d3175211e080143c513c5173abaa4`, clean status SHA256 `e3b0c442...`, inventory SHA256 `790de1be...`, file-hash SHA256 `97a26b12...`, and 303 paths. The maintainer's original sibling Switchloom worktree was not modified for this proof.
+- The successful live oracle proves exact package tarball SHA256 `0c04e94fc4372845edf395b3ea51139b8a4b46f34404940e06b3f4ec3ce22d20`, bundle SHA256 `bf48f502080ff444ccb67bc4eeacc9391e77dbf5f0f8f277814e9abc2443e6c8`, 7 profiles, 5 routes, 10 managed artifacts, Planr declaration consumption, Planr audit, uninstall and unrouted Planr behavior, no-auth fail-closed behavior, requested-only rejection, global sentinel preservation, and routing ownership.
+- The successful live oracle proves separate native maker and reviewer execution: maker `model_routing_terra_high` on `gpt-5.6-terra` with high effort, reviewer `model_routing_sol_high` on `gpt-5.6-sol` with high effort. Hidden spawn messages are intentionally opaque; the proof is exact successful parent `agent_type`, `task_name`, and `fork_turns` metadata correlated with matching direct child role rollouts, repo-local skill reads, and item-specific Planr evidence. It does not claim plaintext hidden-message recovery.
+- One malformed parent `spawn_agent` attempt in the retained live root was retained as a diagnostic and not counted as a successful spawn. The oracle still requires exactly two successful routed spawns and still rejects default, wrong-role, missing-role, or extra successful child execution.
+- A separate fresh root, `/private/tmp/planr-switchloom-cross-product-gHtZQI`, was correctly rejected: Codex claimed `spawn_agent` was unavailable and directly handled the work, producing 0 successful routed spawns. That run is negative evidence for host stochastic failure detection, not a passing compatibility run.
+
+## Stable Planr Boundary
+
+- Planr Core is provider-neutral. It reads `.planr/agents.toml`, `.planr/policy.toml`, and route-audit evidence, but does not install, invoke, compile, apply, or uninstall Switchloom output.
+- `.planr/agents.toml` profiles, routes, model names, efforts, role names, and fallback chains are opaque data to Planr. Planr may place requested routing data in pick packets, but requested-only values are not effective execution proof.
+- `--profile` records the profile a worker reports for a run. Genuine runtime proof belongs in route-audit evidence that separates requested, host-resolved, and effective dimensions.
+- Missing effective host evidence remains explicitly unavailable. Planr must not infer it from generated declarations, policy files, or worker claims.
+- External lifecycle remains external: Switchloom owns compile, apply, generated host roles, host reload requirements, and uninstall. Planr validates its own consumption with `planr agents check` and records evidence through logs/reviews.
+- Planr works without routing declarations. After an external uninstall, unrouted Planr fallback behavior remains the stable Core contract.
+
+## Not Guaranteed For Future Switchloom Work
+
+Future Switchloom work, including thread `019f8a71-5b6c-7c41-9850-7050516fcee4`, may change semantic role names, route names, doctor output, generated artifacts, runtime telemetry, and host-specific evidence shape. Planr must not contract those as stable.
+
+The stable compatibility promise is limited to Planr's boundary: consume provider-neutral declarations when present, keep requested values separate from effective evidence, reject requested-only metadata as proof, avoid owning external lifecycle, and continue operating when routing files are absent.
+
+Any future mismatch in package identity, generated artifacts, Planr declaration parsing, route-audit semantics, host evidence, source-worktree mutation, or security posture should become a new finding or fix item rather than an optimistic compatibility claim.
+
+## Verification Notes
+
+- Rust formatting, clippy, full serial cargo tests, e2e, eval-contract, and routing-ownership tests passed when run outside the sandbox where HTTP/process tests are permitted.
+- Docs reference generation, typecheck, reference verification, maintenance verification, and Node 22 production build passed. Node 26 production docs builds hung in the optimized Next build phase and were terminated; the Node 22 build is the relevant repository runtime.
+- npm package dry-run passed using a temp npm cache because the user npm cache contains root-owned files.
+- Privacy checks passed. The docs app Next.js runtime was upgraded from `16.2.10` to `16.2.11` in `apps/docs/package.json` and `pnpm-lock.yaml`; the lockfile change is limited to Next core/env/SWC and mechanically recalculated peer snapshots. `npm run security:check` passed with BetterLeaks reporting no leaks and Trivy reporting 0 vulnerabilities for both `Cargo.lock` and `pnpm-lock.yaml`.
+- The immutable source clone proof supersedes earlier retained-replay-only evidence. Earlier concurrent external mutation and missing-receipt attempts were treated as real failures and are not counted as passing evidence.