agentera 3.0.0-dev.27 → 3.0.0-dev.29

package/README.md

@@ -38,15 +38,17 @@ Preview has no side effects. The apply path is the explicit, one-way v2-to-v3
 migration described in [UPGRADE.md](../../UPGRADE.md); it does not run a native
 package installer.
 
-Retired Claude cleanup is intentionally separate:
+Native Agentera resource cleanup is intentionally separate from host support:
 
 ```bash
-npx -y agentera@next upgrade --legacy-cleanup claude --dry-run
+npx -y agentera@next upgrade --legacy-cleanup claude.agentera-skill-link --dry-run
 ```
 
-It can remove only the exact Agentera-owned legacy link. Historical transcript
-import is also explicit (`agentera report refresh --import-source claude`) and
-is excluded from default active-runtime analytics.
+It selects declared native Agentera resources only. Each removal needs a
+matching whole-resource ledger identity and fingerprint; shared Codex config
+keys require unavailable key-level evidence and remain action-required.
+Historical transcript import is also explicit (`agentera report refresh
+--import-source claude`) and is excluded from default active-runtime analytics.
 
 ## Bounded state retrieval
 

package/bundle/CHANGELOG.md

@@ -4,6 +4,20 @@
 
 ### Changed
 
+- Health audit appends now receive a CLI-owned UTC timestamp. Bounded health
+  reads and `prime` select timestamped records newest-first regardless of random
+  ID; legacy records retain deterministic date-and-ID ordering without inferred
+  chronology.
+- Removed bundled native capability descriptors and `agentera check validate descriptors`; Codex setup no longer installs descriptors or writes agent-dispatch settings, and the canonical shared skill and CLI are the only active integration seam.
+- `agentera route receipt` now requires the phase-one `semantic_capsule_sha256` as well as `request_sha256`; it fails closed when the current trigger-intent capsule differs, preventing startup from a receipt classified against stale routing authority.
+- Defined the portable routing boundary: `agentera route request` deterministically resolves bare `/agentera`, explicit capability names or aliases, and curated leading phrases to a capability; every other request remains host-owned open-ended semantic classification. `agentera route receipt` validates the host result before authorizing startup, while `agentera route evaluate` and `agentera check verify eval routing` gate implementation with the frozen offline synthetic corpus; Agentera ships no built-in model service or live benchmark.
+- Added ordinary progress, decision, and health reads plus startup handling for
+  immutable v2-compaction summaries. Summary-only history now remains explicitly
+  degraded with source provenance and caveats instead of appearing as current
+  detail. Migration preview now separates corrupt source roots from generated
+  relationship dependents, and a Git-backed lifecycle proof covers interrupted
+  retry without changing aggregate source bytes. The contract excludes
+  reconstruction, dual authority, and repair/import commands.
 - Changed the v2-to-v3 development upgrade to one full Git-backed command that converts unchanged tracked input directly into canonical entities, accepts exact partial targets on retry, validates the complete graph, and activates entity authority last. Runtime blockers are reported as post-activation action-required work without modifying the blocked resource. The optional dry-run is read-only; cross-major apply is one-way and has no staging graph, recovery journal, rollback, restore, non-Git, or partial workflow.
 - Cut ordinary project state over to one canonical writer-owned file per entity. Public records now use only bare `id` and `artifact` identity, bounded `list` and exact `get --id` reads, and typed writers discovered through `agentera state <artifact> explain`; aggregate state files and ordinal selectors remain migration or historical evidence only.
 - Split lifecycle validation orchestration from the public validation facade while preserving its import surface and validation behavior.
@@ -35,7 +49,7 @@
 
 - Added an executable bounded-retrieval authority and reserved CLI grammar for plan tasks, plans, and objective-scoped experiments, including stable and legacy identity rules, experiment `0`, opaque cursors, explicit omissions, and structured compatibility errors; retrieval execution remains staged for subsequent tasks.
 - Added one shared skill at `~/.agents/skills/agentera` plus the CLI and entity-backed project state as the active integration contract; host-native plugin, hook, agent, and package surfaces are not shipped.
-- Retained runtime lifecycle contracts only as migration evidence and for explicit `agentera upgrade --legacy-cleanup claude --dry-run|--yes`, which can remove only the ownership-proven legacy Agentera skill link and excludes user data.
+- Defined native-resource cleanup evidence for supported hosts and explicit `agentera upgrade --legacy-cleanup RESOURCE_ID --dry-run|--yes` selection. Cleanup retains only ledger-proven whole resources; Codex descriptor reports preserve shared configuration keys as report-only action-required items without durable key-level ownership.
 - Added typed artifact writes under `agentera state`: progress/decision/audit appends, decision satisfaction updates, plan create/task/status/archive lifecycle operations, schema-derived `explain`, server-assigned identifiers, exact retry replay, dry-run diffs, project locking, strict mapped-path safety, staged 10/40/50 compaction, final-byte validation, and atomic publication.
 - Added `install_track` to `prime --format json` (`app_home.install_track`) and `doctor --format json`. Values are `v2`, `v3`, `source`, and `unknown`.
 - Added the TypeScript CLI on the npm development channel (`npx -y agentera@next`) as a self-contained package whose governed isolated construction stages compiled commands, registry-owned app data, and the `.agentera-npx-bundle.json` sentinel before packing with lifecycle scripts disabled.
@@ -74,6 +88,7 @@
 
 ### Fixed
 
+- Fixed natural-language capability routing to select from the user's expressed intent and trigger metadata before capability startup; status `next_action` now remains an orientation readiness suggestion rather than a classifier for non-status requests.
 - Fixed overlapping source, build, and package verification to use isolated construction and one atomically selected `dist` + `bundle` generation; clean source no longer requires checkout output, package proof still runs from an extracted tarball, and `pnpm -C packages/cli run pack:dry-run` replaces direct checkout `npm pack`.
 - Fixed `agentera prime --context status` to report severity totals across every open TODO while keeping attention and routing detail bounded with explicit omission recovery.
 - Fixed `agentera prime --context status` to exclude resolved entity TODOs before bounded pagination, so severity counts, attention, and next-action routing reflect only open work.
@@ -118,7 +133,7 @@
 - Removed `hej`, `describe`, and `gate` from top-level `agentera --help` and dispatch; unsupported structured requests return runnable corrections to `agentera prime`, `agentera schema`, and `agentera check compact`.
 - Removed the requirement for `uv` or a git checkout on the development channel; `uvx --from git+https://github.com/jgabor/agentera@main agentera` remains the stable 2.x Python line only.
 - Removed `agentera state migrate`, `agentera state backfill`, projection repair, and automatic v1 conversion. Recognized v2 aggregate projects now have one forward mutation path: full `agentera upgrade --yes`; `state migrate entities --dry-run` remains read-only.
-- Removed host-native runtime selectors, repair actions, package manifests, plugins, hooks, agents, and Bun single-binary delivery from the v3 distribution. Migration fixtures, ownership evidence, and explicit Claude cleanup remain internal migration surfaces.
+- Removed host-native runtime selectors, repair actions, package manifests, plugins, hooks, agents, and Bun single-binary delivery from the v3 distribution. Migration fixtures, ownership evidence, and explicit native Agentera resource cleanup remain internal migration surfaces.
 
 ### Migration notes
 

package/bundle/DESIGN.md

@@ -1,18 +1,14 @@
 # Agentera
 
-Visual identity system for Agentera. Terminal-native tokens for CLI and agent-rendered Markdown; mobile UI tokens live in [`packages/mobile/DESIGN.md`](./packages/mobile/DESIGN.md).
+Visual identity system for Agentera's CLI and agent-rendered Markdown.
 
 ## Surface register
 
-One brand (Agentera), three register layers: terminal/mobile surfaces (below), brand-vs-product output registers, and suite-vs-project design authorities.
+One brand (Agentera), with brand-vs-product output registers and suite-vs-project design authorities.
 
 | Surface | Authority | Renders |
 | --- | --- | --- |
 | `terminal` | This file (`DESIGN.md`) | CLI dashboard, capability introductions, structured artifact headers in Markdown |
-| `mobile` | `packages/mobile/DESIGN.md` | Touch UI, smart bar, sidebar, chat composer, responsive layouts |
-
-Shared across surfaces: product name, capability glyphs, sharp-colleague voice.
-Not shared: box-drawing logo usage (terminal key moments only), terminal severity arrows in mobile UI, Tailwind touch targets in terminal output.
 
 ## Output Registers
 
@@ -65,7 +61,7 @@ Governs the **host repository's own product** — web UI, the user's coding-agen
 - Design in a host project writes **project** `DESIGN.md` only; never merge suite design sources into it.
 - Status reads project design for **status metadata** (exists, stale, missing) — not to style suite chrome.
 - When both authorities apply in one session, suite chrome follows suite sources; the host product follows project `DESIGN.md`.
-- In the Agentera repository, root `DESIGN.md` is suite terminal dogfood plus brand register; `packages/mobile/DESIGN.md` is the mobile surface register.
+- In the Agentera repository, root `DESIGN.md` is the suite terminal dogfood and brand register.
 
 ## Philosophy
 

package/bundle/README.md

@@ -41,19 +41,20 @@ skill at `~/.agents/skills/agentera` plus the Agentera CLI. Normal `upgrade`
 previews and applies only app/project migration; it has no current-runtime
 selector and creates no native plugin, hook, agent, command, descriptor, or
 marketplace file. See [UPGRADE.md](./UPGRADE.md) for the distinct one-way v2
-migration and explicit retired Claude cleanup route:
-`agentera upgrade --legacy-cleanup claude --dry-run|--yes`.
+migration and explicit native-resource cleanup route:
+`agentera upgrade --legacy-cleanup RESOURCE_ID --dry-run|--yes`.
 
 `doctor` reports read-only app, project-state, shared-skill, and CLI evidence.
 `prime`, status, and project-integration output use the app/project recommendation
 and shared-skill diagnosis to select the next action.
 
-Claude Code is retired from active support. Its only lifecycle command is a
-separate, explicit cleanup of the exact Agentera-owned legacy skill link:
+Supported hosts continue to use the canonical shared skill and CLI. Cleanup
+selects a native Agentera resource, never a host. Claude Code is retired from
+active support; its legacy link remains one selectable resource:
 
 ```bash
-npx -y agentera@next upgrade --legacy-cleanup claude --dry-run
-npx -y agentera@next upgrade --legacy-cleanup claude --yes
+npx -y agentera@next upgrade --legacy-cleanup claude.agentera-skill-link --dry-run
+npx -y agentera@next upgrade --legacy-cleanup claude.agentera-skill-link --yes
 ```
 
 Historical Claude transcripts are excluded by default. A local import requires
@@ -117,13 +118,11 @@ The intentional singleton project state is:
 | ♾ | profile | Reusable decision profile |
 | ⎈ | orchestrate | Autonomous plan execution with evaluation |
 
-## Monorepo
+## Package
 
 | Package | Role |
 | --- | --- |
 | `packages/cli` (`agentera`) | Primary TypeScript CLI and bundled runtime data |
-| `packages/web` (`@agentera/web`) | Marketing and Starlight documentation site |
-| `packages/mobile` (`@agentera/mobile`) | Docs-only mobile product stub |
 
 Contributor commands and repository rules live in [AGENTS.md](./AGENTS.md).
 Migration and recovery details live in [UPGRADE.md](./UPGRADE.md).
@@ -132,7 +131,6 @@ Migration and recovery details live in [UPGRADE.md](./UPGRADE.md).
 pnpm -C packages/cli test
 pnpm -C packages/cli run typecheck
 pnpm -C packages/cli build
-vp run web:check
 ```
 
 License: [Apache-2.0](./LICENSE) · Author: Jonathan Gabor

package/bundle/UPGRADE.md

@@ -1,8 +1,8 @@
 # Upgrade and migration
 
 Agentera 3.0 uses one upgrade command for app/project migration and explicit
-retired Claude cleanup. Preview and apply are separate operations. Current
-runtime installation and repair are not upgrade operations.
+native Agentera resource cleanup. Preview and apply are separate operations.
+Current runtime installation and repair are not upgrade operations.
 
 Before the npm stable dist-tag promotion, use `agentera@next`. The stable 2.x
 channel remains `agentera@latest` until that promotion; upgrade does not publish
@@ -24,8 +24,8 @@ runtime package managers, authentication, enablement, or trust operations.
 
 Passing `--runtime` fails before mutation. Remove `--runtime`, ensure the runtime
 can read `~/.agents/skills/agentera`, and invoke the CLI directly. The supported
-v2 migration and Claude cleanup routes below are separate from normal active
-integration.
+v2 migration and native Agentera resource cleanup routes below are separate from
+normal active integration.
 
 ## Preview and apply
 
@@ -55,20 +55,30 @@ Retries re-observe the current app/project state. Completed migration work
 converges to no change; interrupted v2 migration continues through the same full
 apply command.
 
-## Retired Claude cleanup
+## Native Agentera resource cleanup
 
-Claude cleanup is a distinct historical route, not a current-runtime selection:
+Cleanup is a distinct resource route, not a host selection. Codex, Cursor,
+OpenCode, and Copilot remain supported through the canonical shared skill and
+CLI. Accepted smoke evidence records that Codex and Cursor loaded Agentera's
+skill instructions, OpenCode listed the canonical skill, and Copilot's listed
+canonical skill is intentionally disabled.
+
+Use `agentera upgrade --legacy-cleanup RESOURCE_ID --dry-run|--yes` with one
+declared native Agentera resource ID.
 
 ```bash
-npx -y agentera@next upgrade --legacy-cleanup claude --dry-run
-npx -y agentera@next upgrade --legacy-cleanup claude --yes
+npx -y agentera@next upgrade --legacy-cleanup claude.agentera-skill-link --dry-run
+npx -y agentera@next upgrade --legacy-cleanup claude.agentera-skill-link --yes
 ```
 
-Cleanup is limited to the exact Agentera-owned legacy skill link recorded by the
-ownership journal. It never removes Claude projects, transcripts, settings,
-credentials, caches, or other user data. Ambiguous or unowned resources remain
-blocked. Preview is read-only; apply is idempotent and can be retried with the
-same explicit selection.
+The contract also inventories retired Codex descriptor files. Each file needs a
+matching whole-resource ledger identity and fingerprint before it can be
+removed. Codex descriptor previews report each shared configuration key as
+`action_required` without adding it to the selected resource's apply work.
+Agentera has no durable key-level ownership proof, so matching values, markers,
+names, or whole file contents never authorize a shared `config.toml` mutation.
+Preview is read-only; approved apply is idempotent and preserves ambiguous or
+unowned resources.
 
 Historical transcript import is independent of cleanup. Default extraction and
 analytics do not read Claude history. Import requires explicit local consent:
@@ -112,6 +122,39 @@ Forward migration is one-way. Returning to the Python 2.x line is unsupported,
 and cross-major apply has no rollback, restore, non-Git, or partial workflow.
 If apply is interrupted, rerun the same full apply command.
 
+### Compacted v2 summaries
+
+Entity-cutover publication for valid v2 compaction output is implemented for
+`progress`, `decisions`, and `health`. Each valid summary becomes one immutable,
+read-only canonical
+`progress_summary`, `decision_summary`, or `health_summary` entity. The entity
+requires `summary`, preserves every source-retained field except forbidden
+identity aliases, and records the source path plus source-record SHA-256.
+
+Ordinary summary readers and startup projection are implemented. Reads report
+`detail_availability: summary`, `compatibility: degraded`, record-level source
+provenance, and applicable caveats; startup presents summary-only history as
+degraded history rather than current detail. Full records retain their existing
+temporal order; the degraded-summary segment follows in deterministic canonical-ID
+order and makes no chronology claim. Retained decision-summary satisfaction is
+inline and read-only, may be absent, and never creates a standalone satisfaction
+ target. Preview reports independent source roots separately from generated
+ relationship dependents: `root_blockers + dependent_blockers = blockers`, and
+ each dependent names its stable `root_source_identity`. A Git-backed regression
+ copies the supported `progress`, `decisions`, and `health` sources from pinned
+ v2.7.11 compaction output; its protected experiment evidence remains unchanged
+ and excluded. It verifies preview bindings and target hashes, marker-last
+ publication and interrupted exact-target retry, canonical validation, ordinary
+ list/get reads for retained full and summary entries, human/JSON prime, and
+ repeated no-change upgrade behavior while aggregate source hashes remain stable.
+Inherited full-decision `high`, `medium`, and `low` confidence remains readable
+with a legacy caveat; newly supplied or amended confidence remains strict.
+
+Protected objective experiments, runtime-local session state, and compacted TODO
+rows that already satisfy the canonical TODO shape are outside this summary
+scope. This contract does not reconstruct Git history, normalize source records,
+create dual authority, or add a repair or import command.
+
 ## Unsupported legacy state
 
 Pending v1 Markdown state and unknown marker-absent state are not automatic
@@ -131,7 +174,7 @@ npx -y agentera@next prime --format json
 
 `upgrade --verify` without `--yes` is a read-only doctor and capability-context
 verification. With `--yes`, it runs those checks after approved migration.
-Explicit Claude cleanup with `--verify` requires `--yes`.
+Explicit native Agentera resource cleanup with `--verify` requires `--yes`.
 
 `--force` applies only where the owning migration contract explicitly permits
 replacement. It never adopts user-owned resources.
@@ -151,7 +194,8 @@ node packages/cli/dist/bin/agentera.js check validate release-metadata
 ## Mutation ownership
 
 Upgrade apply holds the required project lock before migration begins. Explicit
-Claude cleanup additionally uses its ownership journal and shared lock. Lock
-creation is atomic, and release succeeds only for the matching ownership token.
+native Agentera resource cleanup additionally uses its ownership journal and
+shared lock. Lock creation is atomic, and release succeeds only for the matching
+ownership token.
 A stale or malformed lock stops the operation; inspect the named lock file,
 remove only that file after confirming no operation owns it, then rerun.

package/bundle/fixtures/routing/hybrid-corpus.yaml

@@ -0,0 +1,154 @@
+schema_version: agentera.hybrid_routing_corpus.v3
+status: frozen
+text_provenance: All request text in this fixture is synthetic and authored for conformance testing.
+retention_policy: >-
+  This fixture may contain only synthetic or explicitly consented text. Evaluation
+  reports retain case IDs and aggregate metrics, never private request strings.
+freeze_policy: >-
+  Development and adversarial entries are the sole frozen synthetic implementation
+  corpus. Additions or expectation changes require a new schema_version and a new
+  corpus file; no hidden, sealed, or vendor-host corpus is required.
+partitions:
+  development: { status: frozen, purpose: phrase inventory and structural contract development }
+  adversarial: { status: frozen, purpose: "abstention, separator, and invalid-receipt safety" }
+
+route_cases:
+  - { id: DEV-PHRASE-STATUS, partition: development, request: "show project briefing for the checkout", expected: { phase1: deterministic_selection, tier: phrase, capability: status } }
+  - { id: DEV-PHRASE-VISION, partition: development, request: "define product direction for collaboration", expected: { phase1: deterministic_selection, tier: phrase, capability: vision } }
+  - { id: DEV-PHRASE-DISCUSS, partition: development, request: "help me decide: cache or queue", expected: { phase1: deterministic_selection, tier: phrase, capability: discuss, topic: ": cache or queue" } }
+  - { id: DEV-PHRASE-RESEARCH, partition: development, request: "study external patterns for durable jobs", expected: { phase1: deterministic_selection, tier: phrase, capability: research } }
+  - { id: DEV-PHRASE-PLAN, partition: development, request: "make an implementation plan for import safety", expected: { phase1: deterministic_selection, tier: phrase, capability: plan } }
+  - { id: DEV-PHRASE-BUILD, partition: development, request: "implement the approved plan for task one", expected: { phase1: deterministic_selection, tier: phrase, capability: build } }
+  - { id: DEV-PHRASE-OPTIMIZE, partition: development, request: "improve a measured bottleneck in startup", expected: { phase1: deterministic_selection, tier: phrase, capability: optimize } }
+  - { id: DEV-PHRASE-AUDIT, partition: development, request: "check codebase health before release", expected: { phase1: deterministic_selection, tier: phrase, capability: audit } }
+  - { id: DEV-PHRASE-DOCUMENT, partition: development, request: "refresh project documentation for setup", expected: { phase1: deterministic_selection, tier: phrase, capability: document } }
+  - { id: DEV-PHRASE-PROFILE, partition: development, request: "save a decision profile for local work", expected: { phase1: deterministic_selection, tier: phrase, capability: profile } }
+  - { id: DEV-PHRASE-DESIGN, partition: development, request: "shape the interface for review", expected: { phase1: deterministic_selection, tier: phrase, capability: design } }
+  - { id: DEV-PHRASE-ORCHESTRATE, partition: development, request: "execute the approved plan for phase two", expected: { phase1: deterministic_selection, tier: phrase, capability: orchestrate } }
+  - { id: DEV-ABSTAIN-STATUS, partition: development, request: "show project briefings", expected: { phase1: semantic_required, reason: literal_abstention, boundary: status } }
+  - { id: DEV-ABSTAIN-VISION, partition: development, request: "define our product direction", expected: { phase1: semantic_required, reason: literal_abstention, boundary: vision } }
+  - { id: DEV-ABSTAIN-DISCUSS, partition: development, request: "help us decide", expected: { phase1: semantic_required, reason: literal_abstention, boundary: discuss } }
+  - { id: DEV-ABSTAIN-RESEARCH, partition: development, request: "research patterns", expected: { phase1: semantic_required, reason: literal_abstention, boundary: research } }
+  - { id: DEV-ABSTAIN-PLAN, partition: development, request: "make implementation plan", expected: { phase1: semantic_required, reason: literal_abstention, boundary: plan } }
+  - { id: DEV-ABSTAIN-BUILD, partition: development, request: "implement approved plan", expected: { phase1: semantic_required, reason: literal_abstention, boundary: build } }
+  - { id: DEV-ABSTAIN-OPTIMIZE, partition: development, request: "optimize measured bottleneck", expected: { phase1: semantic_required, reason: literal_abstention, boundary: optimize } }
+  - { id: DEV-ABSTAIN-AUDIT, partition: development, request: "audit the codebase health", expected: { phase1: semantic_required, reason: literal_abstention, boundary: audit } }
+  - { id: DEV-ABSTAIN-DOCUMENT, partition: development, request: "update documentation", expected: { phase1: semantic_required, reason: literal_abstention, boundary: document } }
+  - { id: DEV-ABSTAIN-PROFILE, partition: development, request: "save decision profile", expected: { phase1: semantic_required, reason: literal_abstention, boundary: profile } }
+  - { id: DEV-ABSTAIN-DESIGN, partition: development, request: "design an interface", expected: { phase1: semantic_required, reason: literal_abstention, boundary: design } }
+  - { id: DEV-ABSTAIN-ORCHESTRATE, partition: development, request: "execute approved plan", expected: { phase1: semantic_required, reason: literal_abstention, boundary: orchestrate } }
+  - { id: DEV-BARE, partition: development, request: "/agentera", expected: { phase1: deterministic_selection, tier: bare, capability: status } }
+  - { id: DEV-DIRECT, partition: development, request: "/agentera plan import safety", expected: { phase1: deterministic_selection, tier: direct, capability: plan } }
+  - { id: ADV-BARE-WITH-TEXT, partition: adversarial, request: "/agentera what time is it", expected: { phase1: semantic_required, reason: nonbare_request, boundary: bare } }
+  - { id: ADV-DIRECT-PARTIAL, partition: adversarial, request: "/agentera planner import safety", expected: { phase1: semantic_required, reason: invalid_direct_name, boundary: direct } }
+  - { id: ADV-QUOTED-PHRASE, partition: adversarial, request: 'The words "help me decide" appear in this quote.', expected: { phase1: semantic_required, reason: nonleading_phrase } }
+  - { id: ADV-NEGATED-PHRASE, partition: adversarial, request: "Do not help me decide; just show alternatives.", expected: { phase1: semantic_required, reason: nonleading_phrase } }
+  - { id: ADV-PUNCTUATED-PHRASE, partition: adversarial, request: "help me decide: now", expected: { phase1: deterministic_selection, tier: phrase, capability: discuss, topic: ": now" } }
+  - { id: ADV-EMDASH-SEPARATOR, partition: adversarial, request: "help me decide—now", expected: { phase1: deterministic_selection, tier: phrase, capability: discuss, topic: "—now" } }
+  - { id: ADV-FULLWIDTH-PHRASE, partition: adversarial, request: "ＨＥＬＰ　ＭＥ　ＤＥＣＩＤＥ： cache", expected: { phase1: deterministic_selection, tier: phrase, capability: discuss, topic: "： cache" } }
+  - { id: ADV-REPEATED-WHITESPACE, partition: adversarial, request: "help\t\tme   decide\ncache", expected: { phase1: deterministic_selection, tier: phrase, capability: discuss, topic: "\ncache" } }
+  - { id: ADV-PARTIAL-PHRASE, partition: adversarial, request: "help me deciding now", expected: { phase1: semantic_required, reason: partial_token } }
+  - { id: ADV-UNSUPPORTED-PUNCTUATION, partition: adversarial, request: "help me decide! now", expected: { phase1: semantic_required, reason: unsupported_separator } }
+
+receipt_cases:
+  - id: DEV-RECEIPT-SELECT-PASS
+    partition: development
+    valid: true
+    request: "How should we divide the import work?"
+    expected_terminal: selected
+    receipt: { version: agentera.route_receipt.v1, request_sha256: c28396095a91d6b3f0f6485f8cc4a898f7d012a1d01d000653786fa869626b70, semantic_capsule_sha256: f885d882a3d08a59aac28cebbb9a3270a28096b6f411f55f99e8772c3ce7637e, outcome: select, capability: plan, compound: none }
+  - id: ADV-RECEIPT-SELECT-MISSING-CAPABILITY
+    partition: adversarial
+    valid: false
+    request: "How should we divide the import work?"
+    expected_terminal: invalid_receipt
+    error: required.capability
+    receipt: { version: agentera.route_receipt.v1, request_sha256: c28396095a91d6b3f0f6485f8cc4a898f7d012a1d01d000653786fa869626b70, semantic_capsule_sha256: f885d882a3d08a59aac28cebbb9a3270a28096b6f411f55f99e8772c3ce7637e, outcome: select, compound: none }
+  - id: DEV-RECEIPT-CLARIFY-PASS
+    partition: development
+    valid: true
+    request: "Make it better"
+    expected_terminal: clarification
+    receipt: { version: agentera.route_receipt.v1, request_sha256: d71e91121b85d9e84a5dea968dc995878667e4b631b92f8742622427a23cdaa6, semantic_capsule_sha256: f885d882a3d08a59aac28cebbb9a3270a28096b6f411f55f99e8772c3ce7637e, outcome: clarify, question: "Do you want a plan or implementation?" }
+  - id: ADV-RECEIPT-CLARIFY-MISSING-QUESTION
+    partition: adversarial
+    valid: false
+    request: "Make it better"
+    expected_terminal: invalid_receipt
+    error: required.question
+    receipt: { version: agentera.route_receipt.v1, request_sha256: d71e91121b85d9e84a5dea968dc995878667e4b631b92f8742622427a23cdaa6, semantic_capsule_sha256: f885d882a3d08a59aac28cebbb9a3270a28096b6f411f55f99e8772c3ce7637e, outcome: clarify }
+  - id: DEV-RECEIPT-NO-MATCH-PASS
+    partition: development
+    valid: true
+    request: "What time is the train?"
+    expected_terminal: status_fallback
+    receipt: { version: agentera.route_receipt.v1, request_sha256: b712acb8d881cc37a94f06c8ec9efb91f6ce24fa4e7349883dbbb36b57c5d7bc, semantic_capsule_sha256: f885d882a3d08a59aac28cebbb9a3270a28096b6f411f55f99e8772c3ce7637e, outcome: no_match }
+  - id: ADV-RECEIPT-NO-MATCH-FORBIDDEN-CAPABILITY
+    partition: adversarial
+    valid: false
+    request: "What time is the train?"
+    expected_terminal: invalid_receipt
+    error: not
+    receipt: { version: agentera.route_receipt.v1, request_sha256: b712acb8d881cc37a94f06c8ec9efb91f6ce24fa4e7349883dbbb36b57c5d7bc, semantic_capsule_sha256: f885d882a3d08a59aac28cebbb9a3270a28096b6f411f55f99e8772c3ce7637e, outcome: no_match, capability: plan }
+  - id: DEV-RECEIPT-COMPOUND-PRESERVE-PASS
+    partition: development
+    valid: true
+    request: "Plan the migration and then implement it"
+    expected_terminal: selected
+    receipt: { version: agentera.route_receipt.v1, request_sha256: f26da5835071b706a176032b263b0131817a56dcd2965f4198e57e2e23b0ac60, semantic_capsule_sha256: f885d882a3d08a59aac28cebbb9a3270a28096b6f411f55f99e8772c3ce7637e, outcome: select, capability: plan, compound: preserve, remainder_span: { start: 4, end: 40 } }
+  - id: ADV-RECEIPT-COMPOUND-INVALID
+    partition: adversarial
+    valid: false
+    request: "Plan the migration and then implement it"
+    expected_terminal: invalid_receipt
+    error: compound.enum
+    receipt: { version: agentera.route_receipt.v1, request_sha256: f26da5835071b706a176032b263b0131817a56dcd2965f4198e57e2e23b0ac60, semantic_capsule_sha256: f885d882a3d08a59aac28cebbb9a3270a28096b6f411f55f99e8772c3ce7637e, outcome: select, capability: plan, compound: clarify }
+  - id: ADV-RECEIPT-MISSING-VERSION
+    partition: adversarial
+    valid: false
+    request: "Map the migration before implementation."
+    expected_terminal: invalid_receipt
+    error: required.version
+    receipt: { request_sha256: fc8dfdefc423ea7c375669b044a01c443b48be880e0c4e769579d296ef048f74, semantic_capsule_sha256: f885d882a3d08a59aac28cebbb9a3270a28096b6f411f55f99e8772c3ce7637e, outcome: select, capability: plan, compound: none }
+  - id: ADV-RECEIPT-INVALID-DIGEST
+    partition: adversarial
+    valid: false
+    request: "Which capability should handle this?"
+    expected_terminal: invalid_receipt
+    error: request_sha256.pattern
+    receipt: { version: agentera.route_receipt.v1, request_sha256: not-a-digest, semantic_capsule_sha256: f885d882a3d08a59aac28cebbb9a3270a28096b6f411f55f99e8772c3ce7637e, outcome: select, capability: plan, compound: none }
+  - id: ADV-RECEIPT-UNKNOWN-CAPABILITY
+    partition: adversarial
+    valid: false
+    request: "Which capability should handle this?"
+    expected_terminal: invalid_receipt
+    error: binding.capability
+    receipt: { version: agentera.route_receipt.v1, request_sha256: 9516783492db2d389ec305dfea5f60d23e6d136c7cd27e236bbc29daeca427df, semantic_capsule_sha256: f885d882a3d08a59aac28cebbb9a3270a28096b6f411f55f99e8772c3ce7637e, outcome: select, capability: unknown, compound: none }
+  - id: ADV-RECEIPT-OUT-OF-BOUNDS-SPAN
+    partition: adversarial
+    valid: false
+    request: "Keep the second request deferred."
+    expected_terminal: invalid_receipt
+    error: binding.remainder_span
+    receipt: { version: agentera.route_receipt.v1, request_sha256: 8b5ea821ff9831f5d5c9a87e2b5a2eefbfbbce54032d2f1bc160ada48eb82180, semantic_capsule_sha256: f885d882a3d08a59aac28cebbb9a3270a28096b6f411f55f99e8772c3ce7637e, outcome: select, capability: plan, compound: preserve, remainder_span: { start: 0, end: 999 } }
+  - id: ADV-RECEIPT-MISSING-CAPSULE-DIGEST
+    partition: adversarial
+    valid: false
+    request: "Which capability should handle this?"
+    expected_terminal: invalid_receipt
+    error: required.semantic_capsule_sha256
+    receipt: { version: agentera.route_receipt.v1, request_sha256: 9516783492db2d389ec305dfea5f60d23e6d136c7cd27e236bbc29daeca427df, outcome: select, capability: plan, compound: none }
+  - id: ADV-RECEIPT-INVALID-CAPSULE-DIGEST
+    partition: adversarial
+    valid: false
+    request: "Which capability should handle this?"
+    expected_terminal: invalid_receipt
+    error: semantic_capsule_sha256.pattern
+    receipt: { version: agentera.route_receipt.v1, request_sha256: 9516783492db2d389ec305dfea5f60d23e6d136c7cd27e236bbc29daeca427df, semantic_capsule_sha256: not-a-digest, outcome: select, capability: plan, compound: none }
+  - id: ADV-RECEIPT-STALE-CAPSULE-DIGEST
+    partition: adversarial
+    valid: false
+    request: "Which capability should handle this?"
+    expected_terminal: invalid_receipt
+    error: binding.semantic_capsule_sha256
+    receipt: { version: agentera.route_receipt.v1, request_sha256: 9516783492db2d389ec305dfea5f60d23e6d136c7cd27e236bbc29daeca427df, semantic_capsule_sha256: "0000000000000000000000000000000000000000000000000000000000000000", outcome: select, capability: plan, compound: none }

package/bundle/references/adapters/package-registry.yaml

@@ -45,6 +45,8 @@ records:
           path: LICENSE
         - id: registry
           path: registry.json
+        - id: routing-evaluation-corpus
+          path: fixtures/routing/hybrid-corpus.yaml
       generated_files:
         - id: npx-bundle-marker
           path: .agentera-npx-bundle.json

package/bundle/references/adapters/package-surface-characterization.md

@@ -30,9 +30,8 @@ by [`docs/packaging/v3-packaging.md`](../../docs/packaging/v3-packaging.md).
 
 The self-contained npm package ships `dist/` plus `bundle/`. Bundle data
 includes the canonical `skills/` tree, required `references/`, `registry.json`,
-and package guidance. Compiled commands ship in `dist/`. The shared-skill tree
-includes its capability schemas, artifact schemas, and canonical
-`skills/agentera/agents/*.toml` descriptors.
+the frozen routing evaluation corpus, and package guidance. Compiled commands
+ship in `dist/`. The shared-skill tree includes its capability schemas and artifact schemas.
 
 The package lane's isolated package fixture invokes `npm pack --json
 --ignore-scripts` after governed construction and fails if the CLI or required

package/bundle/references/adapters/runtime-lifecycle-authority.yaml

@@ -3,7 +3,7 @@ status: migration_only_authority
 decision: 92
 operation_contract: references/adapters/runtime-lifecycle-operation-contract.yaml
 adapter_contract: references/adapters/runtime-lifecycle-adapters.yaml
-retired_cleanup_contract: references/adapters/runtime-retired-resources.yaml
+native_resource_cleanup_contract: references/adapters/runtime-retired-resources.yaml
 canonical_skill:
   path: ~/.agents/skills/agentera
   required_for_support_floor: true
@@ -52,11 +52,10 @@ support_floor:
     not_applicable_scope: unobserved_conditional_surface_only
   unmet_blocks_release: true
 active_runtimes: []
-retired_runtime_inputs:
+historical_inputs:
   - id: claude
     purposes:
       - consent_gated_historical_import
-      - owned_legacy_resource_cleanup
 migration_aliases:
   cursor-agent:
     runtime_id: cursor

package/bundle/references/adapters/runtime-retired-resources.yaml

@@ -1,25 +1,58 @@
-schema_version: agentera.retiredRuntimeResources.v1
-status: retired_migration_contract
-decision: 92
+schema_version: agentera.nativeResourceCleanup.v1
+status: resource_retirement_contract
+decision: nksvqmnevm
 authority: references/adapters/runtime-lifecycle-authority.yaml
 operation_contract: references/adapters/runtime-lifecycle-operation-contract.yaml
 policy:
-  active_inventory_exposure: forbidden
+  host_inventory_exposure: evidence_only
+  selection: native_agentera_resource_only
   preview: strictly_read_only
   apply_requires: explicit_approval
-  ownership: matching_whole_resource_legacy_ledger_identity_and_fingerprint
+  ownership: matching_whole_resource_ledger_identity_and_fingerprint
+  shared_configuration: action_required_without_key_level_ownership
+  forbidden_ownership_evidence:
+    - value_equality
+    - managed_marker
+    - resource_name
+    - file_equality
   unsupported_platform_result: action_required
-retired_runtimes:
+accepted_host_evidence:
+  - host: codex
+    state: supported
+    proof: Codex loaded Agentera's specific canonical skill instructions and bootstrap command.
+  - host: cursor
+    state: supported
+    proof: Cursor loaded Agentera's specific canonical skill instructions and bootstrap command.
+  - host: opencode
+    state: supported
+    proof: OpenCode's native CLI listed /home/jgabor/.agents/skills/agentera/SKILL.md.
+  - host: copilot
+    state: supported_disabled
+    proof: Copilot's native CLI listed the canonical personal-agents skill; its disabled state is intentional.
+hosts:
+  - id: codex
+    display_name: Codex
+    support_status: supported
+  - id: cursor
+    display_name: Cursor
+    support_status: supported
+  - id: opencode
+    display_name: OpenCode
+    support_status: supported
+  - id: copilot
+    display_name: Copilot
+    support_status: supported_disabled
   - id: claude
     display_name: Claude Code historical migration
-    active_runtime: false
-    source_product: claude-code
-    resources:
-      - id: claude.agentera-skill-link
-        kind: symlink
-        intent: remove
-        destination: "{home}/.claude/skills/agentera"
-        ledger_status: legacy
+    support_status: retired_historical
+resources:
+  - id: claude.agentera-skill-link
+    host: claude
+    kind: symlink
+    intent: remove
+    destination: "{home}/.claude/skills/agentera"
+    ledger_status: legacy
+    durable_proof: matching whole-resource legacy ledger identity and fingerprint
     never_touch:
       - "{home}/.claude/projects"
       - "{home}/.claude/statsig"
@@ -31,3 +64,34 @@ retired_runtimes:
       - "{home}/.claude/conversations"
       - "{home}/.claude/credentials"
     safety_note: Only the declared Agentera skill symlink may be removed, and only when a matching legacy ownership ledger still binds its identity and target fingerprint. Transcript, settings, credential, conversation, stats, cache, and ambiguous paths are never cleanup targets.
+  - id: codex.agent-descriptor
+    host: codex
+    kind: file
+    intent: remove
+    destination: "{home}/.codex/agents/{descriptor}.toml"
+    descriptors: [status, vision, discuss, research, plan, build, optimize, audit, document, profile, design, orchestrate]
+    ledger_status: managed
+    durable_proof: matching whole-resource ledger identity and fingerprint for each declared descriptor file
+    safety_note: Each descriptor is an independently owned file. A managed marker, descriptor name, or matching content never establishes ownership.
+configuration_inventory:
+  - id: codex.config.shell_environment_policy.set.AGENTERA_HOME
+    host: codex
+    destination: "{home}/.codex/config.toml"
+    key: shell_environment_policy.set.AGENTERA_HOME
+    durable_proof: key-level ownership ledger identity and fingerprint
+    ownership_available: false
+    result_without_proof: action_required
+  - id: codex.config.agents.max_depth
+    host: codex
+    destination: "{home}/.codex/config.toml"
+    key: agents.max_depth
+    durable_proof: key-level ownership ledger identity and fingerprint
+    ownership_available: false
+    result_without_proof: action_required
+  - id: codex.config.features.multi_agent_v2
+    host: codex
+    destination: "{home}/.codex/config.toml"
+    key: features.multi_agent_v2
+    durable_proof: key-level ownership ledger identity and fingerprint
+    ownership_available: false
+    result_without_proof: action_required

package/bundle/references/analysis/benchmark.md

@@ -23,16 +23,9 @@ contract validators, and runtime smoke checks.
 | --- | --- | --- | --- |
 | Startup state benchmark | `mage bench:startupState` | Measures how often Agentera CLI state reads are followed by raw artifact access during startup/state gathering. | Manual only; forbidden in normal CI. |
 
-Verification optimization uses a separate retained baseline rather than this
-runtime-history benchmark. The 2026-07-20 source and pre-commit samples,
-production-scale ownership map, and unresolved worker/lane criteria live in
-[`verification-baseline-2026-07-20.yaml`](./verification-baseline-2026-07-20.yaml).
-That baseline remains measurement authority. Current test ownership, independent
-owner commands, mixed-file separation markers, conservative routing, and named
-execution-policy compositions live in
+Verification ownership, independent owner commands, mixed-file separation
+markers, conservative routing, and named execution-policy compositions live in
 [`verification-policy.yaml`](./verification-policy.yaml).
-Losslessly compressed raw reports live beside a dependency-free recomputation
-command under `references/analysis/evidence/verification-baseline-2026-07-20/`.
 
 The startup benchmark is an optimization signal for Decision 51 and Decision 52.
 It does not implement a startup state envelope or change runtime behavior.