@bjoernrochel/sevro 0.1.0-rc.8 → 1.1.0

package/docs/evidence/runtime-startup-30/before.json

@@ -1,403 +0,0 @@
-{
-  "format": "sevro.runtime-startup-benchmark.v1",
-  "sourceRoot": "/Users/bjro/Sources/sevro",
-  "platform": "darwin",
-  "arch": "arm64",
-  "bun": "1.3.13",
-  "codex": "codex-cli 0.162.1",
-  "case": "synthetic-plugin-response",
-  "model": "synthetic-candidate / synthetic-semantic",
-  "effort": "low",
-  "seed": {
-    "entries": 2049,
-    "bytes": 33554432
-  },
-  "repetitions": 3,
-  "conditions": "Fresh role homes each invocation; first verified snapshot cold, later repetitions warm; OS filesystem caches uncontrolled; no live API/model calls",
-  "rows": [
-    {
-      "repetition": 0,
-      "role": "candidate",
-      "phase": "configuration",
-      "milliseconds": 261.92554200000006,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "candidate",
-      "phase": "runtime.candidate",
-      "milliseconds": 1969.3474580000002,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "candidate",
-      "phase": "plugin-command",
-      "milliseconds": 300.13179200000013,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "candidate",
-      "phase": "plugin-command",
-      "milliseconds": 81.15104199999996,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "candidate",
-      "phase": "installation-assets",
-      "files": [
-        "cache"
-      ],
-      "configurationContainsPrivateHome": true,
-      "configurationContainsWorkspace": true
-    },
-    {
-      "repetition": 1,
-      "role": "candidate",
-      "phase": "plugin-install",
-      "milliseconds": 385.09974999999986,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "candidate",
-      "phase": "runtime.hooks",
-      "milliseconds": 1225.7079159999994,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "candidate",
-      "phase": "sandbox-probe",
-      "milliseconds": 5528.486166999999,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "candidate",
-      "phase": "sandbox-probe",
-      "milliseconds": 5409.168874999999,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "candidate",
-      "phase": "participant-execution",
-      "milliseconds": 27.37004100000013,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "candidate",
-      "phase": "candidate-total",
-      "milliseconds": 14924.6165,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "semantic",
-      "phase": "runtime.semantic",
-      "milliseconds": 1174.1918750000004,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "semantic",
-      "phase": "plugin-install",
-      "milliseconds": 0.014666000002762303,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "semantic",
-      "phase": "runtime.hooks",
-      "milliseconds": 1104.8465419999993,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "semantic",
-      "phase": "sandbox-probe",
-      "milliseconds": 5485.405999999999,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "semantic",
-      "phase": "sandbox-probe",
-      "milliseconds": 5369.393208999998,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "semantic",
-      "phase": "participant-execution",
-      "milliseconds": 27.99250000000029,
-      "status": "completed"
-    },
-    {
-      "repetition": 1,
-      "role": "semantic",
-      "phase": "grading",
-      "milliseconds": 13494.667042000001,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "candidate",
-      "phase": "runtime.candidate",
-      "milliseconds": 1357.1145419999993,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "candidate",
-      "phase": "plugin-command",
-      "milliseconds": 72.52966600000218,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "candidate",
-      "phase": "plugin-command",
-      "milliseconds": 67.09337500000038,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "candidate",
-      "phase": "installation-assets",
-      "files": [
-        "cache"
-      ],
-      "configurationContainsPrivateHome": true,
-      "configurationContainsWorkspace": true
-    },
-    {
-      "repetition": 2,
-      "role": "candidate",
-      "phase": "plugin-install",
-      "milliseconds": 141.13416599999982,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "candidate",
-      "phase": "runtime.hooks",
-      "milliseconds": 1464.9581660000003,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "candidate",
-      "phase": "sandbox-probe",
-      "milliseconds": 5689.016333,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "candidate",
-      "phase": "sandbox-probe",
-      "milliseconds": 5342.566417000002,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "candidate",
-      "phase": "participant-execution",
-      "milliseconds": 28.610333000004175,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "candidate",
-      "phase": "candidate-total",
-      "milliseconds": 14369.195708,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "semantic",
-      "phase": "runtime.semantic",
-      "milliseconds": 1235.6402080000043,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "semantic",
-      "phase": "plugin-install",
-      "milliseconds": 0.014084000002185348,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "semantic",
-      "phase": "runtime.hooks",
-      "milliseconds": 1087.1219169999968,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "semantic",
-      "phase": "sandbox-probe",
-      "milliseconds": 5409.527834,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "semantic",
-      "phase": "sandbox-probe",
-      "milliseconds": 5393.348124999997,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "semantic",
-      "phase": "participant-execution",
-      "milliseconds": 44.382833999996365,
-      "status": "completed"
-    },
-    {
-      "repetition": 2,
-      "role": "semantic",
-      "phase": "grading",
-      "milliseconds": 13533.550041999995,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "candidate",
-      "phase": "runtime.candidate",
-      "milliseconds": 1273.4362919999985,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "candidate",
-      "phase": "plugin-command",
-      "milliseconds": 75.75125000000116,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "candidate",
-      "phase": "plugin-command",
-      "milliseconds": 65.14912499999627,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "candidate",
-      "phase": "installation-assets",
-      "files": [
-        "cache"
-      ],
-      "configurationContainsPrivateHome": true,
-      "configurationContainsWorkspace": true
-    },
-    {
-      "repetition": 3,
-      "role": "candidate",
-      "phase": "plugin-install",
-      "milliseconds": 143.153999999995,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "candidate",
-      "phase": "runtime.hooks",
-      "milliseconds": 1234.849000000002,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "candidate",
-      "phase": "sandbox-probe",
-      "milliseconds": 5916.286457999995,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "candidate",
-      "phase": "sandbox-probe",
-      "milliseconds": 5706.173332999999,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "candidate",
-      "phase": "participant-execution",
-      "milliseconds": 38.983124999998836,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "candidate",
-      "phase": "candidate-total",
-      "milliseconds": 14666.299250000004,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "semantic",
-      "phase": "runtime.semantic",
-      "milliseconds": 2261.5522090000013,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "semantic",
-      "phase": "plugin-install",
-      "milliseconds": 0.016417000006185845,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "semantic",
-      "phase": "runtime.hooks",
-      "milliseconds": 1363.224583999996,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "semantic",
-      "phase": "sandbox-probe",
-      "milliseconds": 5592.143207999994,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "semantic",
-      "phase": "sandbox-probe",
-      "milliseconds": 5439.415540999995,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "semantic",
-      "phase": "participant-execution",
-      "milliseconds": 27.27187499999127,
-      "status": "completed"
-    },
-    {
-      "repetition": 3,
-      "role": "semantic",
-      "phase": "grading",
-      "milliseconds": 15030.493917,
-      "status": "completed"
-    },
-    {
-      "repetition": 4,
-      "role": "semantic",
-      "phase": "cow-copy",
-      "milliseconds": 1.0108749999926658,
-      "status": "completed"
-    },
-    {
-      "phase": "cow-isolation",
-      "sourceUnchanged": true
-    }
-  ]
-}

package/docs/evidence/runtime-startup-30/consumer-smoke.json

@@ -1,63 +0,0 @@
-{
-  "format": "sevro.consumer-smoke.v1",
-  "date": "2026-10-11",
-  "consumer": {
-    "repository": "https://github.com/BjRo/darrow",
-    "revision": "34606ad9e1952b7f4e9c56befa446c18e1a2eb5d",
-    "trackedChanges": false
-  },
-  "environment": {
-    "platform": "darwin",
-    "arch": "arm64",
-    "bun": "1.3.13",
-    "codex": "0.162.1",
-    "candidateModel": "gpt-6-luna",
-    "candidateEffort": "medium",
-    "semanticModel": "gpt-6-luna",
-    "semanticEffort": "medium"
-  },
-  "sampling": {
-    "trials": 1,
-    "jobs": 1,
-    "threshold": 1
-  },
-  "runs": [
-    {
-      "runner": "unchanged c205482b25d4d52a395c70434f2b392f6acfb279",
-      "case": "create-commit-conventional-format",
-      "execution": "failed",
-      "task": "not_assessed",
-      "activation": "unavailable",
-      "participantReached": false,
-      "diagnostic": "First sandbox preflight exceeded its 10-second deadline."
-    },
-    {
-      "runner": "issue-30 candidate",
-      "case": "create-commit-conventional-format",
-      "execution": "completed",
-      "grading": "completed",
-      "task": "failed",
-      "shellChecksPassed": 3,
-      "activation": "unavailable",
-      "limitation": "Implicit repository fixture omitted plugin manifests required by its backend launcher. Candidate correctly refused to create the requested commit; head-change assertion failed."
-    },
-    {
-      "runner": "issue-30 candidate",
-      "case": "tdd-explicit-invocation",
-      "execution": "completed",
-      "grading": "completed",
-      "task": "passed",
-      "shellCheck": "passed",
-      "semanticCheck": "passed",
-      "activation": "passed",
-      "activationCompleteness": "complete",
-      "activationEvidence": "Native Codex explicit-invocation receipt"
-    }
-  ],
-  "limits": [
-    "Only one authenticated trial per listed run.",
-    "Different cases are not a matched live performance comparison.",
-    "No live API/model latency saving is inferred.",
-    "Private transcripts, prompts, tool arguments, and credentials are omitted."
-  ]
-}

package/docs/evidence/runtime-startup-30/full-policy-diagnostic.jsonl

@@ -1,3 +0,0 @@
-{"phase":"sandbox-probe","durationMs":10649.106041000001,"code":0}
-{"phase":"sandbox-probe","durationMs":10690.409208999998,"code":0}
-{"phase":"participant","status":"withheld-diagnostic-control"}

package/docs/evidence/runtime-startup-30/minimal-policy-diagnostic.jsonl

@@ -1,3 +0,0 @@
-{"phase":"sandbox-probe","durationMs":5372.77075,"code":0}
-{"phase":"sandbox-probe","durationMs":5681.134667,"code":0}
-{"phase":"participant","status":"withheld-diagnostic-control"}

package/docs/evidence/runtime-startup-30/plugin-template-assessment.json

@@ -1,20 +0,0 @@
-{
-  "codex": "codex-cli 0.162.1",
-  "registered": {
-    "code": 0,
-    "out": "{\n  \"marketplaceName\": \"sevro-assessment\",\n  \"installedRoot\": \"<assessment>/market\",\n  \"alreadyAdded\": false\n}\n",
-    "err": ""
-  },
-  "installed": {
-    "code": 0,
-    "out": "{\n  \"pluginId\": \"probe@sevro-assessment\",\n  \"name\": \"probe\",\n  \"marketplaceName\": \"sevro-assessment\",\n  \"version\": \"1.0.0\",\n  \"installedPath\": \"<assessment>/home/plugins/cache/sevro-assessment/probe/1.0.0\",\n  \"authPolicy\": \"ON_INSTALL\"\n}\n",
-    "err": ""
-  },
-  "configuration": "[marketplaces.sevro-assessment]\nsource_type = \"local\"\nsource = \"<assessment>/market\"\n\n[plugins.\"probe@sevro-assessment\"]\nenabled = true\n",
-  "cacheOnlyFreshHomeList": {
-    "code": 0,
-    "out": "{\n  \"installed\": [],\n  \"available\": []\n}\n",
-    "err": ""
-  },
-  "conditions": "Local synthetic plugin; fresh homes without credentials; installed files copied to a second home; no registration copied"
-}

package/docs/evidence/runtime-startup-30/seedless-timeout.jsonl

@@ -1,2 +0,0 @@
-{"phase":"sandbox-probe","durationMs":10004.197417000001,"error":"Codex run timed out"}
-{"phase":"host-failure","error":"Codex run timed out"}

package/docs/evidence.md

@@ -1,17 +0,0 @@
-# Historical validation evidence
-
-These records preserve specific observations and limits. They are not current
-public contracts, fresh acceptance runs, or proof of broader platform support.
-Keep their observations intact:
-
-- [Cache ownership](cache-ownership-validation.md)
-- [Claude continuation](claude-continuation-validation.md)
-- [Concurrency](concurrency-validation.md)
-- [Configuration roots](configuration-root-validation.md)
-- [Fixture cleanup](fixture-cleanup-validation.md)
-
-The [first engine slice](engine-slice.md) also records bounded implementation
-context. [Current contracts](contracts.md) and [architecture](architecture.md)
-describe present interfaces. Coverage discovery belongs to [issue #1](https://github.com/BjRo/sevro/issues/1);
-targeted prototypes do not prove full-suite coverage.
-Return to the [hub](README.md).

package/docs/fixture-cleanup-validation.md

@@ -1,73 +0,0 @@
-# Permission-locked fixture cleanup
-
-These historical observations predate the current
-[workspace retention policy](results-v1.md).
-
-The Darrow extraction comparison exposed a cleanup difference: its legacy
-fixture destroyer removes permission-locked directories, while Sevro retained
-them after a completed trial. Sevro now restores owner access inside completed
-candidate workspaces when needed. It clears their contents after trial evidence
-is retained, keeps empty reservations until active peers drain, and then removes
-the completed roots. Directory traversal uses link metadata and skips symbolic
-links; external targets retain their permissions and contents.
-
-## Public CLI regression slices
-
-The public seam is `sevro run --case-file ... --adapter-module ...`, as documented
-in [Development CLI](development-cli.md). Each controlled adapter uses real
-filesystem permissions and returns its workspace path as a bounded observation.
-The test reads retained public evidence and verifies that the workspace is gone.
-A preliminary internal-engine test was diagnostic only; it is not part of this
-TDD trace and was removed before implementation.
-
-Red — `bun test tests/cli.test.ts --test-name-pattern 'CLI removes a permission-locked candidate directory'`: completed evidence existed, but the mode-000 child directory kept the workspace present.
-
-Green — `bun test tests/cli.test.ts --test-name-pattern 'CLI removes a permission-locked candidate directory'`: the workspace was removed and retained evidence still agreed with the CLI result.
-
-Red — `bun test tests/cli.test.ts --test-name-pattern 'permission-locked candidate directory \(root\)'`: a mode-000 workspace root remained present after completion.
-
-Green — `bun test tests/cli.test.ts --test-name-pattern 'permission-locked candidate directory \(root\)'`: the workspace root was removed after evidence retention.
-
-Red — `bun test tests/cli.test.ts --test-name-pattern 'permission-locked candidate directory \(readable root\)'`: the readable mode-500 root lacked write access and remained present.
-
-Green — `bun test tests/cli.test.ts --test-name-pattern 'permission-locked candidate directory \(readable root\)'`: restoring owner write access allowed cleanup; the external link target's mode and bytes were unchanged.
-
-Each final example also links to an external directory with a read-only file.
-All three check that its directory mode, file mode, and file contents stay intact.
-These are deterministic filesystem and lifecycle checks, with no live model call.
-
-## Final source gates
-
-`bun test` passed all 243 tests and 1399 assertions across 38 files in 93.83
-seconds. The gate includes parallel admission, peer isolation, cancellation,
-failed persistence, extension lifecycle, and generated/repository fixture tests.
-`bun run typecheck` and `bun run format:check` pass.
-The full log and subsequent installed-archive checks are retained under
-`/Users/bjro/.darrow/issue95-fixture-cleanup/`. The tests ran on macOS with Bun
-1.3.13; they do not establish another platform or native model route.
-
-## Canonical workspace follow-up
-
-Darrow's private fixture builder also checked that its returned path was
-canonical. An initial diagnostic assertion in the cleanup examples exposed
-Sevro's logical temporary-directory alias; those diagnostic additions were
-removed before the isolated regression. The public canonical-workspace test
-records the operating system's `realpath` through a controlled host and compares
-it with the received workspace in retained evidence. The full source gate above
-predates this follow-up.
-
-The public CLI contract was clarified before implementation. Candidate and
-semantic workspace allocations now resolve the new directory through `realpath`
-before reservation, preparation, or host execution.
-
-Red — `bun test tests/cli.test.ts --test-name-pattern 'CLI supplies a canonical candidate workspace'`:
-exit `1`; the received `/var/...` path differed from the operating system's
-`/private/var/...` path. One test failed with four assertions in 222 milliseconds.
-
-Green — `bun test tests/cli.test.ts --test-name-pattern 'CLI supplies a canonical candidate workspace'`:
-exit `0`; one test and four assertions passed in 228 milliseconds after the fix.
-
-The final `bun test` gate passed 244 tests and 1403 assertions across 38 files in
-94.77 seconds. Typecheck and formatting pass. The source log is retained at
-`/Users/bjro/.darrow/issue95-fixture-mounting/sevro-full-gate.log`. These remain
-deterministic macOS/Bun checks, without a live model or additional platform claim.