@bjoernrochel/sevro 0.1.0-rc.13 → 0.1.0-rc.15

package/CONTRIBUTING.md

@@ -76,7 +76,9 @@ locked dependencies. This runs inventory, schema, formatting, lint, typing and
 documentation checks; it does not replace full acceptance. CI retains machine-readable coverage
 reports under `.quality/` and exposes the stable `TypeScript quality` status.
 The complete command's `static`, `docs`, `tests` and `package` phases run as
-concurrent CI jobs. After frozen installation, use
+concurrent CI jobs. CI divides the tests among four duration-balanced jobs and
+requires one combined coverage gate; every test and both 95% thresholds remain
+required. Superseded runs for the same pull request are cancelled. After frozen installation, use
 `bun run check:typescript --phase <name>` to run one phase locally; it does not
 replace acceptance across all four. See the [phase inventory](docs/typescript-quality.md).
 

package/docs/codex-host.md

@@ -20,75 +20,13 @@ The bounded JSONL stream is retained per trial as the private
 `sevro.codex.events` host artifact. Its file URL and digest appear in trial
 evidence and are available to extension grading; the stream bytes stay out of
 the run JSON.
-The host also retains a bounded `sevro.codex.skill-reads` observation. It
-records the first verified mounted skill and ordered skill names, without
-commands or skill bodies. A `cat` or `sed -n` attempt counts only when its path
-resolves to a mounted skill or a skill below an installed plugin root verified
-by Codex's installation receipt. Missing targets outside a mounted skill
-directory, listings, and other harmless mentions of `SKILL.md` do not make the
-observation partial. A missing `SKILL.md` target does not count as a read just
-because its parent directory belongs to a mounted skill; an existing mounted
-target that fails or produces incomplete bytes remains partial. A completed direct
-`cat` of one mounted `SKILL.md`, alone or alongside literal documentation
-paths, counts only when the command output contains that file's exact body.
-Batched reads naming more than 64 paths remain partial, as do failed,
-malformed, or incomplete recognized reads. Direct
-`sed -n` pages count after their verified line ranges cover the whole body. An
-exact `cat` wrapped by `lean-ctx -c` is accepted only when its reported output
-still contains the full body; a compressed summary cannot prove the read.
-The same exact-body check accepts a literal read followed by one literal `rg`
-command, separated by a semicolon or newline. It also accepts a single-file
-literal `cat` of the skill followed by one or more literal `cat` reads of
-non-skill files, then one literal `rg` command, with the same separators. For
-example:
+Skill activation uses the common `sevro.host.skill-activations` observation
+from passive hooks in the request's private Codex home. The collector matches
+prepared skill bodies in returned tool content without interpreting shell
+syntax or recovering command output from native sessions. See
+[skill activation evidence](native-hosts.md#skill-activation-evidence) for the
+scope, limits, privacy boundaries, and incomplete collection states.
 
-```sh
-cat .agents/skills/darrow-guide/SKILL.md; cat docs/specs/repository-guide.md; rg -n -i 'offline|\bsla\b|service.level|guarantee|deployment' --glob '*.md' --glob '!docs/research/**' --glob '!**/SKILL.md' .
-```
-
-This sequence uses the shared stream and native read check. Quoted separators
-remain part of their literal operand. The ordered file bodies must match the
-retained output, so documentation or search output cannot replace an altered
-or incomplete skill read. Literal `cat` commands may read multiple mounted
-skills and documentation, before or after skills, with or without a terminal
-search. Multiple literal terminal `rg` commands are accepted within the command
-bound. Each verified skill receives its own ordered receipt. Documentation
-must resolve within the workspace or a receipt-bound installed plugin root;
-each file is bounded to 1 MiB. Aliases of mounted skills without a literal
-`SKILL.md` operand remain unsupported.
-The 64-operand bound applies across all reads in the sequence. Shell expansions,
-including unquoted glob and tilde operands, are unsupported in this form.
-
-The bounded composed-read grammar also accepts `unset` with literal variable
-names, `pwd` or `pwd -P`, `git rev-parse --show-toplevel` (optionally with
-`-C "$PWD"`), `printenv` with literal variable names, and `rg --files` with
-literal arguments before the reads. Prefix `printenv` requires the reads to
-end the command, so environment output cannot replace missing read bytes.
-Literal `printenv` commands may follow reads without prefix `printenv`.
-The fixed pair `repo=$(git -C "$PWD" rev-parse --show-toplevel)` and
-`cd "$repo" && pwd -P` is supported only with absolute read operands. Other
-assignments, substitutions, directory changes, or control flow remain
-unsupported. Prefix and environment output cannot supply skill frontmatter;
-ambiguous repeated output cannot establish an attributable read.
-
-The check also accepts a chain of literal
-`cat` fallbacks with `2>/dev/null` and `||`, ending in `true` followed by a newline
-and one literal `rg` discovery command. A fallback chain must resolve to one
-canonical file across all its read operands; absent alternate targets do not
-invalidate the read. Each fallback `cat` names one literal file. Multiple
-existing targets, including unmounted copies,
-cannot establish an attributable read. The total read operands remain bounded
-at 64. The complete command must succeed and expose the mounted file's entire
-exact body. `cat` accepts literal file operands and the optional `--` delimiter;
-other options cannot prove an unchanged read. Substitutions, pipelines, other shell control flow, and dynamic
-search arguments cannot establish a compound read through this check.
-Unrecognized commands remain partial when their output contains the identifying
-`name: <skill>` line from a mounted or receipt-bound installed-plugin skill.
-This is a host observation; an extension decides what selection means for its
-case.
-The same check accepts skill files below the exact installed plugin roots from
-Codex's installation receipts. It does not infer activation from arbitrary
-files in the private plugin cache.
 The `sevro.codex.native-calls` capability retains allowlisted direct goal and
 agent control calls from the native session bound to the completed thread. Its
 observation contains only call names, namespaces, and source ordinals, plus the
@@ -113,37 +51,10 @@ only when plaintext is readable. It retains neither message nor prompt bytes.
 For a second prompt, `sevro.codex.continuation` retains the last validated
 native-session ordinal before resume. Extensions can compare later call
 ordinals with that boundary without reading private arguments.
-The host also retains separate `sevro.codex.initial-skill-reads` and
-`sevro.codex.follow-up-skill-reads` observations. Each applies the same exact
-mounted-skill read check to one completed turn, so an extension can grade read
-order or a missing repeat read without inferring it from the combined list.
-For `app-server`, the verified same-thread feedback boundary separates the
-initial phase from the follow-up phase, including subsequent native goal turns.
-Absent, duplicated, foreign-thread, or failed boundaries do not yield phase
-receipts.
-
-It also checks native parent command records for exact mounted skill bodies,
-including sessions with no spawn request. The bounded diagnostic distinguishes
-no read from an incomplete read without claiming skill activation.
-It retains the skill name and native ordinal when verified reads complete a
-whole body. Repeated complete reads produce separate receipts; paged reads
-produce one receipt when their ranges first cover the body. An incomplete
-later reread makes the diagnostic partial. Extensions can compare these
-ordinals with an accepted owner boundary without retaining commands or output.
-Earlier yielded output can complete a read only when its process and unique
-call identity bind it to that actor's native command completion. Completed
-literal command calls use a bounded TypeScript parser; conditional or ambiguous
-code cannot establish that binding. Recovery verifies the exact mounted bytes
-and recomputes completeness for the matching CLI command. Private commands,
-submitted code and recovered skill bodies stay out of public observations.
-For accepted spawns, it also checks up to eight child thread rollouts and
+For accepted spawns, the host checks up to eight child thread rollouts and
 reports whether each is available, unavailable, ambiguous, or partial, with an
-explicit truncation flag. An available rollout includes bounded diagnostics for
-native child commands: the number of commands and skill read attempts, whether
-the exact mounted `SKILL.md` body was read, and whether the check was complete
-or truncated. A rollout with no read differs from a missing or malformed
-rollout. These diagnostics do not establish skill activation or task completion
-by themselves and retain no child prompt, command, or output.
+explicit truncation flag. Child rollout metadata describes delegation and
+completion; skill activation remains in the common hook observation.
 An available child rollout also reports whether one nonempty final assistant
 message matches a later native completion event for the same turn. This proves
 a returned turn, not the accuracy of the child's work, and retains no message
@@ -166,13 +77,11 @@ acceptance receipts keep their original meaning; submitted requests do not
 acquire direct native acceptance receipts.
 For an explicitly declared `$plugin:skill`, the host verifies that the installed
 skill exists and that the exact token occurs once in the delivered prompt. A
-completed turn yields a complete `sevro.codex.explicit-invocation` with the owner
-first and verified supporting reads after it. This receipt proves verified
-owner dispatch independently of file reads; it does not prove that all
-supporting skills were read. Consumers requiring complete supporting-read
-evidence must also require `sevro.codex.skill-reads` (or the applicable phase
-receipt) to be complete. Failed execution cannot yield a complete dispatch
-receipt.
+completed turn yields a complete `sevro.codex.explicit-invocation` naming the
+dispatched skill. This receipt proves verified dispatch and contains no
+`observedSkills` list. Activation checks require the common hook observation;
+missing hook evidence cannot be repaired by a dispatch receipt or native
+transcript. Failed execution cannot yield a complete dispatch receipt.
 The `sevro.codex.repository-invocation` capability supports an explicitly
 declared `$skill` from `.agents/skills/<skill>/SKILL.md`. The host checks that
 the repository mount is a bounded regular file with no symlink components and
@@ -239,6 +148,127 @@ verification, fresh credentials/configuration, hook rewriting, preflight, and
 invocation evidence for every request. See the [startup measurements](evidence/runtime-startup-30/README.md)
 for measured boundaries, copy-on-write assessment, and limitations.
 
+## Retired skill-read evidence
+
+The current host no longer emits `sevro.codex.skill-reads`,
+`sevro.codex.initial-skill-reads`, `sevro.codex.follow-up-skill-reads`, or native
+parent/child read diagnostics. Migrate activation checks to
+`sevro.host.skill-activations`; old required evidence remains unavailable rather
+than silently receiving a different meaning. Existing retained run evidence
+keeps its original interpretation.
+
+[Issue #70 representative retests](evidence/skill-reads-70/results.json) retain
+separate task, activation, and phase-read outcomes from the private candidate,
+plus its source fingerprints and test-first regression results. Private native
+transcripts remain outside the repository.
+
+<details>
+<summary>Historical command-pattern and read-recovery contract</summary>
+
+The following describes the retired collector before the hook migration.
+These rules are preserved for interpreting older evidence; they do not describe
+the current host.
+
+The host also retains a bounded `sevro.codex.skill-reads` observation. It
+records the first verified mounted skill and ordered skill names, without
+commands or skill bodies. A `cat` or `sed -n` attempt counts only when its path
+resolves to a mounted skill or a skill below an installed plugin root verified
+by Codex's installation receipt. Missing targets outside a mounted skill
+directory, listings, and other harmless mentions of `SKILL.md` do not make the
+observation partial. A missing `SKILL.md` target does not count as a read just
+because its parent directory belongs to a mounted skill; an existing mounted
+target that fails or produces incomplete bytes remains partial. A completed direct
+`cat` of one mounted `SKILL.md`, alone or alongside literal documentation
+paths, counts only when the command output contains that file's exact body.
+Batched reads naming more than 64 paths remain partial, as do failed,
+malformed, or incomplete recognized reads. Direct
+`sed -n` pages count after their verified line ranges cover the whole body. An
+exact `cat` wrapped by `lean-ctx -c` is accepted only when its reported output
+still contains the full body; a compressed summary cannot prove the read.
+The same exact-body check accepts a literal read followed by one literal `rg`
+command, separated by a semicolon or newline. It also accepts a single-file
+literal `cat` of the skill followed by one or more literal `cat` reads of
+non-skill files, then one literal `rg` command, with the same separators. For
+example:
+
+```sh
+cat .agents/skills/darrow-guide/SKILL.md; cat docs/specs/repository-guide.md; rg -n -i 'offline|\bsla\b|service.level|guarantee|deployment' --glob '*.md' --glob '!docs/research/**' --glob '!**/SKILL.md' .
+```
+
+This sequence uses the shared stream and native read check. Quoted separators
+remain part of their literal operand. The ordered file bodies must match the
+retained output, so documentation or search output cannot replace an altered
+or incomplete skill read. Literal `cat` commands may read multiple mounted
+skills and documentation, before or after skills, with or without a terminal
+search. Multiple literal terminal `rg` commands are accepted within the command
+bound. Each verified skill receives its own ordered receipt. Documentation
+must resolve within the workspace or a receipt-bound installed plugin root;
+each file is bounded to 1 MiB. Aliases of mounted skills without a literal
+`SKILL.md` operand remain unsupported.
+The 64-operand bound applies across all reads in the sequence. Shell expansions,
+including unquoted glob and tilde operands, are unsupported in this form.
+
+The bounded composed-read grammar also accepts `unset` with literal variable
+names, `pwd` or `pwd -P`, `git rev-parse --show-toplevel` (optionally with
+`-C "$PWD"`), `printenv` with literal variable names, and `rg --files` with
+literal arguments before the reads. Prefix `printenv` requires the reads to
+end the command, so environment output cannot replace missing read bytes.
+Literal `printenv` commands may follow reads without prefix `printenv`.
+The fixed pair `repo=$(git -C "$PWD" rev-parse --show-toplevel)` and
+`cd "$repo" && pwd -P` is supported only with absolute read operands. Other
+assignments, substitutions, directory changes, or control flow remain
+unsupported. Prefix and environment output cannot supply skill frontmatter;
+ambiguous repeated output cannot establish an attributable read.
+
+The check also accepts a chain of literal
+`cat` fallbacks with `2>/dev/null` and `||`, ending in `true` followed by a newline
+and one literal `rg` discovery command. A fallback chain must resolve to one
+canonical file across all its read operands; absent alternate targets do not
+invalidate the read. Each fallback `cat` names one literal file. Multiple
+existing targets, including unmounted copies,
+cannot establish an attributable read. The total read operands remain bounded
+at 64. The complete command must succeed and expose the mounted file's entire
+exact body. `cat` accepts literal file operands and the optional `--` delimiter;
+other options cannot prove an unchanged read. Substitutions, pipelines, other shell control flow, and dynamic
+search arguments cannot establish a compound read through this check.
+Unrecognized commands remain partial when their output contains the identifying
+`name: <skill>` line from a mounted or receipt-bound installed-plugin skill.
+This is a host observation; an extension decides what selection means for its
+case.
+The same check accepts skill files below the exact installed plugin roots from
+Codex's installation receipts. It does not infer activation from arbitrary
+files in the private plugin cache.
+The host also retains separate `sevro.codex.initial-skill-reads` and
+`sevro.codex.follow-up-skill-reads` observations. Each applies the same exact
+mounted-skill read check to one completed turn, so an extension can grade read
+order or a missing repeat read without inferring it from the combined list.
+For `app-server`, the verified same-thread feedback boundary separates the
+initial phase from the follow-up phase, including subsequent native goal turns.
+Absent, duplicated, foreign-thread, or failed boundaries do not yield phase
+receipts.
+
+It also checks native parent command records for exact mounted skill bodies,
+including sessions with no spawn request. The bounded diagnostic distinguishes
+no read from an incomplete read without claiming skill activation.
+It retains the skill name and native ordinal when verified reads complete a
+whole body. Repeated complete reads produce separate receipts; paged reads
+produce one receipt when their ranges first cover the body. An incomplete
+later reread makes the diagnostic partial. Extensions can compare these
+ordinals with an accepted owner boundary without retaining commands or output.
+Earlier yielded output can complete a read only when its process and unique
+call identity bind it to that actor's native command completion. Completed
+literal command calls use a bounded TypeScript parser; conditional or ambiguous
+code cannot establish that binding. Recovery verifies the exact mounted bytes
+and recomputes completeness for the matching CLI command. Private commands,
+submitted code and recovered skill bodies stay out of public observations.
+For accepted spawns, it also checks up to eight child thread rollouts and
+reports whether each is available, unavailable, ambiguous, or partial, with an
+explicit truncation flag. An available rollout includes bounded diagnostics for
+native child commands: the number of commands and skill read attempts, whether
+the exact mounted `SKILL.md` body was read, and whether the check was complete
+or truncated. A rollout with no read differs from a missing or malformed
+rollout. These diagnostics do not establish skill activation or task completion
+by themselves and retain no child prompt, command, or output.
 Native read diagnostics retain at most 64 `recoverySources` entries. Each
 records its native ordinal, whether the native completion had output, the
 yielded chunk count, and separate `completedCall` and `literalCommandCall`
@@ -246,7 +276,4 @@ flags. These facts distinguish recovery sources without retaining commands,
 submitted code, or skill bodies. The diagnostic's completeness and truncation
 fields still determine whether its read evidence can support grading.
 
-[Issue #70 representative retests](evidence/skill-reads-70/results.json) retain
-separate task, activation, and phase-read outcomes from the private candidate,
-plus its source fingerprints and test-first regression results. Private native
-transcripts remain outside the repository.
+</details>

package/docs/development-cli.md

@@ -148,6 +148,10 @@ Codex route, including semantic and advisory roles, and to both `exec` and
 `app-server` entrypoints. For a 20-minute app-server evaluation, add
 `--codex-entrypoint app-server --codex-timeout-ms 1200000` to the Codex command
 above. The option requires a Codex host route; invalid values fail before a run.
+For `app-server`, this is the only deadline for the whole session, including
+startup requests such as `thread/start`. If it expires while a request is
+unanswered, the failure names that request, for example
+`App-server evaluation time bound reached awaiting thread/start`.
 
 ### Retain native host diagnostics
 
@@ -305,9 +309,10 @@ Without that option, the host does not advertise
 `sevro.claude.repository-invocation` and refuses explicit repository dispatch
 before launching Claude. This avoids recording an unknown command as a usable
 repository-skill route.
-The host reads only bounded Skill metadata from completed child Agent sessions
-in its temporary private configuration, then removes those session files. A
-missing or inconsistent graph leaves `sevro.claude.nested-skills` partial.
+The host collects successful `Skill` calls through the existing structured
+stream as [skill activation evidence](native-hosts.md#skill-activation-evidence).
+It uses the same collector for parent and nested actors. Missing or unmatched
+results remain partial; separate transcript-based skill detectors are retired.
 
 A case's `followUpPrompt` starts a UUID-bound session and resumes that same
 session after a complete successful initial result. Both results must name

package/docs/extension-protocol-v1.md

@@ -171,7 +171,7 @@ other invocation declarations and enters retained configuration and identity.
 The host validates the bounded mount without following symbolic links. Its
 `sevro.claude.repository-invocation` observation binds one native command, exact
 arguments, and the complete mounted body before the first assistant entry in
-the completed session. It retains only acceptance and ordered skill metadata.
+the completed session. It retains only acceptance and the dispatched skill name.
 Missing or ambiguous session evidence yields a partial observation; later Skill
 calls cannot repair an unverified explicit repository dispatch.
 
@@ -224,6 +224,12 @@ grader error, or unavailable required evidence.
 Host adapters can supply additional namespaced observations. The engine bounds
 and retains those records, then passes them to `evaluate`. Required observation
 IDs must be present with `complete` evidence before a task can pass.
+The bundled adapters expose [skill activation evidence](native-hosts.md#skill-activation-evidence)
+as `sevro.host.skill-activations`, with separate methods for Codex tool-result
+body exposure and successful Claude `Skill` calls.
+This replaces the retired Codex skill-read and Claude nested-skill observations.
+Explicit invocation receipts remain dispatch evidence and do not contribute to
+`observedSkills`; extensions must migrate activation checks to the common ID.
 Host adapters can also supply bounded evidence artifacts. The engine persists
 their bytes outside the candidate workspace before `evaluate`, then passes
 file URLs and digests through the existing artifact references. A required host

package/docs/guide-evaluation.md

@@ -73,6 +73,10 @@ Automatic checks remain signals, not a complete truth judgment. Acceptance
 requires inspecting material claims against the sources actually read.
 File listings do not count as source inspection; follow-ups require fresh
 content. Explicit invocation requires Sevro's complete host dispatch receipt.
+Automatic selection requires the complete `sevro.host.skill-activations`
+observation on both hosts. Codex uses passive tool-result hooks; Claude uses
+successful native `Skill` calls. The evaluator does not fall back to command
+patterns, direct Claude file reads, or retired skill-read observations.
 See the [guide contract](specs/repository-guide.md).
 
 The [earlier verification record](guide-verification.json) describes historical

package/docs/installing.md

@@ -23,10 +23,10 @@ Local installation records the selected version in the project lockfile.
 
 ## Current release
 
-The current release is `0.1.0-rc.13`. Install this exact version:
+The current release is `0.1.0-rc.15`. Install this exact version:
 
 ```sh
-bun add --exact @bjoernrochel/sevro@0.1.0-rc.13
+bun add --exact @bjoernrochel/sevro@0.1.0-rc.15
 ```
 
 <!-- sevro-current-release:end -->

package/docs/native-hosts.md

@@ -48,6 +48,61 @@ plugin hooks and reuses declared host tools with private caches. These changes
 require `rc.3` or later. The CLI reference covers credential scrubbing
 and follow-ups.
 
+## Skill activation evidence
+
+Both bundled adapters advertise `sevro.host.skill-activations`. Its observation
+retains qualified `observedSkills`, bounded call identities, and explicit
+`complete` or `partial` collection status. This is the sole activation collector
+for each host. It replaces Codex's command-pattern and native output-recovery
+detectors and Claude's separate nested-skill collector. Consumers must require
+this observation; the retired observation IDs are no longer emitted.
+
+Codex installs passive runner-owned hooks in its private home for each request.
+The `tool_result_body_match` method compares returned tool content against a
+snapshot of prepared repository, plugin and private user skill bodies. It does
+not parse shell commands, so variables, pipelines, Python and nested Code Mode
+calls use the same collector. Pre/post call pairs and session start/stop markers
+establish collection health. Unselected plugin handlers are removed before
+hooks are enabled, and fixture-local Codex configuration remains untrusted.
+No global hook installation or root privileges are required.
+
+This Codex receipt proves exact body exposure to the tool caller. Code Mode can
+discard that output before returning to the model. An identical ordinary
+document also matches; the receipt does not prove its source file was opened.
+Identical bodies registered under different names are reported as
+`ambiguousSkills`, with partial evidence. Exact pages can establish a body match
+across tool results from the same session and turn. Coverage is tied to the
+prepared body digest; overlapping or repeated pages cannot fill a missing range.
+The call that completes coverage receives the activation receipt. Fragments
+from different sessions or turns never combine.
+
+Page matching uses complete nonblank lines as anchors and exact fragments of
+at least 32 string code units. Fragments with multiple possible positions in a
+body cannot establish coverage. Recognizable unfinished fragments appear in
+`partialSkills` and keep the observation partial; a later complete match resolves
+them. Comparison and anchor budgets also fail closed. Private receipts retain
+body offsets rather than tool text; the public observation omits those offsets.
+Shorter, transformed or unanchored fragments remain outside this matching scope.
+Newly created or changed skill bodies are outside the prepared snapshot. A
+complete empty observation is limited to this scope and the supported local
+tool hook paths.
+
+Claude's `skill_tool_result` method observes its existing structured `Skill`
+stream without enabling additional command hooks. It pairs each call with a
+successful result under the same session, parent actor and tool-use ID.
+Failed calls remain failed; unmatched attempts and malformed or conflicting
+records remain partial. Native explicit command expansion can load a skill
+without a `Skill` call. Explicit-dispatch receipts describe dispatch only;
+they do not add entries to the activation observation. A direct Claude `Read`
+also falls outside the `Skill` seam and is not inferred from its file path.
+
+The collectors retain no tool arguments, outputs or skill bodies in the new
+observation. Codex catalogs at most 128 skills, each at most 1 MiB, with an
+8 MiB total body budget. Call receipts are bounded; missing collection,
+unfinished calls, catalog or receipt limits, and failed execution remain
+partial. Required evidence must not interpret these states as proof that a
+skill was unused.
+
 ## Keep sources and credentials separate
 
 Declare source/private roots as documented. Never put credentials in prompts,

package/docs/runtime-v1.md

@@ -428,9 +428,11 @@ host request's private native state. Curated hook read grants validate the
 canonical projection layout, ownership, private state permissions, and binding
 to that request. Only the selected plugin subtree is readable; it stays
 read-only, and credentials, private siblings, and peer requests remain denied.
-Ordinary filesystem declarations cannot select this exception. Codex still
-validates and filters installed plugins with a runtime policy when hooks are
-disabled. Projections are removed with their owning host request.
+Ordinary filesystem declarations cannot select this exception. Codex validates
+and filters installed plugins before enabling its runner-owned skill collector,
+including requests without a runtime policy. Plugin command handlers still
+require explicit hook authority. Projections are removed with their owning host
+request.
 
 Auxiliary `.mcp.json` and `.lsp.json` files and plugin mods are unsupported under
 hook authority. Manifest MCP/LSP declarations are removed from curated mounts.

package/docs/typescript-quality.md

@@ -29,7 +29,11 @@ order; `--fast` runs only `static` without installing dependencies.
 
 Use the same prerequisites as the corresponding complete-gate checks. A single
 phase is partial evidence; full acceptance requires all four on the same candidate.
-The test suite and its coverage denominator remain whole, with no test sharding.
+CI assigns every test file to exactly one of four duration-balanced shards, then
+enforces both coverage thresholds on their combined counters over the complete
+production inventory. Local `--phase tests` and the complete command still run
+the suite in one process. See the [shard commands](../scripts/coverage/README.md#test-shards)
+for reproducing the CI split.
 
 ## Source dispositions
 
@@ -163,6 +167,15 @@ summary, process ledger, Bun test log, unmodified source snapshot, LCOV and HTML
 production files, branch exclusions, and exact projected counts.
 `coverage-raw.json` and the raw summary preserve all validated counters before
 platform projection.
+CI also retains `.quality/shards/<index>/` with each shard's source snapshot,
+process ledger, test log, raw and portable counters, and manifest. Process IDs
+remain scoped to their original shard. Aggregation verifies candidate contents,
+workflow run, platform, architecture, Bun version, instrumentation
+layout, and exact test assignments before combining counters with normalized
+source paths. Missing, repeated, incomplete, or mismatched shards fail the gate.
+Failed-job reruns can reuse successful shards from earlier attempts of the same
+workflow run; manifests retain each attempt, and rerun shards replace only their
+own artifacts. Another candidate or workflow run cannot supply missing evidence.
 `--coverage [Bun test arguments]` is a diagnostic measurement; it still enforces
 both thresholds and writes `.quality/coverage-targeted`, keeping it distinct from
 the full-suite evidence. Sparse runs are expected to fail the full denominator.
@@ -188,20 +201,24 @@ Ubuntu installs `bubblewrap`, `ripgrep`, and `socat` and runs the same native is
 local macOS runs retain `sandbox-exec`. Windows remains unverified.
 
 Ordinary changes and explicit workflow dispatches run the four canonical phases
-as concurrent matrix jobs. Each job installs locked dependencies; native host
-tools are installed for `docs` and `tests`, and UV and mise for `docs`. The
-`tests` job uploads `.quality` even when coverage fails. Matrix jobs do not
-cancel their siblings on failure, and the stable aggregate `TypeScript quality`
-status requires every phase to succeed. A missing, cancelled, skipped or failed
-phase cannot turn that status green.
+concurrently. The tests phase consists of four shard jobs followed by a combined
+coverage job. Each job installs locked dependencies; native host tools are
+installed for `docs` and the test shards, and UV and mise for `docs`. Each shard
+retains its evidence, and the combined `tests` job uploads `.quality` even when
+coverage fails. Shards do not cancel their siblings on failure. A new commit to
+the same pull request cancels its superseded workflow run; main pushes and manual
+runs have independent concurrency groups. The stable aggregate `TypeScript quality`
+status requires every phase and all four shards to succeed. A missing, cancelled,
+skipped or failed phase or shard cannot turn that status green.
 
 Release metadata changes follow [the release workflow](releases.md) and reuse a
 successful full gate from an ancestor on `main`, with identical code,
 dependencies, schemas, tests, and other quality inputs. The selector permits
 only version/distribution-tag changes and its exact release-file inventory.
-It verifies each original phase job and its gate step, or a historical complete
-gate job and step, so a partial matrix or reused release run cannot serve as
-fresh test evidence. Duplicate phase jobs are ambiguous and refused. Release CI
+It verifies each original phase job and its gate step, including every shard and
+the combined tests job for sharded runs, or a historical complete gate job and
+step. A partial matrix or reused release run cannot serve as fresh test evidence.
+Duplicate phase or shard jobs are ambiguous and refused. Release CI
 runs `check:typescript --fast`, records the tested source and CI run URL, and
 skips all four full-gate phase jobs. The aggregate
 status requires both verified prior evidence and successful static checks;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bjoernrochel/sevro",
-  "version": "0.1.0-rc.13",
+  "version": "0.1.0-rc.15",
   "license": "SEE LICENSE IN LICENSE",
   "description": "A standalone evaluation runner for agentic coding capabilities",
   "type": "module",
@@ -44,7 +44,7 @@
     "eval:guide": "bun scripts/eval-guide.ts",
     "release:prepare": "bun scripts/prepare-release.ts",
     "typecheck": "tsc --noEmit",
-    "format:check": "prettier --check README.md CONTRIBUTING.md AGENTS.md CLAUDE.md 'docs/**/*.md' '.agents/**/*.md' '.agents/**/*.json' '.claude/**/*.md' 'scripts/**/*.md' examples/**/*.json examples/**/*.ts schemas/*.json src/**/*.ts scripts/**/*.ts scripts/**/*.cjs tests/**/*.ts eslint.config.mjs package.json tsconfig.json typescript-sources.json .github/workflows/*.yml"
+    "format:check": "prettier --check README.md CONTRIBUTING.md AGENTS.md CLAUDE.md 'docs/**/*.md' '.agents/**/*.md' '.agents/**/*.json' '.claude/**/*.md' 'scripts/**/*.md' 'scripts/**/*.json' examples/**/*.json examples/**/*.ts schemas/*.json src/**/*.ts scripts/**/*.ts scripts/**/*.cjs tests/**/*.ts eslint.config.mjs package.json tsconfig.json typescript-sources.json .github/workflows/*.yml"
   },
   "dependencies": {
     "ajv": "8.20.0",

package/src/hosts/claude-repository-invocation.ts

@@ -264,14 +264,6 @@ export async function claudeRepositoryInvocationObservation(input: {
   } catch {
     /* Unavailable or malformed native evidence stays partial. */
   }
-  const observed = input.tools.data.calls
-    .filter((call) => call.name === "Skill")
-    .map((call) => call.skill);
-  const observedSkills = repositoryObservedSkills(
-    receipt,
-    input.invocation.skillName,
-    observed,
-  );
   return {
     id: "sevro.claude.repository-invocation" as const,
     completeness:
@@ -282,25 +274,10 @@ export async function claudeRepositoryInvocationObservation(input: {
       method: "native_repository_command",
       ...receipt,
       skill: input.invocation.skillName,
-      primarySkill: observedSkills[0] ?? null,
-      observedSkills,
     },
   };
 }
 
-function repositoryObservedSkills(
-  receipt: Receipt,
-  skillName: string,
-  observed: string[],
-): string[] {
-  return [
-    ...new Set([
-      ...(receipt.accepted === true ? [skillName] : []),
-      ...observed,
-    ]),
-  ];
-}
-
 function repositorySessionId(stream: string): string | null {
   const sessions = [
     ...new Set(