@open-agent-toolkit/cli 0.1.62 → 0.1.64

package/assets/skills/oat-project-design/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: oat-project-design
-version: 2.1.0
+version: 2.2.0
 description: Use when discovery is complete and implementation-ready decisions are needed. Runs a collaborative, selective collaborative, or draft-and-review design flow, confirms requirements and produces both `spec.md` and `design.md`, and commits artifacts before the user-review gate.
 disable-model-invocation: true
 user-invocable: true
@@ -688,6 +688,84 @@ Architecture:
 Next: Create implementation plan with the oat-project-plan skill
 ```
 
+### Gate Execution
+
+Before reporting this skill as complete, run the configured gate as the final
+step:
+
+1. Resolve the gate for this skill:
+
+   ```bash
+   oat gate resolve <this-skill> --json
+   ```
+
+   If the command returns JSON `null`, no gate is configured; the skill is
+   complete.
+
+2. Export the resolved project path into the command shell:
+
+   ```bash
+   export PROJECT_PATH
+   ```
+
+   If the resolved command invokes `oat gate review`, the configured review
+   command must already include `--project "$PROJECT_PATH"` and must not include
+   `--target <id>`. A valid reusable shape is
+   `oat gate review --project "$PROJECT_PATH" ...`. If the declaration is
+   missing, stop and migrate the stored gate command; do not inject or append
+   arguments at execution time.
+
+3. Execute the resolved command exactly as configured. Capture stdout, stderr,
+   the exit code, and the structured JSON result. A zero exit code means the
+   review passed its threshold, but it does not by itself authorize artifact
+   receipt or complete the handoff.
+
+4. Review-artifact handoff:
+   - Parse the structured gate result. An exit code or artifact path alone never
+     authorizes `oat-project-review-receive`.
+   - Invoke receive only when all three conditions hold: `status` is `ok` or
+     `blocked`, the envelope explicitly sets `receiveEligible: true`, and a
+     non-null `handoff` confirms the artifact was corroborated.
+   - `receiveEligible: false` is a hard stop even when `artifactPath` is present.
+     Never receive `targeting_correlation_failed`; correct the project/run
+     routing and run a new gate.
+   - Keep `artifact_validation_failed` outside receive until the artifact is
+     corrected and the gate successfully revalidates it. Treat `review_failed`,
+     unknown statuses, null handoffs, and contradictory eligibility fields as
+     operational failures.
+   - `blocked` exits nonzero but is receive-eligible; `ok` exits zero and still
+     requires durable receive disposition. Route by structured status and
+     eligibility, not by exit code.
+
+5. If the command exits nonzero, use `description` to orient the next steps and
+   handle `onFailure`:
+   - `block`: read gate feedback, remediate, and re-run the gate up to
+     `maxAttempts` attempts (default `2`). If attempts are exhausted, escalate
+     to the human with accumulated feedback and append that feedback to
+     `implementation.md`. Treat a launch failure, missing CLI, or no eligible
+     runtime as escalation-biased and do not spend it as a remediation attempt.
+   - `prompt`: surface the gate failure and ask the human how to proceed.
+   - `warn`: record the gate failure and continue.
+
+6. Runtime selection note (V1): the step runs the gate `command` as-is and reads
+   no OAT runtime env var. By default, `oat gate review` and
+   `oat gate cross-provider-exec` resolve the current host from built-in
+   `hostDetectionCommand`s and avoid the same runtime when no exact target is
+   supplied. Reusable lifecycle skill-gate commands must not include
+   `--target <id>` so independent review stays provider-neutral. Use explicit
+   targets only for manual/debug commands or deliberate local/user-specific
+   overrides; do not hardcode provider/model targets in bundled skill guidance
+   or shared lifecycle gate examples.
+
+When `OAT_AUTONOMOUS=1`, perform eligible review receive immediately and apply
+the autonomy contract's `onFailure` semantics without prompting: `warn`
+continues with provenance, `block` stops after bounded attempts, and `prompt`
+is a reported boundary. Unresolved Critical review findings always stop
+autonomous design progression, regardless of a less restrictive gate failure
+setting; record the blocker and leave the project resumable. Important findings
+follow the configured gate policy. When autonomy is inactive, the interactive
+behavior above is unchanged.
+
 ## Success Criteria
 
 - Architecture aligns with existing patterns (from architecture.md)

package/assets/skills/oat-project-discover/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: oat-project-discover
-version: 2.0.3
+version: 2.1.0
 description: Use when the user explicitly asks to continue discovery for an active spec-driven OAT project — e.g. "continue discovery", "run discovery", or confirms a previously offered discovery step. Do NOT auto-invoke for new ideas or quick-mode projects. Gathers requirements and context before spec/design.
 disable-model-invocation: false
 user-invocable: true
@@ -479,3 +479,78 @@ requirements automatically and produce both spec.md and design.md).
 If you'd rather formalize requirements without designing yet, run
 `oat-project-spec` as a standalone step.
 ```
+
+### Gate Execution
+
+Before reporting this skill as complete, run the configured gate as the final
+step:
+
+1. Resolve the gate for this skill:
+
+   ```bash
+   oat gate resolve <this-skill> --json
+   ```
+
+   If the command returns JSON `null`, no gate is configured; the skill is
+   complete.
+
+2. Export the resolved project path into the command shell:
+
+   ```bash
+   export PROJECT_PATH
+   ```
+
+   If the resolved command invokes `oat gate review`, the configured review
+   command must already include `--project "$PROJECT_PATH"` and must not include
+   `--target <id>`. A valid reusable shape is
+   `oat gate review --project "$PROJECT_PATH" ...`. If the declaration is
+   missing, stop and migrate the stored gate command; do not inject or append
+   arguments at execution time.
+
+3. Execute the resolved command exactly as configured. Capture stdout, stderr,
+   the exit code, and the structured JSON result. A zero exit code means the
+   review passed its threshold, but it does not by itself authorize artifact
+   receipt or complete the handoff.
+
+4. Review-artifact handoff:
+   - Parse the structured gate result. An exit code or artifact path alone never
+     authorizes `oat-project-review-receive`.
+   - Invoke receive only when all three conditions hold: `status` is `ok` or
+     `blocked`, the envelope explicitly sets `receiveEligible: true`, and a
+     non-null `handoff` confirms the artifact was corroborated.
+   - `receiveEligible: false` is a hard stop even when `artifactPath` is present.
+     Never receive `targeting_correlation_failed`; correct the project/run
+     routing and run a new gate.
+   - Keep `artifact_validation_failed` outside receive until the artifact is
+     corrected and the gate successfully revalidates it. Treat `review_failed`,
+     unknown statuses, null handoffs, and contradictory eligibility fields as
+     operational failures.
+   - `blocked` exits nonzero but is receive-eligible; `ok` exits zero and still
+     requires durable receive disposition. Route by structured status and
+     eligibility, not by exit code.
+
+5. If the command exits nonzero, use `description` to orient the next steps and
+   handle `onFailure`:
+   - `block`: read gate feedback, remediate, and re-run the gate up to
+     `maxAttempts` attempts (default `2`). If attempts are exhausted, escalate
+     to the human with accumulated feedback and append that feedback to
+     `implementation.md`. Treat a launch failure, missing CLI, or no eligible
+     runtime as escalation-biased and do not spend it as a remediation attempt.
+   - `prompt`: surface the gate failure and ask the human how to proceed.
+   - `warn`: record the gate failure and continue.
+
+6. Runtime selection note (V1): the step runs the gate `command` as-is and reads
+   no OAT runtime env var. By default, `oat gate review` and
+   `oat gate cross-provider-exec` resolve the current host from built-in
+   `hostDetectionCommand`s and avoid the same runtime when no exact target is
+   supplied. Reusable lifecycle skill-gate commands must not include
+   `--target <id>` so independent review stays provider-neutral. Use explicit
+   targets only for manual/debug commands or deliberate local/user-specific
+   overrides; do not hardcode provider/model targets in bundled skill guidance
+   or shared lifecycle gate examples.
+
+When `OAT_AUTONOMOUS=1`, perform eligible review receive immediately and apply
+the autonomy contract's `onFailure` semantics without prompting: `warn`
+continues with provenance, `block` stops after bounded attempts, and `prompt`
+is a reported boundary. When autonomy is inactive, the interactive behavior
+above is unchanged.

package/assets/skills/oat-project-document/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: oat-project-document
-version: 1.5.0
+version: 1.6.1
 description: Use when the user requests or confirms documenting an active OAT project — e.g. "document the project", "update the docs", "run oat-project-document", or confirms a previously offered documentation run. Do NOT auto-invoke when implementation completes. Analyzes project artifacts, presents a documentation delta plan, and applies approved changes.
 argument-hint: '[project-path] [--auto]'
 disable-model-invocation: false
@@ -25,6 +25,11 @@ Read project artifacts and implementation code to identify documentation surface
 
 **Purpose:** Analyze what a project built, identify documentation gaps, and apply approved documentation updates.
 
+When `OAT_AUTONOMOUS=1`, read `references/docs/autonomy-contract.md` and execute
+the existing `--auto` path for this run. Keep `OAT_NON_INTERACTIVE=1`
+session-scoped and never persist either environment signal. This branch is inert
+when autonomy is inactive.
+
 ## Progress Indicators (User-Facing)
 
 - Print a phase banner once at start:
@@ -69,6 +74,13 @@ If you catch yourself:
 2. Return to current step
 3. Ask user for guidance
 
+## Artifact Hygiene
+
+Artifact hygiene contract: Before finishing or committing, format every file you created or edited. Use the concrete write/fix formatting command supplied by the governing plan, task, or brief. If none is usable, discover the repository's documented write/fix command from applicable `AGENTS.md`/`CLAUDE.md` instructions and relevant package manifests; do not infer or hardcode a formatter. Prefer a file-scoped invocation when supported, and avoid rewriting unrelated files. If no command is discoverable, warn once with `no format command discovered in repo instructions; skipping`, then continue.
+
+After formatting, run only repository checks relevant to the files changed;
+writing documentation does not imply unrelated full test suites.
+
 ## Argument Parsing
 
 Parse `$ARGUMENTS` for:
@@ -82,6 +94,11 @@ Parse `$ARGUMENTS` for:
    fi
    ```
 
+   If `OAT_AUTONOMOUS=1`, set `AUTO_MODE=true` after normal argument parsing
+   even when `--auto` was not passed. Record gate `DOCUMENT-02` and the applied
+   recommendation set in the documentation outcome. This is the existing
+   `--auto` behavior, not a new approval mode.
+
 2. **`project-path`:** Any non-flag argument is treated as an explicit project path.
    ```
    PROJECT_ARG=$(echo "$ARGUMENTS" | sed 's/--auto//g' | xargs)
@@ -413,6 +430,12 @@ Format and present the recommendations for user approval.
 - If no recommendations found: report "No documentation updates identified for this project.", set `oat_docs_updated: complete` in state.md, and exit
 - If only instruction recommendations (no docs): still present, but note the documentation-first priority
 
+Under `OAT_AUTONOMOUS=1`, the auto path applies all non-destructive
+recommendations without presenting Step 6c. A recommendation that deletes
+documentation or broadly restructures existing documentation beyond the
+approved project plan remains gate `DOCUMENT-03`: stop before applying it,
+record the proposed change and evidence, and leave the project resumable.
+
 **6c. Interactive approval:**
 
 ```