@gobing-ai/spur 0.4.12 → 0.4.13

package/.claude-plugin/marketplace.json

@@ -7,7 +7,7 @@
     "plugins": [
         {
             "name": "sp",
-            "version": "0.4.12",
+            "version": "0.4.13",
             "source": "./plugins/sp"
         }
     ]

package/config/rules/boundary/config-loading-ownership.yaml

@@ -67,7 +67,7 @@ rules:
     exclude:
       - "packages/config/src/**"
       - "apps/cli/src/index.ts"
-      - "apps/cli/src/workflow-transport.ts" # boot-free composition root of `spur workflow inline|commit-guard` (PR-4)
+      - "apps/cli/src/workflow-transport.ts" # boot-free composition root of `spur workflow commit-guard|persist-*` (PR-4)
       - "apps/server/src/serve.ts"
       - "apps/server/src/context.ts"
       - "**/tests/**"

package/config/rules/strict/runtime-boundaries.yaml

@@ -101,8 +101,8 @@ rules:
             - "packages/app/src/services/history-anatomy.ts" # deterministic history-anatomy cache core (task 1005 R2): fsync'd tmp+rename atomic publish, readdir digest scans and sync report reads must stay byte-stable; bundled standalone for the bare-node plugin twin (mirrors agent-usage-producer.ts / history-service.ts exemptions)
             - "packages/app/src/observability/workflow-run-log-sink.ts" # sync FD append for mid-run tail-able all-in-one run log (task 0426 / feature D2); append() is sync from the observability bus
             - "packages/app/src/observability/agent-run-log.ts" # same primitive as the sink above for the per-run agent stream (task 1076 R1, ADR-132); append() is sync from the agent service's own onOutput hook, and the byte cap needs the FD position it tracks
-            # Inline-driver transports (script-absorption PR-4, `spur workflow inline|commit-guard`): moved
-            # verbatim from the plugin scripts with their golden output pinned; synchronous probes and
+            # Workflow transports (script-absorption PR-4, `spur workflow commit-guard`): moved
+            # verbatim from the plugin scripts; synchronous probes and
             # atomic tmp+rename snapshot writes inside one short-lived CLI process.
             - "packages/app/src/workflow/commit-guard.ts" # .spur/run/<run>-tree-start.json atomic snapshot + target conflict-marker reads
             - "packages/app/src/workflow/persist-check.ts" # recursive evidence-tree listing + byte comparison of both trees

package/config/rules/typescript/output-boundaries.yaml

@@ -17,11 +17,6 @@ rules:
       type: rg
       config:
         pattern: "console\\.(log|error|warn|info|debug|dir|time|trace)"
-    # Task 1006 R3: the inline-run driver's fail-closed stderr lines moved here from the
-    # plugin script (byte-stable driver contract, emitted through the bundled lib under
-    # bare node); the output seam is a CLI-layer dependency the app service cannot take.
-    exclude:
-      - "packages/app/src/services/inline-run-setup.ts"
 
   - id: no-raw-stdout-stderr
     description: "Use the output seam (ts-utils echo/echoError) instead of process.stdout/stderr.write directly."
@@ -30,10 +25,9 @@ rules:
       type: rg
       config:
         pattern: "process\\.(stdout|stderr)\\.write"
-    # Tasks 1006 R1/R3: gate receipts (`check-receipt/v1`, one JSON line — the runner's parsed
-    # stdout contract) and the inline driver's stdout lines moved here from the plugin scripts.
-    # Both must stay byte-stable through the bundled libs under bare node; the seam would
-    # rewrite framing the CLI/tests parse. Mirrors the history-anatomy bundling exemptions.
+    # Task 1006 R1: gate receipts (`check-receipt/v1`, one JSON line — the runner's parsed
+    # stdout contract) moved here from the plugin script. It must stay byte-stable through the
+    # bundled lib under bare node; the seam would rewrite framing the CLI/tests parse. Mirrors
+    # the history-anatomy bundling exemptions.
     exclude:
       - "packages/app/src/services/quality-gate.ts"
-      - "packages/app/src/services/inline-run-setup.ts"

package/config/workflows/task-pipeline.yaml

@@ -114,8 +114,8 @@ vars:
     # Timeout for the `implement` step specifically (R2a). Implementation is the
     # heaviest agent.run step (full read/write/test-probe loop); the old 600s default
     # failed five consecutive dogfood runs (bugs 742/744/746/748). Default is 45 min
-    # (task 1108); inline hosts receive it only when their dispatch tool accepts a
-    # timeout (inline-pipeline-driver.md § Timeout boundary).
+    # (task 1108); the host executor forwards it only when the host's dispatch tool
+    # accepts a timeout.
     # Override per run: `--vars '{"implementTimeoutMs":"3600000"}'`.
     implementTimeoutMs: "2700000"
     # Answer captured by the review's approval decision point: "yes" | "no" | "cancel"

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@gobing-ai/spur",
-    "version": "0.4.12",
+    "version": "0.4.13",
     "description": "Spur CLI — local-first harness for mainstream coding agents: constraint checking, workflow orchestration, agent health, and history analytics. Bun-native; exposes the `spur` command.",
     "keywords": [
         "spur",

package/plugins/sp/commands/dev-run.md

@@ -53,7 +53,7 @@ For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag
 
 **Flags:**
 
-- `--auto` | `--agent <inline|auto|name>` — Skip objective HITL confirmations (taste/irreversible gates still pause). `--agent` names who does the model-bearing work. Interactive omit/`inline` keeps the controller and implement-only stages in this session; full mode reads `task-pipeline.yaml` as the SSOT and interprets its actions/guards through the inline driver, whose eligible `agent.run` stages dispatch once to a native subagent and otherwise run in the host (0508 eligibility — task 0687 resolved-inline) It records `stage <id> executed inline in session <session-id>` or `stage <id> executed via subagent <agent-id> (host session <session-id>)` in the run log. `auto` or a name is merged into `vars.agent` and `vars.implementAgent` and keeps the existing subprocess workflow; `--agent fleet` maps the run to `vars.executor: 'fleet'` instead (fleet dispatch, 0942). Headless `spur workflow run` / `spur agent run` is unchanged. See the [execution-surface contract](../skills/spur-dev/references/cross-cutting.md#inline-default-execution-surface).
+- `--auto` | `--agent <inline|auto|name>` — Skip objective HITL confirmations (taste/irreversible gates still pause). `--agent` names who does the model-bearing work. Interactive omit/`inline` keeps the controller and implement-only stages in this session; full mode reads `task-pipeline.yaml` as the SSOT and runs on the host executor (`vars.executor: 'host'`; the engine walks its actions/guards and `spur workflow continue` advances each pause), whose eligible `agent.run` stages dispatch once to a native subagent and otherwise run in the host (0508 eligibility — task 0687 resolved-inline) It records `stage <id> executed inline in session <session-id>` or `stage <id> executed via subagent <agent-id> (host session <session-id>)` in the run log. `auto` or a name is merged into `vars.agent` and `vars.implementAgent` and keeps the existing subprocess workflow; `--agent fleet` maps the run to `vars.executor: 'fleet'` instead (fleet dispatch, 0942). Headless `spur workflow run` / `spur agent run` is unchanged. See the [execution-surface contract](../skills/spur-dev/references/cross-cutting.md#inline-default-execution-surface).
 - `--escalation-file <path>` (implement step only, 0933) — names the Q/A escalation transcript
   (default `.spur/run/<wbs>-escalation.md`). Absent on a first attempt means "no prior
   escalations". When the implement agent needs an operator decision it appends its question to

package/plugins/sp/plugin.json

@@ -1,5 +1,5 @@
 {
     "name": "sp",
-    "version": "0.4.12",
+    "version": "0.4.13",
     "description": "Spur — a local-first harness engineering toolkit that wraps mainstream coding agents with constraint checking, workflow orchestration, and history analytics."
 }

package/plugins/sp/skills/spur-dev/references/cross-cutting.md

@@ -239,13 +239,13 @@ Inline avoids process startup and preserves the host session's context and tools
 subprocess dispatch it provides **no isolated workspace**, **no per-stage subprocess action
 record**, **no independent timeout or abort boundary**, and **no tier-selected executor**: the
 executor is the current coding agent. Interactive pipelines retain a run log and session provenance
-through the inline driver; task pipelines additionally record a task run-link. If process isolation or an independently killable
+through the host executor; task pipelines additionally record a task run-link. If process isolation or an independently killable
 stage is required, select the subprocess path (`--agent auto` or `--agent <name>`).
 
 ## Shared startup contract (task 0814 R1/R3/R4/R6/R7/R8)
 
 The workflow-backed dev commands (`dev-run`, `dev-runall`, `dev-refineall`, `dev-verifyall`) share one
-startup order. The order is load-bearing and applies on both the inline driver and the subprocess
+startup order. The order is load-bearing and applies on both the host executor and the subprocess
 path. Runs that resolve a workflow definition publish the generated plan as their first action
 (1105 R1); skill-only operations (refine/verify batches with no nested workflow) display their owned
 procedure and do not fabricate a workflow YAML.
@@ -571,7 +571,7 @@ does not earn another full-gate run:
    final gate.
 3. **Red alone**, or a failure that is not a timeout → it is a real failure. Fix it.
 4. Give the test an explicit per-test timeout and a WHY comment (see
-   `plugins/sp/tests/inline-run-close-reason.test.ts:100-102`) as soon as EITHER (a) the same test
+   `plugins/sp/tests/helpers/cli-surface.test.ts:81`) as soon as EITHER (a) the same test
    load-flakes in two separate runs, OR (b) it times out once **outside the change scope** and then
    passes green alone on three consecutive isolated reruns. **Prefer making the test cheap or
    hermetic first** — a test that hashes the live checkout transitively, or writes a probe file into

package/plugins/sp/skills/spur-dev/references/dev-operations.md

@@ -76,7 +76,7 @@ each would be scope creep for one-liner procedures.
 | 4   | run        | `dev-run`           | `Skill()`         | `sp:spur-dev` (`run` / `implement`)                                                | `<wbs> [--mode <full\|implement>] [--agent <inline\|auto\|name>] [--auto] [--next] [--wrap] [--continue] [--worktree [<name>]] [--no-summary]`                                                                                              |
 | 5   | refine     | `dev-refine`        | `Skill()`         | `sp:spur-dev` (`refine`)                                                           | `<wbs> [--focus <mode>] [--description <text>] [--depth <standard\|ready>] [--agent <inline\|auto\|name>] [--auto] [--next]`                                                                           |
 | 5a  | refineall  | `dev-refineall`     | `Skill()`         | `sp:spur-dev` (`refineall`)                                                        | `--feature <id> \| --tasks <selector> [--focus <mode>] [--description <text>] [--depth <standard\|ready>] [--agent <inline\|auto\|name>] [--auto] [--keep-going] [--status <s>] [--json] [--worktree [<name>]]` |
-| 6   | plan       | `dev-plan`          | `Skill()`         | inline driver (`idea-pipeline`) or async workflow                                  | `"<description>" [--feature <id>] [--parent <feature-id>] [--skip-design] [--agent <inline\|auto\|name>] [--auto]`                                                                   |
+| 6   | plan       | `dev-plan`          | `Skill()`         | host executor (`idea-pipeline`) or async workflow                                  | `"<description>" [--feature <id>] [--parent <feature-id>] [--skip-design] [--agent <inline\|auto\|name>] [--auto]`                                                                   |
 | 7   | docs       | _(no thin wrapper)_ | `Skill()`         | `sp:doc-evolve`                                                                    | `"<change description>"`                                                                                                                                                                               |
 | 8   | changelog  | `dev-changelog`     | `inline`          | git log + conventional-commit grouping                                             | `[<file>] [--since <ref>] [--until <ref>] [--version <ver>]`                                                                                                                                            |
 | 9   | gitmsg     | `dev-gitmsg`        | `inline`          | bounded diff capture → concern grouping → conventional commit                      | `[--commit] [--squash] [--all] [--scope <path>] [--check <cmd>]`                                                                                                           |
@@ -89,7 +89,7 @@ each would be scope creep for one-liner procedures.
 | 13  | runall     | `dev-runall`        | `Skill()` → agent | `sp:spur-dev` (`runall`) → `sp:super-planner`                                      | `--tasks <selector> [--feature <id>] [--mode <sequential\|parallel\|auto>] [--concurrency <n>] [--keep-going] [--auto] [--agent <inline\|auto\|name>] [--json] [--wrap] [--next] [--continue] [--worktree [<name>]] [--no-summary] [--defer-gate]`                      |
 | 14  | wrap       | `dev-wrap`          | `Skill()`         | `spur workflow run` (wrapup-pipeline)                                              | `<wbs> [--agent <inline\|auto\|name>] [--auto] [--merge] [--dry-run]`                                                                                                                                 |
 | 15  | wrapall    | `dev-wrapall`       | `Skill()`         | `spur workflow run` (wrapup-pipeline)                                              | `[--since <iso>] [--feature <id>] [--status <s>] [--agent <inline\|auto\|name>] [--auto] [--merge] [--dry-run]`                                                                                        |
-| 16  | idea       | `dev-idea`          | `Skill()`         | inline driver (`idea-pipeline`) or async workflow                                  | `"<idea>" \| --from-file <path> [--skip-design] [--agent <inline\|auto\|name>] [--auto]`                                                                                                                              |
+| 16  | idea       | `dev-idea`          | `Skill()`         | host executor (`idea-pipeline`) or async workflow                                  | `"<idea>" \| --from-file <path> [--skip-design] [--agent <inline\|auto\|name>] [--auto]`                                                                                                                              |
 | 17  | refactor   | `dev-refactor`      | `Skill()`         | `sp:code-refactoring` skill (thin wrapper, ADR-032)                                | `[<description>] [--scope <path>] [--focus <api\|architect\|tests\|ui\|auto>] [--fix <none\|blockers-first\|all>] [--check <cmd>] [--agent <inline\|auto\|name>] [--auto]`                                                                                          |
 
 ## Skill-backed operations
@@ -537,9 +537,9 @@ gate commands, pending questions and approval requirements.>
   `--from-file` contents) unmodified to `.spur/run/<run-id>-idea-input.md` (0887 R1); the precheck
   fails the run when that file is empty or missing, and every model-bearing stage prompt treats
   it as the authoritative ask (R2).
-- **Backing:** `idea-pipeline.yaml` through the inline driver for omitted/`inline`, or `spur workflow run idea-pipeline.yaml --async` for `auto`/name.
+- **Backing:** `idea-pipeline.yaml` on the host executor (`vars.executor: host`, advanced by `spur workflow continue`) for omitted/`inline`, or `spur workflow run idea-pipeline.yaml --async` for `auto`/name.
 - **Behavior:** Builds vars from the table above and drives the idea pipeline. Flow: discovery → **idea-eval** (taste; reject → cancelled) → feature-create → ac-generate → feature-check → system-design (conditional) → design-approval (taste) → decompose → batch-create (`--skip-ready`) → ready-prepare (ready checklist per created task + ready-evidence sidecar, 0788) → handoff. STOPS at handoff — no task execution, no pipeline nesting. Headless runs use one `trace --follow`; cancellation is reported stopped only when `workflow cancel --json` returns `killed: true`.
-- **Delegation:** Host-session inline driver by default; explicit executor selection uses the async workflow worker.
+- **Delegation:** Host executor (this session answers each work item) by default; explicit executor selection uses the async workflow worker.
 - **Idea-evaluation gate:** After discovery, operator reviews `.spur/run/idea-eval-report.md` ([idea-evaluation.md](idea-evaluation.md)). Approve continues; reject/cancel → no feature. Under `--auto`, follows the report's recommendation (`drop` → cancelled; missing recommendation → pauses). Enhanced idea is a sidecar — `vars.idea` is not overwritten.
 - **Design package (`--skip-design` only):**
 

package/plugins/sp/skills/spur-dev/references/execution-workflow.md

@@ -101,7 +101,7 @@ cache-conservation discipline (`plugins/sp/skills/dogfood-testing/references/mon
 
 **`--worktree [<name>]` wraps Step 2, on either surface.** When `/sp:dev-run --mode full` carries
 [`--worktree`](flag-glossary.md#flag-worktree), create or adopt the worktree *before* launching the
-pipeline, `cd` into it (`spur workflow run` and the inline driver both resolve cwd from the process),
+pipeline, `cd` into it (`spur workflow run` and `spur workflow continue` both resolve cwd from the process),
 and merge-or-retain after the run reports. The lifecycle is
 [execution-batch.md § Worktree isolation](execution-batch.md#worktree-isolation---worktree-name)
 applied to a batch of one. Rejected with `--mode implement`.

package/plugins/sp/skills/spur-dev/references/idea-evaluation.md

@@ -21,7 +21,7 @@ re-author the report.
 
 **Sidecar rule:** The enhanced idea does **not** overwrite `vars.idea`. Feature-create reads both
 the original idea and this report. The operator's verbatim ask of record is the run's
-`.spur/run/<run-id>-idea-input.md` (persisted by the pipeline `start` state / the inline driver
+`.spur/run/<run-id>-idea-input.md` (persisted by the pipeline `start` state on every executor surface
 before any processing); the `## Requirement inventory` items trace back to it.
 
 ## Template