@gobing-ai/spur 0.3.27 → 0.3.28

package/config/templates/AGENTS.md

@@ -33,10 +33,10 @@ All product development work goes through the harness by default.
 ### Harness tool routing
 
 | Need | Route to | Avoid |
-|------|----------|--------|
+| ------ | ---------- | -------- |
 | Plan a feature (intake → AC → tasks) | `/sp:dev-plan`, `/sp:dev-idea` | Freeform feature files without gates |
-| Drive one task end-to-end | `/sp:dev-run <wbs>` or **`sp:super-coder`** | Implement with no task / no pipeline |
-| Batch or parallel task runs | `/sp:dev-runall`, `/sp:dev-parallel` → **`sp:super-coder`** | Unordered multi-task thrash |
+| Drive one task end-to-end | `/sp:dev-run <wbs>` or **`sp:super-planner`** | Implement with no task / no pipeline |
+| Batch or parallel task runs | `/sp:dev-runall`, `/sp:dev-parallel` → **`sp:super-planner`** | Unordered multi-task thrash |
 | Batch-refine tasks under a feature | `/sp:dev-refineall --feature <id> --auto` | Hand-looping `/sp:dev-refine` per WBS |
 | Multi-step corpus CLI (tasks/features/rules/workflows) | **`sp:expert-spur`** | Raw Write/Edit on corpus files |
 | Look up `spur` verbs / flags / `--json` | Skill **`sp:spur-cli`** | Inventing flags from memory |
@@ -59,7 +59,7 @@ All product development work goes through the harness by default.
 2. **Gates before done** — `spur task check` / `spur feature check` / `spur rule run`; pipeline done
    needs a real verify **PASS**.
 3. **`--json` for machines** — parse CLI with `--json`.
-4. **Route, don’t invent** — verbs → `sp:spur-cli`; lifecycle → `/sp:dev-*` / `sp:super-coder`;
+4. **Route, don’t invent** — verbs → `sp:spur-cli`; lifecycle → `/sp:dev-*` / `sp:super-planner`;
    multi-noun corpus → `sp:expert-spur`; review → `sp:super-reviewer`; docs process → `sp:doc-evolve`.
 5. **Keep tool ownership explicit** — project lifecycle/corpus/gates → Spur; plugin installation and
    capability lifecycle → Superskill. Do not hand-maintain per-platform adapters Superskill generates.
@@ -84,7 +84,7 @@ authority first, then derived docs, then this file.
 ### Doc map
 
 | Doc | Owns | Authority | When |
-|------|------|-----------|------|
+| ------ | ------ | ----------- | ------ |
 | `docs/00_ADR.md` | **WHY** | Authoritative (content) | Structural change; dated entry before diverging |
 | `docs/01_PRD.md` | **WHAT** | Authoritative on scope | New feature/command |
 | `docs/02_ROADMAP.md` | **WHEN** | Derived | Phase placement |
@@ -134,7 +134,7 @@ _(Fill from package manifests / README — or during `sp:doc-evolve` customize.)
 ## Spur CLI surface
 
 **Not the verb catalog.** For `task` / `feature` / `rule` / `workflow` flags, exit codes, and
-`--json` shapes → skill **`sp:spur-cli`**. Lifecycle → `/sp:dev-*` / **`sp:super-coder`**.
+`--json` shapes → skill **`sp:spur-cli`**. Lifecycle → `/sp:dev-*` / **`sp:super-planner`**.
 Multi-noun corpus campaigns → **`sp:expert-spur`**.
 
 ```bash

package/config/workflows/task-pipeline.yaml

@@ -49,7 +49,15 @@ vars:
   # Step-level timeout for agent.run steps in milliseconds. A timed-out agent
   # subprocess is killed (not abandoned) and the step fails → pipeline routes to
   # `failed`. Override per run with `--vars '{"stepTimeoutMs":120000}'`.
-  stepTimeoutMs: "600000"
+  # Raised 600s → 1800s (task 0398 R4). The H6 dogfood batch lost 3 of its 4
+  # timeouts on `test` steps hitting exactly the 600s wall (0391, 0395 test;
+  # `.spur/run/*-test-partial.md`), the same failure signature that justified
+  # implementTimeoutMs below. Agentic test/review/verify steps read the diff,
+  # run the suite, and write a section — that does not fit in 10 min on this
+  # corpus. Same honesty rule as implementTimeoutMs: 30 min is headroom, not a
+  # licence to run unbounded. If a step still hits this wall, STOP and record it
+  # rather than raising again without operator sign-off.
+  stepTimeoutMs: "1800000"
   # Timeout for the `implement` step specifically (R2a). Implementation is the
   # heaviest agent.run step (full read/write/test-probe loop) and has timed out
   # at the 600s default in five consecutive dogfood runs (bugs 742/744/746/748),

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@gobing-ai/spur",
-    "version": "0.3.27",
+    "version": "0.3.28",
     "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",
@@ -50,14 +50,14 @@
     },
     "devDependencies": {
         "@commander-js/extra-typings": "^14.0.0",
-        "@gobing-ai/ts-db": "^0.4.14",
-        "@gobing-ai/ts-ai-runner": "^0.4.14",
-        "@gobing-ai/ts-dual-workflow-engine": "^0.4.14",
-        "@gobing-ai/ts-infra": "^0.4.14",
-        "@gobing-ai/ts-llm-jsonl-importer": "^0.4.14",
-        "@gobing-ai/ts-rule-engine": "^0.4.14",
-        "@gobing-ai/ts-runtime": "^0.4.14",
-        "@gobing-ai/ts-utils": "^0.4.14",
+        "@gobing-ai/ts-db": "^0.4.15",
+        "@gobing-ai/ts-ai-runner": "^0.4.15",
+        "@gobing-ai/ts-dual-workflow-engine": "^0.4.15",
+        "@gobing-ai/ts-infra": "^0.4.15",
+        "@gobing-ai/ts-llm-jsonl-importer": "^0.4.15",
+        "@gobing-ai/ts-rule-engine": "^0.4.15",
+        "@gobing-ai/ts-runtime": "^0.4.15",
+        "@gobing-ai/ts-utils": "^0.4.15",
         "@types/bun": "1.3.14",
         "@types/figlet": "^1.7.0",
         "@types/node-notifier": "8.0.5",