@pareto4/pp-core 1.7.0 → 1.8.0

package/pp-core/workflows/plan-phase.md

@@ -488,12 +488,13 @@ If user selects "Skip research": skip to step 6.
 
 **If `--auto` and `research_enabled` is false:** Skip research silently (preserves automated behavior).
 
-Display banner:
+Run this Bash command to emit the branded Discovery stage banner (renders on stderr, auto-degrades on non-TTY — do NOT print an inline ASCII banner, that would double-print):
+```bash
+pp_run banner discovery "RESEARCHING PHASE {X}"
 ```
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
- pp-core ► RESEARCHING PHASE {X}
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
+Then announce the spawn:
+```
 ◆ Spawning researcher... (runs in a subagent — no output until it returns, ~1–5 min; expected, not a freeze)
 ```
 
@@ -501,7 +502,7 @@ Display banner:
 
 ```bash
 if pp_run query teams-status --active >/dev/null 2>&1; then
-  echo "⚠️  CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS detected. pp-core's multi-agent orchestration is not validated under claude-code agent-teams and may stall (a subagent's completion can fail to route to the orchestrator). Recommend disabling agent-teams for GSD workflows. See https://github.com/open-gsd/pp-core/issues/1355" >&2
+  echo "⚠️  CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS detected. pp-core's multi-agent orchestration is not validated under claude-code agent-teams and may stall (a subagent's completion can fail to route to the orchestrator). Recommend disabling agent-teams for pp-core workflows. See https://github.com/open-gsd/pp-core/issues/1355" >&2
 fi
 ```
 
@@ -634,12 +635,12 @@ Read the `activeHooks` array directly from `PLAN_PRE_HOOKS_JSON` / `HOOKS_JSON`
 **Branch 1 — all plan:pre hooks inactive (`activeHooks` is empty or absent):** Skip to step 6.
 
 **Generic step hook dispatch contract:** For each active entry where `kind == "step"`:
-- If `ref.skill` is set, dispatch with `Skill(skill="gsd-${ref.skill}", args="${PHASE} --auto ${GSD_WS}")` when pipeline mode allows auto-chaining. Prepend `gsd-` to `ref.skill` — `ui-phase` → `pp-ui-phase`.
+- If `ref.skill` is set, dispatch with `Skill(skill="pp-${ref.skill}", args="${PHASE} --auto ${GSD_WS}")` when pipeline mode allows auto-chaining. Prepend `pp-` to `ref.skill` — `ui-phase` → `pp-ui-phase`.
 - If `ref.agent` is set, dispatch with `Agent(prompt=filled_hook_fragment, subagent_type=ref.agent, model="{researcher_model}")`. Use the hook's `fragment.inline` as the prompt body and fill phase fields before spawning.
 - The `research` hook is handled by §5.1's research decision. The `pattern-mapper` hook is handled by §7.8 after `RESEARCH_PATH` is known. Future plan:pre agent hooks use the same `ref.agent` fragment contract.
 
 **AI integration capability:** If the active `ai-integration` step hook is present, `AI_SPEC_PATH` is empty, and the phase goal contains AI keywords (`agent`, `llm`, `rag`, `chatbot`, `embedding`, `langchain`, `llamaindex`, `crewai`, `langgraph`, `openai`, `anthropic`, `vector`, `eval`, `ai system`), then:
-- In pipeline / `--auto` mode, invoke the hook's `ref.skill` via `Skill(skill="gsd-${ref.skill}", args="${PHASE} --auto ${GSD_WS}")`.
+- In pipeline / `--auto` mode, invoke the hook's `ref.skill` via `Skill(skill="pp-${ref.skill}", args="${PHASE} --auto ${GSD_WS}")`.
 - In manual mode, display the existing non-blocking `/pp:ai-integration-phase {N}` recommendation and let the user continue planning without AI-SPEC or stop to run the capability workflow first.
 
 Run the UI deterministic gate whenever **any** `plan:pre` UI hook is active — including the step-only case (`workflow.ui_safety_gate` off). (`check.query` = `"ui.plan-gate"`; router normalizes dots→hyphens.)
@@ -674,7 +675,7 @@ AUTO_CHAIN=$(pp_run query check auto-mode --pick auto_chain_active 2>/dev/null |
 **Branch 5 — `AUTO_CHAIN` is `true` (pipeline / `--auto`):** Fire each active UI **step** hook — runs independently of whether a gate is active (covers `{ui_phase:true,ui_safety_gate:false}`). For each entry in `activeHooks` (in array order) where `kind == "step"` and `ref.skill` is set:
 
 ```
-Skill(skill="gsd-${ref.skill}", args="${PHASE} --auto ${GSD_WS}")
+Skill(skill="pp-${ref.skill}", args="${PHASE} --auto ${GSD_WS}")
 ```
 
 After all UI step hooks return, re-read:
@@ -827,12 +828,13 @@ Continue to step 8.
 
 ## 8. Spawn pp-planner Agent
 
-Display banner:
+Run this Bash command to emit the branded Plan stage banner (renders on stderr, auto-degrades on non-TTY — do NOT print an inline ASCII banner, that would double-print):
+```bash
+pp_run banner plan "PLANNING PHASE {X}"
 ```
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
- pp-core ► PLANNING PHASE {X}
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
+Then announce the spawn:
+```
 ◆ Spawning planner... (runs in a subagent — no output until it returns, ~1–5 min; expected, not a freeze)
 ```
 

package/pp-core/workflows/pr-branch.md

@@ -31,12 +31,13 @@ if [ "$AHEAD" = "0" ]; then
 fi
 ```
 
-Display:
+Run this Bash command to emit the branded Deploy stage banner (renders on stderr, auto-degrades on non-TTY — do NOT print an inline ASCII banner, that would double-print):
+```bash
+pp_run banner deploy "PR BRANCH"
 ```
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
- pp-core ► PR BRANCH
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
+Then display the branch summary:
+```
 Branch: {CURRENT_BRANCH}
 Target: {TARGET}
 Commits: {AHEAD} ahead

package/pp-core/workflows/reapply-patches.md

@@ -1,6 +1,6 @@
 # Reapply Local Patches Workflow
 
-Invoked by `/pp:update --reapply` (`commands/gsd/update.md`).
+Invoked by `/pp:update --reapply` (`commands/pp-update.md`).
 
 After a pp-core update wipes and reinstalls files, this workflow merges user's previously saved local modifications back into the new version. Uses three-way comparison (pristine baseline, user-modified backup, newly installed version) to reliably distinguish user customizations from version drift.
 

package/pp-core/workflows/ship.md

@@ -442,7 +442,7 @@ Read the `activeHooks` array directly from `SHIP_POST_HOOKS_JSON` in-context (do
   ```
 
   `Agent(subagent_type=ref.agent, prompt="Ship-time capability hook for phase ${PHASE_NUMBER}. Phase dir: ${PHASE_DIR}. Consume: ${consumed_files}. Follow your agent instructions.", model="{balanced_model}")`
-- If `ref.skill` is set, apply **prefix-aware resolution**: if `ref.skill` already begins with a runtime-resolvable stem (e.g. `pareto-`), dispatch it verbatim with no phase/workspace args — `Skill(skill=ref.skill)` — because the skill handles its own invocation (e.g. `pareto-sync-board` triggers bare). Otherwise, fall back to the existing stem behavior: `Skill(skill="gsd-${ref.skill}", args="${PHASE_NUMBER} --auto ${GSD_WS}")`. This prevents a `pareto-` skill from being incorrectly prefixed to a non-existent `gsd-pareto-*` name.
+- If `ref.skill` is set, apply **prefix-aware resolution**: if `ref.skill` already begins with a runtime-resolvable stem (e.g. `pareto-`), dispatch it verbatim with no phase/workspace args — `Skill(skill=ref.skill)` — because the skill handles its own invocation (e.g. `pareto-sync-board` triggers bare). Otherwise, fall back to the existing stem behavior: `Skill(skill="pp-${ref.skill}", args="${PHASE_NUMBER} --auto ${GSD_WS}")`. This prevents a `pareto-` skill from being incorrectly prefixed to a non-existent `pp-pareto-*` name.
 
 Each dispatch is best-effort: if it errors, record a warning and continue — never re-raise (`onError: skip`).
 </step>

package/pp-core/workflows/thread.md

@@ -1,6 +1,6 @@
 # Thread Workflow
 
-Invoked by `/pp:thread` (`commands/gsd/thread.md`).
+Invoked by `/pp:thread` (`commands/pp-thread.md`).
 
 Create, list, close, or resume persistent context threads for cross-session work.
 

package/pp-core/workflows/verify-work.md

@@ -467,7 +467,7 @@ Resolve active step hooks from `VERIFY_POST_HOOKS_JSON` where `kind == "step"` a
 If an active secure-phase step hook exists AND `SECURITY_FILE` is empty, dispatch the registry-provided skill stem:
 
 ```
-Skill(skill="gsd-${ref.skill}", args="{phase}")
+Skill(skill="pp-${ref.skill}", args="{phase}")
 ```
 
 After the skill returns, refresh `SECURITY_FILE`:
@@ -619,12 +619,13 @@ On return:
 <step name="verify_gap_plans">
 **Verify fix plans with checker:**
 
-Display:
+Run this Bash command to emit the branded Validate stage banner (renders on stderr, auto-degrades on non-TTY — do NOT print an inline ASCII banner, that would double-print):
+```bash
+pp_run banner validate "VERIFYING"
 ```
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
- pp-core ► VERIFYING FIX PLANS
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
+Then announce the spawn:
+```
 ◆ Spawning plan checker... (runs in a subagent — no output until it returns, ~1–5 min; expected, not a freeze)
 ```