@bhargavvc/sdd-cc 1.30.1 → 1.42.3

package/sdd/workflows/execute-phase.md

@@ -8,13 +8,13 @@ Orchestrator coordinates, not executes. Each subagent loads the full execute-pla
 
 <runtime_compatibility>
 **Subagent spawning is runtime-specific:**
-- **Claude Code:** Uses `Task(subagent_type="sdd-executor", ...)` — blocks until complete, returns result
+- **Claude Code:** Uses `Agent(subagent_type="sdd-executor", ...)` — blocks until complete, returns result
 - **Copilot:** Subagent spawning does not reliably return completion signals. **Default to
   sequential inline execution**: read and follow execute-plan.md directly for each plan
   instead of spawning parallel agents. Only attempt parallel spawning if the user
   explicitly requests it — and in that case, rely on the spot-check fallback in step 3
   to detect completion.
-- **Other runtimes:** If `Task`/`task` tool is unavailable, use sequential inline execution as the
+- **Other runtimes:** If `Agent`/`agent` tool is unavailable, use sequential inline execution as the
   fallback. Check for tool availability at runtime rather than assuming based on runtime name.
 
 **Fallback rule:** If a spawned agent completes its work (commits visible, SUMMARY.md exists) but
@@ -25,6 +25,9 @@ via filesystem and git state.
 
 <required_reading>
 Read STATE.md before any operation to load project context.
+@~/.claude/sdd/references/agent-contracts.md
+@~/.claude/sdd/references/context-budget.md
+@~/.claude/sdd/references/gates.md
 </required_reading>
 
 <available_agent_types>
@@ -53,6 +56,8 @@ Parse `$ARGUMENTS` before loading any context:
 - First positional token → `PHASE_ARG`
 - Optional `--wave N` → `WAVE_FILTER`
 - Optional `--gaps-only` keeps its current meaning
+- Optional `--cross-ai` → `CROSS_AI_FORCE=true` (force all plans through cross-AI execution)
+- Optional `--no-cross-ai` → `CROSS_AI_DISABLED=true` (disable cross-AI for this run, overrides config and frontmatter)
 
 If `--wave` is absent, preserve the current behavior of executing all incomplete waves in the phase.
 </step>
@@ -61,12 +66,64 @@ If `--wave` is absent, preserve the current behavior of executing all incomplete
 Load all context in one call:
 
 ```bash
-INIT=$(node "$HOME/.claude/sdd/bin/sdd-tools.cjs" init execute-phase "${PHASE_ARG}")
+INIT=$(sdd-sdk query init.execute-phase "${PHASE_ARG}")
 if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
-AGENT_SKILLS=$(node "$HOME/.claude/sdd/bin/sdd-tools.cjs" agent-skills sdd-executor 2>/dev/null)
+AGENT_SKILLS=$(sdd-sdk query agent-skills sdd-executor)
 ```
 
-Parse JSON for: `executor_model`, `verifier_model`, `commit_docs`, `parallelization`, `branching_strategy`, `branch_name`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `plans`, `incomplete_plans`, `plan_count`, `incomplete_count`, `state_exists`, `roadmap_exists`, `phase_req_ids`.
+Parse JSON for: `executor_model`, `verifier_model`, `commit_docs`, `parallelization`, `branching_strategy`, `branch_name`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `plans`, `incomplete_plans`, `plan_count`, `incomplete_count`, `state_exists`, `roadmap_exists`, `phase_req_ids`, `response_language`.
+
+**Model resolution:** If `executor_model` is `"inherit"`, omit the `model=` parameter from all `Agent()` calls — do NOT pass `model="inherit"` to Agent. Omitting the `model=` parameter causes Claude Code to inherit the current orchestrator model automatically. Only set `model=` when `executor_model` is an explicit model name (e.g., `"claude-sonnet-4-6"`, `"claude-opus-4-7"`).
+
+**If `response_language` is set:** Include `response_language: {value}` in all spawned subagent prompts so any user-facing output stays in the configured language.
+
+Read runtime/worktree config and fail closed before any executor dispatch:
+
+```bash
+RUNTIME=$(sdd-sdk query config-get runtime --default claude 2>/dev/null || echo "claude")
+USE_WORKTREES=$(sdd-sdk query config-get workflow.use_worktrees 2>/dev/null || echo "true")
+EXECUTOR_STALL_INTERVAL_MINUTES=$(sdd-sdk query config-get executor.stall_detect_interval_minutes 2>/dev/null || echo "5")
+EXECUTOR_STALL_THRESHOLD_MINUTES=$(sdd-sdk query config-get executor.stall_threshold_minutes 2>/dev/null || echo "10")
+
+if [ "$RUNTIME" = "codex" ] && [ "$USE_WORKTREES" != "false" ]; then
+  echo "FATAL: Codex execute-phase worktree isolation is unsupported. Set workflow.use_worktrees=false or use a runtime with Agent isolation=\"worktree\" support." >&2
+  exit 1
+fi
+```
+Codex maps subagents to `spawn_agent`, which has no direct Codex mapping for Claude Code's `isolation="worktree"` parameter. Failing closed prevents main-checkout edits while the workflow believes agents are isolated.
+
+If the project uses git submodules, worktree isolation is unsafe **only when a plan touches a submodule path** — the executor commit protocol cannot correctly handle submodule commits inside isolated worktrees. The previous behavior unconditionally disabled worktree isolation whenever `.gitmodules` existed, which penalised every plan in a submodule project even when the plan was nowhere near a submodule. Compute submodule paths once and intersect them per-plan with the plan's declared `files_modified` frontmatter.
+
+```bash
+# Parse submodule paths from .gitmodules once (empty if no .gitmodules).
+# SUBMODULE_PATHS is a newline-separated list of repo-relative paths.
+if [ -f .gitmodules ]; then
+  SUBMODULE_PATHS=$(git config --file .gitmodules --get-regexp '^submodule\..*\.path$' 2>/dev/null | awk '{print $2}')
+else
+  SUBMODULE_PATHS=""
+fi
+```
+
+`SUBMODULE_PATHS` is exported to the `execute_waves` step, where the per-plan decision actually happens (see "Per-plan worktree decision" sub-step inside `execute_waves`). The decision is per-plan because different plans in the same wave can touch different files — only plans whose paths intersect a submodule must drop worktree isolation; plans nowhere near a submodule keep parallel isolation.
+
+When `USE_WORKTREES` (project-level) is `false`, all executor agents run without `isolation="worktree"` — they execute sequentially on the main working tree instead of in parallel worktrees. The per-plan decision below has no effect when worktrees are project-disabled.
+
+Read context window size for adaptive prompt enrichment:
+
+```bash
+CONTEXT_WINDOW=$(sdd-sdk query config-get context_window 2>/dev/null || echo "200000")
+```
+
+When `CONTEXT_WINDOW >= 500000` (1M-class models), subagent prompts include richer context:
+- Executor agents receive prior wave SUMMARY.md files and the phase CONTEXT.md/RESEARCH.md
+- Verifier agents receive all PLAN.md, SUMMARY.md, CONTEXT.md files plus REQUIREMENTS.md
+- This enables cross-phase awareness and history-aware verification
+
+When `CONTEXT_WINDOW < 200000` (sub-200K models), subagent prompts are thinned to reduce static overhead:
+- Executor agents omit extended deviation rule examples and checkpoint examples from inline prompt — load on-demand via @~/.claude/sdd/references/executor-examples.md
+- Planner agents omit extended anti-pattern lists and specificity examples from inline prompt — load on-demand via @~/.claude/sdd/references/planner-antipatterns.md
+- Core rules and decision logic remain inline; only verbose examples and edge-case lists are extracted
+- This reduces executor static overhead by ~40% while preserving behavioral correctness
 
 **If `phase_found` is false:** Error — phase directory not found.
 **If `plan_count` is 0:** Error — no plans found in phase.
@@ -76,7 +133,7 @@ When `parallelization` is false, plans within a wave execute sequentially.
 
 **Runtime detection for Copilot:**
 Check if the current runtime is Copilot by testing for the `@sdd-executor` agent pattern
-or absence of the `Task()` subagent API. If running under Copilot, force sequential inline
+or absence of the `Agent()` subagent API. If running under Copilot, force sequential inline
 execution regardless of the `parallelization` setting — Copilot's subagent completion
 signals are unreliable (see `<runtime_compatibility>`). Set `COPILOT_SEQUENTIAL=true`
 internally and skip the `execute_waves` step in favor of `check_interactive_mode`'s
@@ -86,9 +143,73 @@ inline path for each plan.
 ```bash
 # REQUIRED: prevents stale auto-chain from previous --auto runs
 if [[ ! "$ARGUMENTS" =~ --auto ]]; then
-  node "$HOME/.claude/sdd/bin/sdd-tools.cjs" config-set workflow._auto_chain_active false 2>/dev/null
+  sdd-sdk query config-set workflow._auto_chain_active false || true
 fi
 ```
+
+Resolve `MVP_MODE` once via the centralized `phase.mvp-mode` query verb (precedence chain: CLI flag → ROADMAP `**Mode:** mvp` → `workflow.mvp_mode` config → false):
+```bash
+MVP_FLAG_ARG=""
+if [[ "$ARGUMENTS" =~ (^|[[:space:]])--mvp([[:space:]]|$) ]]; then MVP_FLAG_ARG="--cli-flag"; fi
+MVP_MODE=$(sdd-sdk query phase.mvp-mode "${PHASE_NUMBER}" $MVP_FLAG_ARG --pick active)
+TDD_MODE=$(sdd-sdk query config-get workflow.tdd_mode 2>/dev/null || echo "false")
+```
+
+<step name="safe_resume_gate">
+Before trusting `STATE.md` or dispatching any executor, derive `CURRENT_PLAN_ID`
+from the active incomplete plan in `INIT`, then search recent history:
+```bash
+CURRENT_PLAN_ID="{phase_number}-{plan_padded}"
+SUMMARY_PATH="{phase_dir}/{plan_padded}-SUMMARY.md"
+PLAN_COMMITS=$(git log --oneline --grep="${CURRENT_PLAN_ID}" -30)
+```
+If production commits exist and `SUMMARY.md is missing`, stop before spawning a
+new executor; continuing risks duplicate work and stale `STATE.md`/ROADMAP progress.
+Offer these recovery options:
+- `close out manually` — inspect commits, write SUMMARY.md, then update STATE/ROADMAP.
+- `re-execute from scratch` — revert or supersede partial commits before dispatch.
+- `mark-and-skip` — record the anomaly and move on only with explicit confirmation.
+</step>
+
+**MVP+TDD gate.** Task-scoped enforcement runs inside plan execution (immediately before each implementation step), where `TASK_FILE`, `PLAN_ID`, and `TASK_ID` are defined. Keep the same predicate and RED-commit contract:
+```bash
+if [ "$MVP_MODE" = "true" ] && [ "$TDD_MODE" = "true" ]; then
+  IS_BEHAVIOR_ADDING=$(sdd-sdk query task.is-behavior-adding "$TASK_FILE" --pick is_behavior_adding)
+  if [ "$IS_BEHAVIOR_ADDING" = "true" ]; then
+    RED_COMMIT=$(git log --oneline --grep="^test(${PHASE_NUMBER}-${PLAN_ID}):" -- "**/*.test.*" "**/*.spec.*" "tests/" | head -1)
+    if [ -z "$RED_COMMIT" ]; then
+      sdd-sdk query state.update last_gate_trip "${PLAN_ID}/${TASK_ID}" || true
+      echo "MVP+TDD GATE TRIPPED: missing RED commit for ${PLAN_ID}/${TASK_ID}"
+      exit 1
+    fi
+  fi
+fi
+```
+Pure doc-only / config-only / test-only tasks return `is_behavior_adding=false` and are exempt. See `execute-mvp-tdd.md` for the halt report format.
+</step>
+
+<step name="check_blocking_antipatterns" priority="first">
+**MANDATORY — Check for blocking anti-patterns before any other work.**
+
+Look for a `.continue-here.md` in the current phase directory:
+
+```bash
+ls ${phase_dir}/.continue-here.md 2>/dev/null || true
+```
+
+If `.continue-here.md` exists, parse its "Critical Anti-Patterns" table for rows with `severity` = `blocking`.
+
+**If one or more `blocking` anti-patterns are found:**
+
+This step cannot be skipped. Before proceeding to `check_interactive_mode` or any other step, the agent must demonstrate understanding of each blocking anti-pattern by answering all three questions for each one:
+
+1. **What is this anti-pattern?** — Describe it in your own words, not by quoting the handoff.
+2. **How did it manifest?** — Explain the specific failure that caused it to be recorded.
+3. **What structural mechanism (not acknowledgment) prevents it?** — Name the concrete step, checklist item, or enforcement mechanism that stops recurrence.
+
+Write these answers inline before continuing. If a blocking anti-pattern cannot be answered from the context in `.continue-here.md`, stop and ask the user for clarification.
+
+**If no `.continue-here.md` exists, or no `blocking` rows are found:** Proceed directly to `check_interactive_mode`.
 </step>
 
 <step name="check_interactive_mode">
@@ -144,9 +265,33 @@ Check `branching_strategy` from init:
 
 **"none":** Skip, continue on current branch.
 
-**"phase" or "milestone":** Use pre-computed `branch_name` from init:
+**"phase" or "milestone":** Use pre-computed `branch_name` from init.
+
+Fork the new phase branch off `origin/HEAD` (the project's default branch), not the current HEAD — otherwise consecutive phases compound and stay unpushed (#2916). If `$BRANCH_NAME` already exists locally, reuse it as-is.
+
 ```bash
-git checkout -b "$BRANCH_NAME" 2>/dev/null || git checkout "$BRANCH_NAME"
+DEFAULT_BRANCH=$(git symbolic-ref --quiet --short refs/remotes/origin/HEAD 2>/dev/null | sed 's|^origin/||')
+DEFAULT_BRANCH=${DEFAULT_BRANCH:-main}
+
+if git show-ref --verify --quiet "refs/heads/$BRANCH_NAME"; then
+  git switch "$BRANCH_NAME" || { echo "ERROR: Could not switch to existing branch '$BRANCH_NAME'." >&2; exit 1; }
+else
+  if ! git fetch --quiet origin "$DEFAULT_BRANCH"; then  # #2916
+    git show-ref --verify --quiet "refs/remotes/origin/$DEFAULT_BRANCH" \
+      || { echo "ERROR: fetch origin/$DEFAULT_BRANCH failed and no local copy exists. Refusing to create '$BRANCH_NAME' off current HEAD (#2916)." >&2; exit 1; }
+    echo "WARNING: fetch origin/$DEFAULT_BRANCH failed; using local copy as base." >&2
+  fi
+  if [ -n "$(git status --porcelain)" ]; then
+    echo "WARNING: Uncommitted changes will be carried onto '$BRANCH_NAME' (branched off origin/$DEFAULT_BRANCH, not previous HEAD)."
+  else
+    git switch --quiet "$DEFAULT_BRANCH" 2>/dev/null && git merge --ff-only --quiet "origin/$DEFAULT_BRANCH" 2>/dev/null || true
+  fi
+  # Pinned base + fail-fast: on success HEAD is exactly at origin/$DEFAULT_BRANCH,
+  # so a post-creation merge-base or "ahead-of" guard would be unreachable. The
+  # explicit base argument here is the single source of correctness for #2916.
+  git checkout -b "$BRANCH_NAME" "origin/$DEFAULT_BRANCH" \
+    || { echo "ERROR: Could not create '$BRANCH_NAME' from origin/$DEFAULT_BRANCH (#2916)." >&2; exit 1; }
+fi
 ```
 
 All subsequent commits go to this branch. User handles merging.
@@ -159,7 +304,7 @@ Report: "Found {plan_count} plans in {phase_dir} ({incomplete_count} incomplete)
 
 **Update STATE.md for phase start:**
 ```bash
-node "$HOME/.claude/sdd/bin/sdd-tools.cjs" state begin-phase --phase "${PHASE_NUMBER}" --name "${PHASE_NAME}" --plans "${PLAN_COUNT}"
+sdd-sdk query state.begin-phase --phase "${PHASE_NUMBER}" --name "${PHASE_NAME}" --plans "${PLAN_COUNT}"
 ```
 This updates Status, Last Activity, Current focus, Current Position, and plan counts in STATE.md so frontmatter and body text reflect the active phase immediately.
 </step>
@@ -168,7 +313,7 @@ This updates Status, Last Activity, Current focus, Current Position, and plan co
 Load plan inventory with wave grouping in one call:
 
 ```bash
-PLAN_INDEX=$(node "$HOME/.claude/sdd/bin/sdd-tools.cjs" phase-plan-index "${PHASE_NUMBER}")
+PLAN_INDEX=$(sdd-sdk query phase-plan-index "${PHASE_NUMBER}")
 ```
 
 Parse JSON for: `phase`, `plans[]` (each with `id`, `wave`, `autonomous`, `objective`, `files_modified`, `task_count`, `has_summary`), `waves` (map of wave number → plan IDs), `incomplete`, `has_checkpoints`.
@@ -194,14 +339,147 @@ Report:
 ```
 </step>
 
+<step name="cross_ai_delegation">
+**Optional step 2.5 — Delegate plans to an external AI runtime.**
+
+This step runs after plan discovery and before normal wave execution. It identifies plans
+that should be delegated to an external AI command and executes them via stdin-based prompt
+delivery. Plans handled here are removed from the execute_waves plan list so the normal
+executor skips them.
+
+**Activation logic:**
+
+1. If `CROSS_AI_DISABLED` is true (`--no-cross-ai` flag): skip this step entirely.
+2. If `CROSS_AI_FORCE` is true (`--cross-ai` flag): mark ALL incomplete plans for cross-AI execution.
+3. Otherwise: check each plan's frontmatter for `cross_ai: true` AND verify config
+   `workflow.cross_ai_execution` is `true`. Plans matching both conditions are marked for cross-AI.
+
+```bash
+CROSS_AI_ENABLED=$(sdd-sdk query config-get workflow.cross_ai_execution 2>/dev/null || echo "false")
+CROSS_AI_CMD=$(sdd-sdk query config-get workflow.cross_ai_command 2>/dev/null || echo "")
+CROSS_AI_TIMEOUT=$(sdd-sdk query config-get workflow.cross_ai_timeout 2>/dev/null || echo "300")
+```
+
+**If no plans are marked for cross-AI:** Skip to execute_waves.
+
+**If plans are marked but `cross_ai_command` is empty:** Error — tell user to set
+`workflow.cross_ai_command` via `sdd-sdk query config-set workflow.cross_ai_command "<command>"`.
+
+**For each cross-AI plan (sequentially):**
+
+1. **Construct the task prompt** from the plan file:
+   - Extract `<objective>` and `<tasks>` sections from the PLAN.md
+   - Append PROJECT.md context (project name, description, tech stack)
+   - Format as a self-contained execution prompt
+
+2. **Check for dirty working tree before execution:**
+   ```bash
+   if ! git diff --quiet HEAD 2>/dev/null; then
+     echo "WARNING: dirty working tree detected — the external AI command may produce uncommitted changes that conflict with existing modifications"
+   fi
+   ```
+
+3. **Run the external command** from the project root, writing the prompt to stdin.
+   Never shell-interpolate the prompt — always pipe via stdin to prevent injection:
+   ```bash
+   echo "$TASK_PROMPT" | timeout "${CROSS_AI_TIMEOUT}s" ${CROSS_AI_CMD} > "$CANDIDATE_SUMMARY" 2>"$ERROR_LOG"
+   EXIT_CODE=$?
+   ```
+
+4. **Evaluate the result:**
+
+   **Success (exit 0 + valid summary):**
+   - Read `$CANDIDATE_SUMMARY` and validate it contains meaningful content
+     (not empty, has at least a heading and description — a valid SUMMARY.md structure)
+   - Write it as the plan's SUMMARY.md file
+   - Update STATE.md plan status to complete
+   - Update ROADMAP.md progress
+   - Mark plan as handled — skip it in execute_waves
+
+   **Failure (non-zero exit or invalid summary):**
+   - Display the error output and exit code
+   - Warn: "The external command may have left uncommitted changes or partial edits
+     in the working tree. Review `git status` and `git diff` before proceeding."
+   - Offer three choices:
+     - **retry** — run the same plan through cross-AI again
+     - **skip** — fall back to normal executor for this plan (re-add to execute_waves list)
+     - **abort** — stop execution entirely, preserve state for resume
+
+5. **After all cross-AI plans processed:** Remove successfully handled plans from the
+   incomplete plan list so execute_waves skips them. Any skipped-to-fallback plans remain
+   in the list for normal executor processing.
+</step>
+
 <step name="execute_waves">
 Execute each selected wave in sequence. Within a wave: parallel if `PARALLELIZATION=true`, sequential if `false`.
 
+**Stream-idle-timeout prevention — checkpoint heartbeats (#2410):**
+
+Multi-plan phases can accumulate enough subagent context that the Claude API
+SSE layer terminates with `Stream idle timeout - partial response received`
+between a large tool_result and the next assistant turn (seen on Claude Code
++ Opus 4.7 at ~200K+ cache_read). To keep the stream warm, emit short
+assistant-text heartbeats — **no tool call, just a literal line** — at every
+wave and plan boundary. Each heartbeat MUST start with `[checkpoint]` so
+tooling and `/sdd:manager`'s background-completion handler can grep partial
+transcripts. `{P}/{Q}` is the phase-wide completed/total plans counter and
+increases monotonically across waves. `{status}` is `complete` (success),
+`failed` (executor error), or `checkpoint` (human-gate returned).
+
+```
+[checkpoint] phase {PHASE_NUMBER} wave {N}/{M} starting, {wave_plan_count} plan(s), {P}/{Q} plans done
+[checkpoint] phase {PHASE_NUMBER} wave {N}/{M} plan {plan_id} starting ({P}/{Q} plans done)
+[checkpoint] phase {PHASE_NUMBER} wave {N}/{M} plan {plan_id} {status} ({P}/{Q} plans done)
+[checkpoint] phase {PHASE_NUMBER} wave {N}/{M} complete, {P}/{Q} plans done ({wave_success}/{wave_plan_count} ok)
+```
+
 **For each wave:**
 
-1. **Describe what's being built (BEFORE spawning):**
+1. **Intra-wave files_modified overlap check (BEFORE spawning):**
+
+   Before spawning any agents for this wave, inspect the `files_modified` list of all plans
+   in the wave. Check every pair of plans in the wave — if any two plans share even one file
+   in their `files_modified` lists, those plans have an implicit dependency and MUST NOT run
+   in parallel.
+
+   **Detection algorithm (pseudocode):**
+   ```
+   seen_files = {}
+   overlapping_plans = []
+   for each plan in wave_plans:
+     for each file in plan.files_modified:
+       if file in seen_files:
+         overlapping_plans.add(plan, seen_files[file])  # both plans overlap on this file
+       else:
+         seen_files[file] = plan
+   ```
+
+   **If overlap is detected:**
+   - Warn the user:
+     ```
+     ⚠ Intra-wave files_modified overlap detected in Wave {N}:
+       Plan {A} and Plan {B} both modify {file}
+       Running these plans sequentially to avoid parallel worktree conflicts.
+     ```
+   - Override `PARALLELIZATION` to `false` for this wave only — run all plans in the wave
+     sequentially regardless of the global parallelization setting.
+   - This is a safety net for plans that were incorrectly assigned to the same wave.
+     The planner should have caught this; flag it as a planning defect so the user can
+     replan the phase if desired.
+
+   **If no overlap:** proceed normally (parallel if `PARALLELIZATION=true`).
+
+2. **Describe what's being built (BEFORE spawning):**
 
-   Read each plan's `<objective>`. Extract what's being built and why.
+   **First, emit the wave-start checkpoint heartbeat as a literal assistant-text
+   line — no tool call (#2410). Do NOT skip this even for single-plan waves; it
+   is required before any further reasoning or spawning:**
+
+   ```
+   [checkpoint] phase {PHASE_NUMBER} wave {N}/{M} starting, {wave_plan_count} plan(s), {P}/{Q} plans done
+   ```
+
+   Then read each plan's `<objective>`. Extract what's being built and why.
 
    ```
    ---
@@ -217,29 +495,107 @@ Execute each selected wave in sequence. Within a wave: parallel if `PARALLELIZAT
    - Bad: "Executing terrain generation plan"
    - Good: "Procedural terrain generator using Perlin noise — creates height maps, biome zones, and collision meshes. Required before vehicle physics can interact with ground."
 
-2. **Spawn executor agents:**
+2.5. **Per-plan worktree decision (run for each plan in this wave BEFORE its dispatch):**
+
+   Read and execute `sdd/workflows/execute-phase/steps/per-plan-worktree-gate.md` for each plan. It extracts `PLAN_FILES` from the plan's JSON, intersects against `SUBMODULE_PATHS` (with normalization, bidirectional matching, and glob-prefix handling), and sets `USE_WORKTREES_FOR_PLAN` to `false` when the plan touches a submodule path. Append `plan_id` to a `WAVE_WORKTREE_PLANS` accumulator when `USE_WORKTREES_FOR_PLAN != false`.
+
+   The dispatch branches in step 3 below MUST gate on `USE_WORKTREES_FOR_PLAN` for the current plan, not on the project-level `USE_WORKTREES`.
+
+3. **Spawn executor agents:**
+
+   **Emit a plan-start heartbeat (literal line, no tool call) immediately before
+   each `Agent()` dispatch (#2410):**
+
+   `[checkpoint] phase {PHASE_NUMBER} wave {N}/{M} plan {plan_id} starting ({P}/{Q} plans done)`
 
    Pass paths only — executors read files themselves with their fresh context window.
    For 200k models, this keeps orchestrator context lean (~10-15%).
    For 1M+ models (Opus 4.6, Sonnet 4.6), richer context can be passed directly.
 
+   **Worktree mode** (`USE_WORKTREES_FOR_PLAN` is not `false` — evaluated per-plan in step 2.5):
+
+   Before spawning, capture the current HEAD:
+   ```bash
+   EXPECTED_BASE=$(git rev-parse HEAD)
+   DISPATCH_TS=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
+   EXPECTED_BRANCH=$(git rev-parse --abbrev-ref HEAD)
+   if [ "${USE_WORKTREES_FOR_PLAN:-true}" != "false" ] && [ -z "${WAVE_WORKTREE_MANIFEST:-}" ]; then
+     WAVE_WORKTREE_MANIFEST=$(mktemp "${TMPDIR:-/tmp}/sdd-worktree-wave-XXXXXX.json")
+     printf '{"worktrees":[]}\n' > "$WAVE_WORKTREE_MANIFEST"
+     export WAVE_WORKTREE_MANIFEST
+   fi
    ```
-   Task(
+
+   **Sequential dispatch for parallel execution (waves with 2+ agents):**
+   Dispatch each `Agent()` call **one at a time with `run_in_background: true`**. Do NOT
+   send all Agent calls in a single message: simultaneous `git worktree add` calls race
+   on `.git/config.lock`. Agents still run in parallel once their worktrees are created.
+
+   ```text
+   # CORRECT: one Agent() per message with run_in_background: true
+   # WRONG: multiple Agent() calls in one message -> .git/config.lock contention
+   ```
+
+   ```text
+   Agent(
      subagent_type="sdd-executor",
-     model="{executor_model}",
+     description="Execute plan {plan_number} of phase {phase_number}",
+     # Only include model= when executor_model is an explicit model name.
+     # When executor_model is "inherit", omit this parameter entirely so
+     # Claude Code inherits the orchestrator model automatically.
+     model="{executor_model}",  # omit this line when executor_model == "inherit"
      isolation="worktree",
      prompt="
        <objective>
        Execute plan {plan_number} of phase {phase_number}-{phase_name}.
-       Commit each task atomically. Create SUMMARY.md. Update STATE.md and ROADMAP.md.
+       Commit each task atomically. Create SUMMARY.md.
+       Do NOT update STATE.md or ROADMAP.md — the orchestrator owns those writes after all worktree agents in the wave complete.
        </objective>
 
+       <worktree_branch_check>
+       FIRST ACTION: HEAD assertion MUST run before any reset/checkout. Worktrees
+       spawned by Claude Code's `isolation="worktree"` use the `worktree-agent-<id>`
+       namespace. If HEAD is on a protected ref (main/master/develop/trunk/release/*)
+       or detached, HALT — do NOT self-recover by force-rewinding via `git update-ref`,
+       that destroys concurrent commits in multi-active scenarios (#2924). Only after
+       Step 1 passes is `git reset --hard` safe (#2015 — affects all platforms).
+       ```bash
+       HEAD_REF=$(git symbolic-ref --quiet HEAD || echo "DETACHED")
+       ACTUAL_BRANCH=$(git rev-parse --abbrev-ref HEAD)
+       if [ "$HEAD_REF" = "DETACHED" ] || echo "$ACTUAL_BRANCH" | grep -Eq '^(main|master|develop|trunk|release/.*)$'; then
+         echo "FATAL: worktree HEAD on '$ACTUAL_BRANCH' (expected worktree-agent-*); refusing to self-recover via 'git update-ref' (#2924)." >&2
+         exit 1
+       fi
+       if ! echo "$ACTUAL_BRANCH" | grep -Eq '^worktree-agent-[A-Za-z0-9._/-]+$'; then
+         echo "FATAL: worktree HEAD '$ACTUAL_BRANCH' is not in the worktree-agent-* namespace; refusing to commit (#2924)." >&2
+         exit 1
+       fi
+       ACTUAL_BASE=$(git merge-base HEAD {EXPECTED_BASE})
+       if [ "$ACTUAL_BASE" != "{EXPECTED_BASE}" ]; then
+         git reset --hard {EXPECTED_BASE}
+         [ "$(git rev-parse HEAD)" != "{EXPECTED_BASE}" ] && { echo "ERROR: could not correct worktree base"; exit 1; }
+       fi
+       ```
+       Per-commit HEAD/cwd-drift/path-guard: `agents/sdd-executor.md` steps 0/0a/0b + `references/worktree-path-safety.md` (in <execution_context>).
+       </worktree_branch_check>
+
        <parallel_execution>
-       You are running as a PARALLEL executor agent. Use --no-verify on all git
-       commits to avoid pre-commit hook contention with other agents. The
-       orchestrator validates hooks once after all agents complete.
-       For sdd-tools commits: add --no-verify flag.
-       For direct git commits: use git commit --no-verify -m "..."
+       You are running as a PARALLEL executor agent in a git worktree. Worktree path safety (cwd-drift, absolute-path guards) is in `worktree-path-safety.md` (loaded below).
+       Run `git commit` normally — hooks run by default. Do NOT pass `--no-verify`
+       unless the orchestrator surfaces `workflow.worktree_skip_hooks=true` in this
+       prompt; silent bypass violates project CLAUDE.md guidance (#2924).
+
+       IMPORTANT: Do NOT modify STATE.md or ROADMAP.md. execute-plan.md
+       auto-detects worktree mode (`.git` is a file, not a directory) and skips
+       shared file updates automatically. The orchestrator updates them centrally
+       after merge.
+
+       REQUIRED: SUMMARY.md MUST be committed before you return. In worktree mode the
+       git_commit_metadata step in execute-plan.md commits SUMMARY.md and REQUIREMENTS.md
+       only (STATE.md and ROADMAP.md are excluded automatically). Do NOT skip or defer
+       this commit — the orchestrator force-removes the worktree after you return, and
+       any uncommitted SUMMARY.md will be permanently lost (#2070).
+       REQUIRED ORDER: Write SUMMARY.md → commit → only then any narration. No text between Write and commit (truncation risk; #2070 rescue is not primary defense).
        </parallel_execution>
 
        <execution_context>
@@ -247,6 +603,8 @@ Execute each selected wave in sequence. Within a wave: parallel if `PARALLELIZAT
        @~/.claude/sdd/templates/summary.md
        @~/.claude/sdd/references/checkpoints.md
        @~/.claude/sdd/references/tdd.md
+       @~/.claude/sdd/references/worktree-path-safety.md
+       ${CONTEXT_WINDOW < 200000 ? '' : '@~/.claude/sdd/references/executor-examples.md'}
        </execution_context>
 
        <files_to_read>
@@ -255,6 +613,11 @@ Execute each selected wave in sequence. Within a wave: parallel if `PARALLELIZAT
        - .planning/PROJECT.md (Project context — core value, requirements, evolution rules)
        - .planning/STATE.md (State)
        - .planning/config.json (Config, if exists)
+       ${CONTEXT_WINDOW >= 500000 ? `
+       - ${phase_dir}/*-CONTEXT.md (User decisions from discuss-phase — honors locked choices)
+       - ${phase_dir}/*-RESEARCH.md (Technical research — pitfalls and patterns to follow)
+       - ${prior_wave_summaries} (SUMMARY.md files from earlier waves in this phase — what was already built)
+       ` : ''}
        - ./CLAUDE.md (Project instructions, if exists — follow project-specific guidelines and coding conventions)
        - .claude/skills/ or .agents/skills/ (Project skills, if either exists — list skills, read SKILL.md for each, follow relevant rules during implementation)
        </files_to_read>
@@ -272,16 +635,55 @@ Execute each selected wave in sequence. Within a wave: parallel if `PARALLELIZAT
        - [ ] All tasks executed
        - [ ] Each task committed individually
        - [ ] SUMMARY.md created in plan directory
-       - [ ] STATE.md updated with position and decisions
-       - [ ] ROADMAP.md updated with plan progress (via `roadmap update-plan-progress`)
+       - [ ] No modifications to shared orchestrator artifacts (the orchestrator handles all post-wave shared-file writes)
        </success_criteria>
      "
    )
    ```
 
-3. **Wait for all agents in wave to complete.**
+   Immediately after each worktree `Agent()` spawn returns metadata, atomically append `{agent_id, worktree_path, branch, expected_base}` to `WAVE_WORKTREE_MANIFEST`. If any field is missing, stop and ask for recovery instead of scanning all agent worktrees.
+
+   > **ORCHESTRATOR RULE — CODEX RUNTIME**: After calling Agent() above to spawn executor agent(s), stop working on this task immediately. Do not read more files, edit code, or run tests related to this task while the subagent is active. Wait for the subagent to return its result. This prevents duplicate work, conflicting edits, and wasted context. Only resume when the subagent result is available.
+
+   **Sequential mode** (`USE_WORKTREES_FOR_PLAN` is `false` — either project-level `USE_WORKTREES=false`, or per-plan submodule intersection forced it false in step 2.5):
+
+   Omit `isolation="worktree"` from the Agent call. Replace the `<parallel_execution>` block with:
+
+   ```
+       <sequential_execution>
+       You are running as a SEQUENTIAL executor agent on the main working tree.
+       Use normal git commits (with hooks). Do NOT use --no-verify.
+       REQUIRED ORDER: Write SUMMARY.md → commit → only then any narration. No text between Write and commit (truncation risk; #2070 rescue is not primary defense).
+       </sequential_execution>
+   ```
+
+   The sequential mode Agent prompt uses the same structure as worktree mode but with these differences in success_criteria — since there is only one agent writing at a time, there are no shared-file conflicts:
+
+   ```
+       <success_criteria>
+       - [ ] All tasks executed
+       - [ ] Each task committed individually
+       - [ ] SUMMARY.md created in plan directory
+       - [ ] STATE.md updated with position and decisions
+       - [ ] ROADMAP.md updated with plan progress (via `roadmap update-plan-progress`)
+       </success_criteria>
+   ```
+
+   When worktrees are disabled for a plan (per-plan or project-level), that plan's executor runs on the main working tree. If **any** plan in the current wave dropped to sequential mode, execute the affected plan(s) **one at a time** to avoid concurrent writes to the main working tree — plans in the same wave that retained worktree isolation can still run in parallel alongside the sequential ones, but two non-worktree plans in the same wave must serialize. When the project-level `USE_WORKTREES=false`, all plans in the wave serialize regardless of the `PARALLELIZATION` setting.
+
+4. **Wait for all agents in wave to complete.**
+
+   **Plan-complete heartbeat (#2410):** as each executor returns (or is verified
+   via spot-check below), emit one line — `complete` advances `{P}`, `failed`
+   and `checkpoint` do not but still warm the stream:
 
-   **Completion signal fallback (Copilot and runtimes where Task() may not return):**
+   ```
+   [checkpoint] phase {PHASE_NUMBER} wave {N}/{M} plan {plan_id} complete ({P}/{Q} plans done)
+   [checkpoint] phase {PHASE_NUMBER} wave {N}/{M} plan {plan_id} failed ({P}/{Q} plans done)
+   [checkpoint] phase {PHASE_NUMBER} wave {N}/{M} plan {plan_id} checkpoint ({P}/{Q} plans done)
+   ```
+
+   **Completion signal fallback (Copilot and runtimes where Agent() may not return):**
 
    If a spawned agent does not return a completion signal but appears to have finished
    its work, do NOT block indefinitely. Instead, verify completion via spot-checks:
@@ -290,30 +692,298 @@ Execute each selected wave in sequence. Within a wave: parallel if `PARALLELIZAT
    # For each plan in this wave, check if the executor finished:
    SUMMARY_EXISTS=$(test -f "{phase_dir}/{plan_number}-{plan_padded}-SUMMARY.md" && echo "true" || echo "false")
    COMMITS_FOUND=$(git log --oneline --all --grep="{phase_number}-{plan_padded}" --since="1 hour ago" | head -1)
+   COMMITS_SINCE_DISPATCH=$(git log "${EXPECTED_BRANCH}" --since="${DISPATCH_TS}" --oneline | head -1)
    ```
 
    **If SUMMARY.md exists AND commits are found:** The agent completed successfully —
-   treat as done and proceed to step 4. Log: `"✓ {Plan ID} completed (verified via spot-check — completion signal not received)"`
+   treat as done and proceed to step 5. Log: `"✓ {Plan ID} completed (verified via spot-check — completion signal not received)"`
 
    **If SUMMARY.md does NOT exist after a reasonable wait:** The agent may still be
    running or may have failed silently. Check `git log --oneline -5` for recent
    activity. If commits are still appearing, wait longer. If no activity, report
-   the plan as failed and route to the failure handler in step 5.
+   the plan as failed and route to the failure handler in step 6.
 
-   **This fallback applies automatically to all runtimes.** Claude Code's Task() normally
-   returns synchronously, but the fallback ensures resilience if it doesn't.
+   **Configurable stall surveillance (#3212):** Every `${EXECUTOR_STALL_INTERVAL_MINUTES}`
+   minutes while waiting, inspect `git log "${EXPECTED_BRANCH}" --since="${DISPATCH_TS}"`
+   for activity. If no completion signal, no SUMMARY.md, and no expected-branch
+   commits appear for `${EXECUTOR_STALL_THRESHOLD_MINUTES}` minutes, pause and
+   ask for one recovery path: `continue waiting`, `kill and retry`, or
+   `kill and switch to inline execution`.
 
-4. **Post-wave hook validation (parallel mode only):**
+   **This fallback applies automatically to all runtimes.** Claude Code's Agent() normally
+   returns synchronously, but the fallback ensures resilience if it doesn't.
 
-   When agents committed with `--no-verify`, run pre-commit hooks once after the wave:
+5. **Post-wave hook validation (parallel mode only):** Hooks run on every executor commit by default (#2924); this post-wave run only fires when `workflow.worktree_skip_hooks=true` opted out of per-commit hooks:
    ```bash
-   # Run project's pre-commit hooks on the current state
-   git diff --cached --quiet || git stash  # stash any unstaged changes
-   git hook run pre-commit 2>&1 || echo "⚠ Pre-commit hooks failed — review before continuing"
+   SKIP_HOOKS=$(sdd-sdk query config-get workflow.worktree_skip_hooks 2>/dev/null || echo "false")
+   if [ "$SKIP_HOOKS" = "true" ]; then
+     # Stash uncommitted changes under a named ref so we always pop (bare `git stash` strands them on hook/script failure). #3542: `refs/stash` is shared across worktrees, so this helper runs ONLY in the orchestrator's main checkout after all wave worktrees have been merged + removed; executors are forbidden from running any `git stash` subcommand (see `<destructive_git_prohibition>` in `agents/sdd-executor.md`).
+     STASHED=false
+     if (! git diff --quiet || ! git diff --cached --quiet) && git stash push -u -m "sdd-post-wave-hook-$$" >/dev/null 2>&1; then STASHED=true; fi
+     git hook run pre-commit 2>&1 || echo "⚠ Pre-commit hooks failed — review before continuing"
+     [ "$STASHED" = "true" ] && (git stash pop >/dev/null 2>&1 || echo "⚠ Could not pop sdd-post-wave-hook stash — recover manually")
+   fi
    ```
    If hooks fail: report the failure and ask "Fix hook issues now?" or "Continue to next wave?"
 
-5. **Report completion — spot-check claims first:**
+5.5. **Worktree cleanup (when `isolation="worktree"` was used):**
+
+   **Standard wave contract:** Each wave's worktrees merge to main via the templated path below before the next wave's worktrees fork. The cleanup loop runs once per wave at the end of the wave lifecycle. Worktrees created in wave N must be fully removed before wave N+1 forks new ones.
+
+   **Cross-wave dependency deviation (supported execution mode):** When the orchestrator legitimately deviates from the standard wave model — for example, a phase with cross-wave plan dependencies that requires custom inter-worktree base-update merges (e.g., `merge: bring 09-01 + 09-02 into 09-03 base`) — the cleanup loop below is NOT automatically re-entered for those custom merges. The deviation path produces correct final history but bypasses this loop, leaving `worktree-agent-*` directories in place. Use the **cleanup-tail snippet** below to remove any residual worktrees after such a deviation.
+
+   When executor agents ran in worktree isolation, their commits land on temporary branches in separate working trees. After the wave completes, merge these changes back and clean up:
+
+   **Manifest source of truth (#3384):** Cleanup consumes the `WAVE_WORKTREE_MANIFEST` created and populated during executor dispatch in step 3. Do not recreate or truncate it here.
+
+   Prefer the bounded helper, which validates branch identity, expected base, deletion
+   diffs, merge result, and worktree removal before deleting the temporary branch.
+   If the helper reports a blocked cleanup, resolve the reported manifest entry and
+   rerun the same command. Do not fall back to broad worktree discovery.
+
+   ```bash
+   [ -n "${WAVE_WORKTREE_MANIFEST:-}" ] && [ -f "$WAVE_WORKTREE_MANIFEST" ] || {
+     echo "BLOCKED: missing WAVE_WORKTREE_MANIFEST; refusing broad worktree cleanup (#3384)." >&2
+     exit 1
+   }
+
+   # Guard: pin cleanup back to the primary worktree and fail on branch drift (#3174).
+   PRIMARY_WT=$(git worktree list --porcelain | awk '/^worktree /{print substr($0,10); exit}')
+   if [ -z "$PRIMARY_WT" ]; then
+     echo "FATAL: could not resolve primary worktree before cleanup" >&2
+     exit 1
+   fi
+   if [ -n "$PRIMARY_WT" ] && [ "$(pwd -P 2>/dev/null)" != "$(cd "$PRIMARY_WT" 2>/dev/null && pwd -P)" ]; then echo "⚠ Orchestrator CWD drifted to $(pwd) — pinning to $PRIMARY_WT before worktree cleanup (#3174)"; cd "$PRIMARY_WT" || { echo "FATAL: cannot cd to primary worktree $PRIMARY_WT" >&2; exit 1; }; fi
+   ORCH_BRANCH=$(git rev-parse --abbrev-ref HEAD)
+   [ -z "${EXPECTED_BRANCH:-}" ] || [ "$ORCH_BRANCH" = "$EXPECTED_BRANCH" ] || { echo "FATAL: orchestrator on '$ORCH_BRANCH' but expected '$EXPECTED_BRANCH' before worktree cleanup — refusing to merge (#3174-class drift)" >&2; exit 1; }
+
+   if command -v sdd-sdk >/dev/null 2>&1; then
+     sdd-sdk query worktree.cleanup-wave --manifest "$WAVE_WORKTREE_MANIFEST" || exit 1
+   else
+     echo "WARN: sdd-sdk unavailable; using manifest-scoped shell fallback (#3384)." >&2
+   WT_PATHS_FILE=$(mktemp "${TMPDIR:-/tmp}/sdd-worktree-paths-XXXXXX")
+   node -e 'const fs=require("fs");const p=process.env.WAVE_WORKTREE_MANIFEST;try{if(!p)throw new Error("WAVE_WORKTREE_MANIFEST is unset");if(!fs.existsSync(p))throw new Error("manifest does not exist");const s=fs.readFileSync(p,"utf8");if(!s.trim())throw new Error("manifest is empty");const j=JSON.parse(s);for(const w of j.worktrees||[])if(w.worktree_path)console.log(w.worktree_path)}catch(e){console.error(`ERROR: cannot read worktree manifest ${p||"(unset)"}: ${e.message}`);process.exit(1)}' > "$WT_PATHS_FILE" || { echo "BLOCKED: cannot read WAVE_WORKTREE_MANIFEST; refusing cleanup (#3384)." >&2; exit 1; }
+   while IFS= read -r WT; do
+     [ -z "$WT" ] && continue
+     WT_BRANCH=$(git -C "$WT" rev-parse --abbrev-ref HEAD 2>/dev/null)
+     if [ -n "$WT_BRANCH" ] && [ "$WT_BRANCH" != "HEAD" ]; then
+       CURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
+       STATE_BACKUP=$(mktemp)
+       ROADMAP_BACKUP=$(mktemp)
+       [ -f .planning/STATE.md ] && cp .planning/STATE.md "$STATE_BACKUP" || true
+       [ -f .planning/ROADMAP.md ] && cp .planning/ROADMAP.md "$ROADMAP_BACKUP" || true
+       DELETIONS=$(git diff --diff-filter=D --name-only HEAD..."$WT_BRANCH" 2>/dev/null || true)
+       if [ -n "$DELETIONS" ]; then
+         echo "BLOCKED: Worktree branch $WT_BRANCH contains file deletions: $DELETIONS"
+         echo "Review these deletions before merging. If intentional, remove this guard and re-run."
+         rm -f "$STATE_BACKUP" "$ROADMAP_BACKUP"
+         continue
+       fi
+       git merge "$WT_BRANCH" --no-ff --no-edit -m "chore: merge executor worktree ($WT_BRANCH)" 2>&1 || {
+         echo "⚠ Merge conflict from worktree $WT_BRANCH — resolve manually"
+         echo "  STATE.md backup:   $STATE_BACKUP"
+         echo "  ROADMAP.md backup: $ROADMAP_BACKUP"
+         echo "  Restore with: cp \$STATE_BACKUP .planning/STATE.md && cp \$ROADMAP_BACKUP .planning/ROADMAP.md"
+         break
+       }
+       MERGE_DEL_COUNT=$(git diff --diff-filter=D --name-only HEAD~1 HEAD 2>/dev/null | grep -vc '^\.planning/' || true)
+       if [ "$MERGE_DEL_COUNT" -gt 5 ] && [ "${ALLOW_BULK_DELETE:-0}" != "1" ]; then
+         MERGE_DELETIONS=$(git diff --diff-filter=D --name-only HEAD~1 HEAD 2>/dev/null | grep -v '^\.planning/' || true)
+         echo "⚠ BLOCKED: Merge of $WT_BRANCH deleted $MERGE_DEL_COUNT files outside .planning/ — reverting to protect repository integrity (#2384)"
+         echo "$MERGE_DELETIONS"
+         echo "  If these deletions are intentional, re-run with ALLOW_BULK_DELETE=1"
+         git reset --hard HEAD~1 2>/dev/null || true
+         rm -f "$STATE_BACKUP" "$ROADMAP_BACKUP"
+         continue
+       fi
+       if [ -s "$STATE_BACKUP" ]; then
+         cp "$STATE_BACKUP" .planning/STATE.md
+       fi
+       if [ -s "$ROADMAP_BACKUP" ]; then
+         cp "$ROADMAP_BACKUP" .planning/ROADMAP.md
+       fi
+       rm -f "$STATE_BACKUP" "$ROADMAP_BACKUP"
+       # Detect files deleted on main but re-added by worktree merge (#2501).
+       DELETED_FILES=$(git diff --diff-filter=A --name-only HEAD~1 -- .planning/ 2>/dev/null || true)
+       for RESURRECTED in $DELETED_FILES; do
+         WAS_DELETED=$(git log --follow --diff-filter=D --name-only --format="" HEAD~1 -- "$RESURRECTED" 2>/dev/null | grep -c . || true)
+         if [ "${WAS_DELETED:-0}" -gt 0 ]; then
+           git rm -f "$RESURRECTED" 2>/dev/null || true
+         fi
+       done
+       if ! git diff --quiet .planning/STATE.md .planning/ROADMAP.md 2>/dev/null || \
+          [ -n "$DELETED_FILES" ]; then
+         COMMIT_DOCS=$(sdd-sdk query config-get commit_docs 2>/dev/null || echo "true")
+         if [ "$COMMIT_DOCS" != "false" ]; then
+           git add .planning/STATE.md .planning/ROADMAP.md 2>/dev/null || true
+           git commit --amend --no-edit 2>/dev/null || true
+         fi
+       fi
+       # Safety net: rescue uncommitted SUMMARY.md before worktree removal (#2070, #2838).
+       while IFS= read -r SUMMARY; do
+         [ -z "$SUMMARY" ] && continue
+         REL_PATH="${SUMMARY#$WT/}"
+         if [ ! -f "$REL_PATH" ] || ! cmp -s "$SUMMARY" "$REL_PATH"; then
+           mkdir -p "$(dirname "$REL_PATH")"
+           cp "$SUMMARY" "$REL_PATH"
+           echo "⚠ Rescued $REL_PATH from worktree before removal"
+         fi
+       done < <(find "$WT/.planning" -name "*SUMMARY.md" 2>/dev/null)
+       REMOVE_OK=false
+       if git worktree remove "$WT" --force; then
+         REMOVE_OK=true
+       else
+         WT_NAME=$(basename "$WT")
+         if [ -f ".git/worktrees/${WT_NAME}/locked" ]; then
+           echo "⚠ Worktree $WT is locked — attempting to unlock and retry"
+           git worktree unlock "$WT" 2>/dev/null || true
+           if git worktree remove "$WT" --force; then
+             REMOVE_OK=true
+           else
+             echo "⚠ Residual worktree at $WT — manual cleanup required after session exits:"
+             echo "    git worktree unlock \"$WT\" && git worktree remove \"$WT\" --force && git branch -D \"$WT_BRANCH\""
+           fi
+         else
+           echo "⚠ Residual worktree at $WT (remove failed) — investigate manually"
+         fi
+       fi
+       if [ "$REMOVE_OK" = "true" ]; then
+         git branch -D "$WT_BRANCH" 2>/dev/null || true
+       else
+         echo "⚠ Keeping branch $WT_BRANCH because worktree removal failed (#3384)"
+       fi
+     fi
+   done < "$WT_PATHS_FILE"
+   fi
+   ```
+
+   **Cleanup-tail snippet (use after any wave whose merges did not flow through the templated path above):**
+
+   If the orchestrator deviated from the standard wave merge path (e.g., custom inter-worktree base-update merges with `merge: bring …` style messages), run this snippet after the custom merges are complete. It reads only `WAVE_WORKTREE_MANIFEST`; do not discover unrelated `worktree-agent-*` worktrees.
+
+   ```bash
+   # Cleanup-tail: pin orchestrator CWD to primary worktree before cleanup-tail (#3174).
+   PRIMARY_WT=$(git worktree list --porcelain | awk '/^worktree /{print substr($0,10); exit}')
+   if [ -n "$PRIMARY_WT" ] && [ "$(pwd -P 2>/dev/null)" != "$(cd "$PRIMARY_WT" 2>/dev/null && pwd -P)" ]; then echo "⚠ Orchestrator CWD drifted to $(pwd) — pinning to $PRIMARY_WT before cleanup-tail (#3174)"; cd "$PRIMARY_WT" || { echo "FATAL: cannot cd to primary worktree $PRIMARY_WT" >&2; exit 1; }; fi
+   # Cleanup-tail: remove residual agent worktrees after a cross-wave-dependency deviation.
+   # Uses only the current wave manifest to avoid touching unrelated active agents (#3384).
+   WT_PATHS_FILE=$(mktemp "${TMPDIR:-/tmp}/sdd-worktree-paths-XXXXXX")
+   node -e 'const fs=require("fs");const p=process.env.WAVE_WORKTREE_MANIFEST;try{if(!p)throw new Error("WAVE_WORKTREE_MANIFEST is unset");if(!fs.existsSync(p))throw new Error("manifest does not exist");const s=fs.readFileSync(p,"utf8");if(!s.trim())throw new Error("manifest is empty");const j=JSON.parse(s);for(const w of j.worktrees||[])if(w.worktree_path)console.log(w.worktree_path)}catch(e){console.error(`ERROR: cannot read worktree manifest ${p||"(unset)"}: ${e.message}`);process.exit(1)}' > "$WT_PATHS_FILE" || { echo "BLOCKED: cannot read WAVE_WORKTREE_MANIFEST; refusing cleanup (#3384)." >&2; exit 1; }
+   while IFS= read -r WT; do
+     [ -z "$WT" ] && continue
+     WT_BRANCH=$(git -C "$WT" rev-parse --abbrev-ref HEAD 2>/dev/null)
+     [ -z "$WT_BRANCH" ] || [ "$WT_BRANCH" = "HEAD" ] && continue
+     echo "Cleaning up residual worktree: $WT (branch: $WT_BRANCH)"
+     git worktree unlock "$WT" 2>/dev/null || true
+     if ! git worktree remove "$WT" --force; then
+       WT_NAME=$(basename "$WT")
+       if [ -f ".git/worktrees/${WT_NAME}/locked" ]; then
+         echo "⚠ Worktree $WT is locked — unlock failed; manual cleanup required:"
+         echo "    git worktree unlock \"$WT\" && git worktree remove \"$WT\" --force && git branch -D \"$WT_BRANCH\""
+       else
+         echo "⚠ Residual worktree at $WT — remove failed; manual cleanup required"
+       fi
+     else
+       git branch -D "$WT_BRANCH" 2>/dev/null || true
+     fi
+   done < "$WT_PATHS_FILE"
+   git worktree prune
+   ```
+
+   **When to skip step 5.5:**
+
+   **If no plan in this wave used worktree isolation** (project-level `USE_WORKTREES=false` OR every plan in the wave had `USE_WORKTREES_FOR_PLAN=false` — i.e. `WAVE_WORKTREE_PLANS` from step 2.5 is empty): all agents ran on the main working tree — skip this step entirely.
+
+   **If the orchestrator merged via custom messages (cross-wave-dependency deviation):** the templated cleanup loop above was not triggered for those merges. Run the cleanup-tail snippet above instead. After the snippet completes, proceed to step 5.6.
+
+   **If at least one plan used worktrees but others did not:** still run this cleanup — it iterates over actual `git worktree list` output and only merges back the worktrees that were created, leaving sequential plans' commits on the main tree untouched.
+
+   **If no worktrees found at runtime:** Skip silently — agents may have been spawned without worktree isolation, or the orchestrator already cleaned them up.
+
+5.6. **Post-merge build & test gate:**
+
+   After merging all worktrees in a wave (parallel mode), or after the last plan completes
+   (serial mode), run a build and then the project's test suite to catch cross-plan
+   integration issues that individual worktree self-checks cannot detect (e.g., conflicting
+   type definitions, removed exports, import changes, link errors).
+
+   This addresses the Generator self-evaluation blind spot identified in Anthropic's
+   harness engineering research: agents reliably report Self-Check: PASSED even when
+   merging their work creates failures.
+
+   Read and execute `sdd/workflows/execute-phase/steps/post-merge-gate.md`.
+
+5.7. **Post-wave shared artifact update (when at least one plan used worktrees, skip if tests failed):**
+
+   When **any** executor agent in this wave ran with `isolation="worktree"`, that agent skipped STATE.md and ROADMAP.md updates to avoid last-merge-wins overwrites. The orchestrator is the single writer for these files. After worktrees are merged back, update shared artifacts once for every completed plan in the wave (worktree-mode plans **and** sequential plans that ran on the main tree but deferred to the orchestrator for tracking writes).
+
+   **Only update tracking when tests passed (TEST_EXIT=0).**
+   If tests failed or timed out, skip the tracking update — plans should
+   not be marked as complete when integration tests are failing or inconclusive.
+
+   ```bash
+   # Guard: only update tracking if post-merge tests passed
+   # Timeout (124) is treated as inconclusive — do NOT mark plans complete
+   if [ "${TEST_EXIT}" -eq 0 ]; then
+     # Update ROADMAP plan progress for each completed plan in this wave
+     for plan_id in {completed_plan_ids}; do
+       sdd-sdk query roadmap.update-plan-progress "${PHASE_NUMBER}" "${plan_id}" "complete"
+     done
+
+     # Only commit tracking files if they actually changed
+     if ! git diff --quiet .planning/ROADMAP.md .planning/STATE.md 2>/dev/null; then
+       sdd-sdk query commit "docs(phase-${PHASE_NUMBER}): update tracking after wave ${N}" --files .planning/ROADMAP.md .planning/STATE.md
+     fi
+   elif [ "${TEST_EXIT}" -eq 124 ]; then
+     echo "⚠ Skipping tracking update — test suite timed out. Plans remain in-progress. Run tests manually to confirm."
+   else
+     echo "⚠ Skipping tracking update — post-merge tests failed (exit ${TEST_EXIT}). Plans remain in-progress until tests pass."
+   fi
+   ```
+
+   Where `WAVE_PLAN_IDS` is the space-separated list of plan IDs that completed in this wave.
+
+   **If no plan in this wave used worktrees** (project-level `USE_WORKTREES=false` OR `WAVE_WORKTREE_PLANS` is empty): sequential agents already updated STATE.md and ROADMAP.md themselves — skip this step.
+
+5.8. **Handle test gate failures (when `WAVE_FAILURE_COUNT > 0`):**
+
+   ```
+   ## ⚠ Post-Merge Test Failure (cumulative failures: ${WAVE_FAILURE_COUNT})
+
+   Wave {N} worktrees merged successfully, but {M} tests fail after merge.
+   This typically indicates conflicting changes across parallel plans
+   (e.g., type definitions, shared imports, API contracts).
+
+   Failed tests:
+   {first 10 lines of failure output}
+
+   Options:
+   1. Fix now (recommended) — resolve conflicts before next wave
+   2. Continue — failures may compound in subsequent waves
+   ```
+
+   Note: If `WAVE_FAILURE_COUNT > 1`, strongly recommend "Fix now" — compounding
+   failures across multiple waves become exponentially harder to diagnose.
+
+   If "Fix now": diagnose failures (typically import conflicts, missing types,
+   or changed function signatures from parallel plans modifying the same module).
+   Fix, commit as `fix: resolve post-merge conflicts from wave {N}`, re-run tests.
+
+   **Why this matters:** Worktree isolation means each agent's Self-Check passes
+   in isolation. But when merged, add/add conflicts in shared files (models, registries,
+   CLI entry points) can silently drop code. The post-merge gate catches this before
+   the next wave builds on a broken foundation.
+
+6. **Report completion — spot-check claims first:**
+
+   **Wave-close heartbeat (#2410):** after spot-checks finish (pass or fail),
+   before the `## Wave {N} Complete` summary, emit as a literal line:
+
+   ```
+   [checkpoint] phase {PHASE_NUMBER} wave {N}/{M} complete, {P}/{Q} plans done ({wave_success}/{wave_plan_count} ok)
+   ```
+
+
 
    For each SUMMARY.md:
    - Verify first 2 files from `key-files.created` exist on disk
@@ -335,53 +1005,52 @@ Execute each selected wave in sequence. Within a wave: parallel if `PARALLELIZAT
    ---
    ```
 
-   - Bad: "Wave 2 complete. Proceeding to Wave 3."
-   - Good: "Terrain system complete — 3 biome types, height-based texturing, physics collision meshes. Vehicle physics (Wave 3) can now reference ground surfaces."
-
-5. **Handle failures:**
-
-   **Known Claude Code bug (classifyHandoffIfNeeded):** If an agent reports "failed" with error containing `classifyHandoffIfNeeded is not defined`, this is a Claude Code runtime bug — not a SDD or agent issue. The error fires in the completion handler AFTER all tool calls finish. In this case: run the same spot-checks as step 4 (SUMMARY.md exists, git commits present, no Self-Check: FAILED). If spot-checks PASS → treat as **successful**. If spot-checks FAIL → treat as real failure below.
-
-   For real failures: report which plan failed → ask "Continue?" or "Stop?" → if continue, dependent plans may also fail. If stop, partial completion report.
-
-5b. **Pre-wave dependency check (waves 2+ only):**
-
-    Before spawning wave N+1, for each plan in the upcoming wave:
-    ```bash
-    node "$HOME/.claude/sdd/bin/sdd-tools.cjs" verify key-links {phase_dir}/{plan}-PLAN.md
-    ```
-
-    If any key-link from a PRIOR wave's artifact fails verification:
-
-    ## Cross-Plan Wiring Gap
-
-    | Plan | Link | From | Expected Pattern | Status |
-    |------|------|------|-----------------|--------|
-    | {plan} | {via} | {from} | {pattern} | NOT FOUND |
-
-    Wave {N} artifacts may not be properly wired. Options:
-    1. Investigate and fix before continuing
-    2. Continue (may cause cascading failures in wave {N+1})
-
-    Key-links referencing files in the CURRENT (upcoming) wave are skipped.
-
-6. **Execute checkpoint plans between waves** — see `<checkpoint_handling>`.
-
-7. **Proceed to next wave.**
+7. **Handle failures:**
+   **Step 7.0 — classify before branching (#3095):**
+   ```bash
+   CLASS_JSON=$(sdd-sdk query agent.classify-failure -- "$AGENT_RETURN_BODY")
+   CLASS=$(echo "$CLASS_JSON" | jq -r '.class')
+   SENTINEL=$(echo "$CLASS_JSON" | jq -r '.sentinel // empty')
+   RETRY_AFTER=$(echo "$CLASS_JSON" | jq -r '.retryAfterSeconds // empty')
+   if [ -n "$RETRY_AFTER" ]; then RETRY_HINT="  Provider hinted retry-after: ${RETRY_AFTER}s"; else RETRY_HINT=""; fi
+   ```
+   One classifier branch handles sentinels across Claude/Copilot/Codex/Gemini. Reference: `docs/research/provider-rate-limit-signals.md`.
+   **Step 7.1 — `class == "quota-exceeded"`:**
+   Do not offer "retry now". Run step-5 spot-check first; if SUMMARY.md is missing but commits exist, route to safe-resume (`state.verify-against-disk`) instead of immediate redispatch.
+   ```text
+   ⚠ Plan {plan_id} terminated by provider quota / rate limit
+     Runtime sentinel: {SENTINEL}
+     {RETRY_HINT}
+     Partial commits on worktree branch: {N}
+     SUMMARY.md present: {yes|no}
+     1. Wait for quota reset, then resume (recommended)
+   2. Switch to a different runtime / model and resume
+   3. Abort phase and report partial state
+   ```
+   Re-run `/sdd:execute-phase` after quota reset for Option 1.
+   **Step 7.2 — `class == "classify-handoff-bug"`:**
+   If error contains `classifyHandoffIfNeeded is not defined`, treat as Claude runtime bug. Run the same step-5 spot-checks; PASS => treat as success, FAIL => fall through.
+   **Step 7.3 — `class == "unknown-failure"`:**
+   Report failed plan and ask Continue/Stop; continuing may cascade into dependent plan failures.
+
+7b. **Pre-wave dependency check (waves 2+ only):**
+    Before wave N+1, run `sdd-sdk query verify.key-links {phase_dir}/{plan}-PLAN.md` for each upcoming plan.
+    If any PRIOR-wave artifact link fails, present:
+    - `## Cross-Plan Wiring Gap` with plan/link/from/pattern rows
+    - Options: investigate+fix before continue, or continue with cascade risk
+    Skip key-links that reference files in the CURRENT (upcoming) wave.
+8. **Execute checkpoint plans between waves** — see `<checkpoint_handling>`.
+9. **Proceed to next wave.**
 </step>
-
 <step name="checkpoint_handling">
 Plans with `autonomous: false` require user interaction.
-
 **Auto-mode checkpoint handling:**
-
-Read auto-advance config (chain flag + user preference):
+Read auto-advance config (chain flag OR user preference — same boolean as `check.auto-mode`):
 ```bash
-AUTO_CHAIN=$(node "$HOME/.claude/sdd/bin/sdd-tools.cjs" config-get workflow._auto_chain_active 2>/dev/null || echo "false")
-AUTO_CFG=$(node "$HOME/.claude/sdd/bin/sdd-tools.cjs" config-get workflow.auto_advance 2>/dev/null || echo "false")
+AUTO_MODE=$(sdd-sdk query check auto-mode --pick active 2>/dev/null || echo "false")
 ```
 
-When executor returns a checkpoint AND (`AUTO_CHAIN` is `"true"` OR `AUTO_CFG` is `"true"`):
+When executor returns a checkpoint AND `AUTO_MODE` is `true`:
 - **human-verify** → Auto-spawn continuation agent with `{user_response}` = `"approved"`. Log `⚡ Auto-approved checkpoint`.
 - **decision** → Auto-spawn continuation agent with `{user_response}` = first option from checkpoint details. Log `⚡ Auto-selected: [option]`.
 - **human-action** → Present to user (existing behavior below). Auth gates cannot be automated.
@@ -436,13 +1105,87 @@ After all waves:
 ### Issues Encountered
 [Aggregate from SUMMARYs, or "None"]
 ```
+
+**Security gate check:**
+```bash
+SECURITY_CFG=$(sdd-sdk query config-get workflow.security_enforcement --raw 2>/dev/null || echo "true")
+SECURITY_FILE=$(ls "${PHASE_DIR}"/*-SECURITY.md 2>/dev/null | head -1)
+```
+
+If `SECURITY_CFG` is `false`: skip.
+
+If `SECURITY_CFG` is `true` AND `SECURITY_FILE` is empty (no SECURITY.md yet):
+Include in the next-steps routing output:
+```
+⚠ Security enforcement enabled — run before advancing:
+  /sdd:secure-phase {PHASE} ${SDD_WS}
+```
+
+If `SECURITY_CFG` is `true` AND SECURITY.md exists: check frontmatter `threats_open`. If > 0:
+```
+⚠ Security gate: {threats_open} threats open
+  /sdd:secure-phase {PHASE} — resolve before advancing
+```
+</step>
+
+<step name="tdd_review_checkpoint">
+**Optional step — TDD collaborative review.**
+
+```bash
+TDD_MODE=$(sdd-sdk query config-get workflow.tdd_mode 2>/dev/null || echo "false")
+```
+
+**Skip if `TDD_MODE` is `false`.**
+
+When `TDD_MODE` is `true`, check whether any completed plans in this phase have `type: tdd` in their frontmatter:
+
+```bash
+TDD_PLANS=$(grep -rl "^type: tdd" "${PHASE_DIR}"/*-PLAN.md 2>/dev/null | wc -l | tr -d ' ')
+```
+
+**If `TDD_PLANS` > 0:** Insert end-of-phase collaborative review checkpoint.
+
+1. Collect all SUMMARY.md files for TDD plans
+2. For each TDD plan summary, verify the RED/GREEN/REFACTOR gate sequence:
+   - RED gate: A failing test commit exists (`test(...)` commit with MUST-fail evidence)
+   - GREEN gate: An implementation commit exists (`feat(...)` commit making tests pass)
+   - REFACTOR gate: Optional cleanup commit (`refactor(...)` commit, tests still pass)
+3. If any TDD plan is missing the RED or GREEN gate commits, flag it:
+   ```
+   ⚠ TDD gate violation: Plan {plan_id} missing {RED|GREEN} phase commit.
+     Expected commit pattern: test({phase}-{plan}): ... → feat({phase}-{plan}): ...
+   ```
+4. Present collaborative review summary:
+   ```
+   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+    TDD REVIEW — Phase {X}
+   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+   TDD Plans: {TDD_PLANS} | Gate violations: {count}
+
+   | Plan | RED | GREEN | REFACTOR | Status |
+   |------|-----|-------|----------|--------|
+   | {id} |  ✓  |   ✓   |    ✓     | Pass   |
+   | {id} |  ✓  |   ✗   |    —     | FAIL   |
+   ```
+
+**Escalation under MVP+TDD.** When `MVP_MODE=true` AND `TDD_MODE=true`, the review verdict escalates from advisory to **blocking**: missing RED or GREEN gate commits prevent marking the phase complete.
+```text
+Phase blocked: {N} TDD plan(s) violate the RED→GREEN gate sequence under MVP+TDD.
+Resolve and re-run /sdd execute-phase, or override with
+/sdd execute-phase {phase} --force-mvp-gate to ship anyway.
+```
+`--force-mvp-gate` is the escape hatch (documented, not yet implemented). Policy is:
+- `MVP_MODE=true` AND `TDD_MODE=true`: violations are **blocking** unless explicitly overridden.
+- otherwise: violations are advisory/non-blocking and are surfaced for review.
+The verifier agent (step `verify_phase_goal`) still checks TDD discipline in both cases.
 </step>
 
 <step name="handle_partial_wave_execution">
 If `WAVE_FILTER` was used, re-run plan discovery after execution:
 
 ```bash
-POST_PLAN_INDEX=$(node "$HOME/.claude/sdd/bin/sdd-tools.cjs" phase-plan-index "${PHASE_NUMBER}")
+POST_PLAN_INDEX=$(sdd-sdk query phase-plan-index "${PHASE_NUMBER}")
 ```
 
 Apply the same "incomplete" filtering rules as earlier:
@@ -469,6 +1212,39 @@ Selected wave finished successfully. This phase still has incomplete plans, so p
 - this means the selected wave happened to be the last remaining work in the phase
 </step>
 
+<step name="code_review_gate" required="true">
+**This step is REQUIRED and must not be skipped.** Auto-invoke code review on the phase's source changes. Advisory only — never blocks execution flow.
+
+**Config gate:**
+```bash
+CODE_REVIEW_ENABLED=$(sdd-sdk query config-get workflow.code_review 2>/dev/null || echo "true")
+```
+
+If `CODE_REVIEW_ENABLED` is `"false"`: display "Code review skipped (workflow.code_review=false)" and proceed to next step.
+
+**Invoke review:**
+```
+Skill(skill="sdd-code-review", args="${PHASE_NUMBER}")
+```
+
+**Check results using deterministic path (not glob):**
+```bash
+PADDED=$(printf "%02d" "${PHASE_NUMBER}")
+REVIEW_FILE="${PHASE_DIR}/${PADDED}-REVIEW.md"
+REVIEW_STATUS=$(sed -n '/^---$/,/^---$/p' "$REVIEW_FILE" | grep "^status:" | head -1 | cut -d: -f2 | tr -d ' ')
+```
+
+If REVIEW_STATUS is not "clean" and not "skipped" and not empty, display:
+```
+Code review found issues. Consider running:
+/sdd:code-review ${PHASE_NUMBER} --fix
+```
+
+**Error handling:** If the Skill invocation fails or throws, catch the error, display "Code review encountered an error (non-blocking): {error}" and proceed to next step. Review failures must never block execution.
+
+Regardless of review result, ALWAYS proceed to close_parent_artifacts → regression_gate → verify_phase_goal.
+</step>
+
 <step name="close_parent_artifacts">
 **For decimal/polish phases only (X.Y pattern):** Close the feedback loop by resolving parent UAT and debug artifacts.
 
@@ -484,7 +1260,7 @@ fi
 
 **2. Find parent UAT file:**
 ```bash
-PARENT_INFO=$(node "$HOME/.claude/sdd/bin/sdd-tools.cjs" find-phase "${PARENT_PHASE}" --raw)
+PARENT_INFO=$(sdd-sdk query find-phase "${PARENT_PHASE}" --raw)
 # Extract directory from PARENT_INFO JSON, then find UAT file in that directory
 ```
 
@@ -515,7 +1291,7 @@ mv .planning/debug/{slug}.md .planning/debug/resolved/
 
 **6. Commit updated artifacts:**
 ```bash
-node "$HOME/.claude/sdd/bin/sdd-tools.cjs" commit "docs(phase-${PARENT_PHASE}): resolve UAT gaps and debug sessions after ${PHASE_NUMBER} gap closure" --files .planning/phases/*${PARENT_PHASE}*/*-UAT.md .planning/debug/resolved/*.md
+sdd-sdk query commit "docs(phase-${PARENT_PHASE}): resolve UAT gaps and debug sessions after ${PHASE_NUMBER} gap closure" --files .planning/phases/*${PARENT_PHASE}*/*-UAT.md .planning/debug/resolved/*.md
 ```
 </step>
 
@@ -542,15 +1318,27 @@ Collect all unique test file paths into `REGRESSION_FILES`.
 **Step 3: Run regression tests (if any found)**
 
 ```bash
-# Detect test runner and run prior phase tests
-if [ -f "package.json" ]; then
-  # Node.js — use project's test runner
-  npx jest ${REGRESSION_FILES} --passWithNoTests --no-coverage -q 2>&1 || npx vitest run ${REGRESSION_FILES} 2>&1
-elif [ -f "Cargo.toml" ]; then
-  cargo test 2>&1
-elif [ -f "requirements.txt" ] || [ -f "pyproject.toml" ]; then
-  python -m pytest ${REGRESSION_FILES} -q --tb=short 2>&1
+# Resolve test command: project config > Makefile > language sniff
+REG_TEST_CMD=$(sdd-sdk query config-get workflow.test_command --default "" 2>/dev/null || true)
+if [ -z "$REG_TEST_CMD" ]; then
+  if [ -f "Makefile" ] && grep -q "^test:" Makefile; then
+    REG_TEST_CMD="make test"
+  elif [ -f "Justfile" ] || [ -f "justfile" ]; then
+    REG_TEST_CMD="just test"
+  elif [ -f "package.json" ]; then
+    REG_TEST_CMD="npm test"
+  elif [ -f "Cargo.toml" ]; then
+    REG_TEST_CMD="cargo test"
+  elif [ -f "go.mod" ]; then
+    REG_TEST_CMD="go test ./..."
+  elif [ -f "requirements.txt" ] || [ -f "pyproject.toml" ]; then
+    REG_TEST_CMD="python -m pytest ${REGRESSION_FILES} -q --tb=short"
+  else
+    REG_TEST_CMD="true"
+  fi
 fi
+# Detect test runner and run prior phase tests
+eval "$REG_TEST_CMD" 2>&1
 ```
 
 **Step 4: Report results**
@@ -580,15 +1368,93 @@ Options:
 Use AskUserQuestion to present the options.
 </step>
 
+<step name="schema_drift_gate">
+Post-execution schema drift detection. Catches false-positive verification where
+build/types pass because TypeScript types come from config, not the live database.
+
+**Run after execution completes but BEFORE verification marks success.**
+
+```bash
+SCHEMA_DRIFT=$(sdd-sdk query verify.schema-drift "${PHASE_NUMBER}" 2>/dev/null)
+```
+
+Parse JSON result for: `drift_detected`, `blocking`, `schema_files`, `orms`, `unpushed_orms`, `message`.
+
+**If `drift_detected` is false:** Skip to verify_phase_goal.
+
+**If `drift_detected` is true AND `blocking` is true:**
+
+Check for override:
+```bash
+SKIP_SCHEMA=$(echo "${SDD_SKIP_SCHEMA_CHECK:-false}")
+```
+
+**If `SKIP_SCHEMA` is `true`:**
+
+Display:
+```
+⚠ Schema drift detected but SDD_SKIP_SCHEMA_CHECK=true — bypassing gate.
+
+Schema files changed: {schema_files}
+ORMs requiring push: {unpushed_orms}
+
+Proceeding to verification (database may be out of sync).
+```
+→ Continue to verify_phase_goal.
+
+**If `SKIP_SCHEMA` is not `true`:**
+
+BLOCK verification. Display:
+
+```
+## BLOCKED: Schema Drift Detected
+
+Schema-relevant files changed during this phase but no database push command
+was executed. Build and type checks pass because TypeScript types come from
+config, not the live database — verification would produce a false positive.
+
+Schema files changed: {schema_files}
+ORMs requiring push: {unpushed_orms}
+
+Required push commands:
+{For each unpushed ORM, show the push command from the message}
+
+Options:
+1. Run push command now (recommended) — execute the push, then re-verify
+2. Skip schema check (SDD_SKIP_SCHEMA_CHECK=true) — bypass this gate
+3. Abort — stop execution and investigate
+```
+
+If `TEXT_MODE` is true, present as a plain-text numbered list. Otherwise use AskUserQuestion.
+
+**If user selects option 1:** Present the specific push command(s) to run. After user confirms execution, re-run the schema drift check. If it passes, continue to verify_phase_goal.
+
+**If user selects option 2:** Set override and continue to verify_phase_goal.
+
+**If user selects option 3:** Stop execution. Report partial completion.
+</step>
+
+<step name="codebase_drift_gate">
+Post-execution structural drift detection (#2003). Non-blocking by contract:
+any internal error here MUST fall through to `verify_phase_goal`. The phase
+is never failed by this gate.
+
+Load and follow the full step spec from
+`sdd/workflows/execute-phase/steps/codebase-drift-gate.md` —
+covers the SDK call, JSON contract, `warn` vs `auto-remap` branches, mapper
+spawn template, and the two `workflow.drift_*` config keys.
+</step>
+
 <step name="verify_phase_goal">
 Verify phase achieved its GOAL, not just completed tasks.
 
 ```bash
-VERIFIER_SKILLS=$(node "$HOME/.claude/sdd/bin/sdd-tools.cjs" agent-skills sdd-verifier 2>/dev/null)
+VERIFIER_SKILLS=$(sdd-sdk query agent-skills sdd-verifier)
 ```
 
 ```
-Task(
+Agent(
+  description="Verify phase {phase_number} goal achievement",
   prompt="Verify phase {phase_number} goal achievement.
 Phase directory: {phase_dir}
 Phase goal: {goal from ROADMAP.md}
@@ -596,12 +1462,26 @@ Phase requirement IDs: {phase_req_ids}
 Check must_haves against actual codebase.
 Cross-reference requirement IDs from PLAN frontmatter against REQUIREMENTS.md — every ID MUST be accounted for.
 Create VERIFICATION.md.
+
+<files_to_read>
+Read these files before verification:
+- {phase_dir}/*-PLAN.md (All plans — understand intent, check must_haves)
+- {phase_dir}/*-SUMMARY.md (All summaries — cross-reference claimed vs actual)
+- .planning/REQUIREMENTS.md (Requirement traceability)
+${CONTEXT_WINDOW >= 500000 ? `- {phase_dir}/*-CONTEXT.md (User decisions — verify they were honored)
+- {phase_dir}/*-RESEARCH.md (Known pitfalls — check for traps)
+- Prior VERIFICATION.md files from earlier phases (regression check)
+` : ''}
+</files_to_read>
+
 ${VERIFIER_SKILLS}",
   subagent_type="sdd-verifier",
   model="{verifier_model}"
 )
 ```
 
+> **ORCHESTRATOR RULE — CODEX RUNTIME**: After calling Agent() above, stop working on this task immediately. Do not read more files, edit code, or run tests related to this task while the subagent is active. Wait for the subagent to return its result. This prevents duplicate work, conflicting edits, and wasted context. Only resume when the subagent result is available.
+
 Read status:
 ```bash
 grep "^status:" "$PHASE_DIR"/*-VERIFICATION.md | cut -d: -f2 | tr -d ' '
@@ -610,7 +1490,7 @@ grep "^status:" "$PHASE_DIR"/*-VERIFICATION.md | cut -d: -f2 | tr -d ' '
 | Status | Action |
 |--------|--------|
 | `passed` | → update_roadmap |
-| `human_needed` | Present items for human testing, get approval or feedback |
+| `human_needed` | Persist and present human testing items; keep phase pending until verification reruns as `passed` |
 | `gaps_found` | Present gap summary, offer `/sdd:plan-phase {phase} --gaps ${SDD_WS}` |
 
 **If human_needed:**
@@ -654,7 +1534,7 @@ blocked: 0
 
 Commit the file:
 ```bash
-node "$HOME/.claude/sdd/bin/sdd-tools.cjs" commit "test({phase_num}): persist human verification items as UAT" --files "{phase_dir}/{phase_num}-HUMAN-UAT.md"
+sdd-sdk query commit "test({phase_num}): persist human verification items as UAT" --files "{phase_dir}/{phase_num}-HUMAN-UAT.md"
 ```
 
 **Step B: Present to user:**
@@ -686,11 +1566,11 @@ Items saved to `{phase_num}-HUMAN-UAT.md` — they will appear in `/sdd:progress
 {Gap summaries from VERIFICATION.md}
 
 ---
-## ▶ Next Up
+## ▶ Next Up — [${PROJECT_CODE}] ${PROJECT_TITLE}
 
-`/sdd:plan-phase {X} --gaps ${SDD_WS}`
+`/clear` then:
 
-<sub>`/clear` first → fresh context window</sub>
+`/sdd:plan-phase {X} --gaps ${SDD_WS}`
 
 Also: `cat {phase_dir}/{phase_num}-VERIFICATION.md` — full report
 Also: `/sdd:verify-work {X} ${SDD_WS}` — manual testing first
@@ -703,7 +1583,7 @@ Gap closure cycle: `/sdd:plan-phase {X} --gaps ${SDD_WS}` reads VERIFICATION.md
 **Mark phase complete and update all tracking files:**
 
 ```bash
-COMPLETION=$(node "$HOME/.claude/sdd/bin/sdd-tools.cjs" phase complete "${PHASE_NUMBER}")
+COMPLETION=$(sdd-sdk query phase.complete "${PHASE_NUMBER}")
 ```
 
 The CLI handles:
@@ -726,8 +1606,63 @@ These items are tracked and will appear in `/sdd:progress` and `/sdd:audit-uat`.
 ```
 
 ```bash
-node "$HOME/.claude/sdd/bin/sdd-tools.cjs" commit "docs(phase-{X}): complete phase execution" --files .planning/ROADMAP.md .planning/STATE.md .planning/REQUIREMENTS.md {phase_dir}/*-VERIFICATION.md
+sdd-sdk query commit "docs(phase-{X}): complete phase execution" --files .planning/ROADMAP.md .planning/STATE.md .planning/REQUIREMENTS.md {phase_dir}/*-VERIFICATION.md
+```
+</step>
+
+<step name="auto_copy_learnings">
+**Auto-copy phase learnings to global store (when enabled).**
+
+This step runs AFTER phase completion and SUMMARY.md is written. It copies any LEARNINGS.md
+entries from the completed phase to the global learnings store at `~/.sdd/knowledge/`.
+
+**Check config gate:**
+```bash
+GL_ENABLED=$(sdd-sdk query config-get features.global_learnings --raw 2>/dev/null || echo "false")
+```
+
+**If `GL_ENABLED` is not `true`:** Skip this step entirely (feature disabled by default).
+
+**If enabled:**
+
+1. Check if LEARNINGS.md exists in the phase directory (use the `phase_dir` value from init context)
+2. If found, copy to global store:
+```bash
+sdd-sdk query learnings.copy 2>/dev/null || echo "⚠ Learnings copy failed — continuing"
+```
+Copy failure must NOT block phase completion.
+</step>
+
+<step name="close_phase_todos">
+**Auto-close pending todos tagged for this phase (#2433).**
+
+This step runs AFTER `update_roadmap` marks the phase complete. It moves any pending todos that carry `resolves_phase: <current-phase-number>` to the completed directory.
+
+```bash
+PHASE_NUM="${PHASE_NUMBER}"
+PENDING_DIR=".planning/todos/pending"
+COMPLETED_DIR=".planning/todos/completed"
+mkdir -p "$COMPLETED_DIR"
+
+CLOSED=()
+for TODO_FILE in "$PENDING_DIR"/*.md; do
+  [ -f "$TODO_FILE" ] || continue
+  # Extract resolves_phase from YAML frontmatter (first --- block only)
+  RP=$(awk '/^---/{c++;next} c==1 && /^resolves_phase:/{print $2;exit} c==2{exit}' "$TODO_FILE" 2>/dev/null || true)
+  if [ "$RP" = "$PHASE_NUM" ] || [ "$RP" = "\"$PHASE_NUM\"" ]; then
+    mv "$TODO_FILE" "$COMPLETED_DIR/"
+    CLOSED+=("$(basename "$TODO_FILE")")
+  fi
+done
+
+if [ ${#CLOSED[@]} -gt 0 ]; then
+  sdd-sdk query commit "docs(phase-${PHASE_NUMBER}): auto-close ${#CLOSED[@]} todo(s) resolved by this phase" --files .planning/todos/completed/ .planning/STATE.md|| true
+  echo "◆ Closed ${#CLOSED[@]} todo(s) resolved by Phase ${PHASE_NUMBER}:"
+  for f in "${CLOSED[@]}"; do echo "  ✓ $f"; done
+fi
 ```
+
+**If no todos have `resolves_phase: <this-phase>`:** Skip silently — this step is always additive and never blocks phase completion.
 </step>
 
 <step name="update_project_md">
@@ -746,7 +1681,7 @@ PROJECT.md falls behind silently over multiple phases.
 5. Commit the change:
 
 ```bash
-node "$HOME/.claude/sdd/bin/sdd-tools.cjs" commit "docs(phase-{X}): evolve PROJECT.md after phase completion" --files .planning/PROJECT.md
+sdd-sdk query commit "docs(phase-{X}): evolve PROJECT.md after phase completion" --files .planning/PROJECT.md
 ```
 
 **Skip this step if** `.planning/PROJECT.md` does not exist.
@@ -782,13 +1717,12 @@ STOP. Do not proceed to auto-advance or transition.
 **Auto-advance detection:**
 
 1. Parse `--auto` flag from $ARGUMENTS
-2. Read both the chain flag and user preference (chain flag already synced in init step):
+2. Read consolidated auto-mode (`active` = chain flag OR user preference; chain flag already synced in init step):
    ```bash
-   AUTO_CHAIN=$(node "$HOME/.claude/sdd/bin/sdd-tools.cjs" config-get workflow._auto_chain_active 2>/dev/null || echo "false")
-   AUTO_CFG=$(node "$HOME/.claude/sdd/bin/sdd-tools.cjs" config-get workflow.auto_advance 2>/dev/null || echo "false")
+   AUTO_MODE=$(sdd-sdk query check auto-mode --pick active 2>/dev/null || echo "false")
    ```
 
-**If `--auto` flag present OR `AUTO_CHAIN` is true OR `AUTO_CFG` is true (AND verification passed with no gaps):**
+**If `--auto` flag present OR `AUTO_MODE` is true (AND verification passed with no gaps):**
 
 ```
 ╔══════════════════════════════════════════╗
@@ -797,23 +1731,42 @@ STOP. Do not proceed to auto-advance or transition.
 ╚══════════════════════════════════════════╝
 ```
 
-Execute the transition workflow inline (do NOT use Task — orchestrator context is ~10-15%, transition needs phase completion data already in context):
+Execute the transition workflow inline (do NOT use Agent — orchestrator context is ~10-15%, transition needs phase completion data already in context):
 
 Read and follow `~/.claude/sdd/workflows/transition.md`, passing through the `--auto` flag so it propagates to the next phase invocation.
 
-**If none of `--auto`, `AUTO_CHAIN`, or `AUTO_CFG` is true:**
+**If neither `--auto` nor `AUTO_MODE` is true:**
 
 **STOP. Do not auto-advance. Do not execute transition. Do not plan next phase. Present options to the user and wait.**
 
-**IMPORTANT: There is NO `/sdd:transition` command. Never suggest it. The transition workflow is internal only.**
+**IMPORTANT: There is NO `/sdd-transition` command. Never suggest it. The transition workflow is internal only.**
+
+Check whether CONTEXT.md already exists for the next phase:
+
+```bash
+ls .planning/phases/*{next}*/{next}-CONTEXT.md 2>/dev/null || echo "no-context"
+```
+
+If CONTEXT.md does **not** exist for the next phase, present:
+
+```
+## ✓ Phase {X}: {Name} Complete
+
+/sdd:progress ${SDD_WS} — see updated roadmap
+/sdd:discuss-phase {next} ${SDD_WS} — start here: discuss next phase before planning  ← recommended
+/sdd:plan-phase {next} ${SDD_WS} — plan next phase (skip discuss)
+/sdd:execute-phase {next} ${SDD_WS} — execute next phase (skip discuss and plan)
+```
+
+If CONTEXT.md **exists** for the next phase, present:
 
 ```
 ## ✓ Phase {X}: {Name} Complete
 
 /sdd:progress ${SDD_WS} — see updated roadmap
-/sdd:discuss-phase {next} ${SDD_WS} — discuss next phase before planning
-/sdd:plan-phase {next} ${SDD_WS} — plan next phase
-/sdd:execute-phase {next} ${SDD_WS} — execute next phase
+/sdd:plan-phase {next} ${SDD_WS} — start here: plan next phase (CONTEXT.md already present)  ← recommended
+/sdd:discuss-phase {next} ${SDD_WS} — re-discuss next phase
+/sdd:execute-phase {next} ${SDD_WS} — execute next phase (skip planning)
 ```
 
 Only suggest the commands listed above. Do not invent or hallucinate command names.
@@ -823,7 +1776,7 @@ Only suggest the commands listed above. Do not invent or hallucinate command nam
 
 <context_efficiency>
 Orchestrator: ~10-15% context for 200k windows, can use more for 1M+ windows.
-Subagents: fresh context each (200k-1M depending on model). No polling (Task blocks). No context bleed.
+Subagents: fresh context each (200k-1M depending on model). No polling (Agent blocks). No context bleed.
 
 For 1M+ context models, consider:
 - Passing richer context (code snippets, dependency outputs) directly to executors instead of just file paths
@@ -832,6 +1785,7 @@ For 1M+ context models, consider:
 </context_efficiency>
 
 <failure_handling>
+- **Quota / rate-limit (any runtime — #3095):** Agent return body contains a sentinel like `usage limit`, `rate limit`, `429`, `too many requests`, `RESOURCE_EXHAUSTED`, `usage_limit_reached`. Route via `sdd-sdk query agent.classify-failure` → `class: "quota-exceeded"`. Do not offer retry-now; the right action is wait-for-reset and resume.
 - **classifyHandoffIfNeeded false failure:** Agent reports "failed" but error is `classifyHandoffIfNeeded is not defined` → Claude Code bug, not SDD. Spot-check (SUMMARY exists, commits present) → if pass, treat as success
 - **Agent fails mid-plan:** Missing SUMMARY.md → report, ask user how to proceed
 - **Dependency chain breaks:** Wave 1 fails → Wave 2 dependents likely fail → user chooses attempt or skip