fix: add PR merge conflict check and review reading to dev agent workflow

Dev agent should:
1. Check if PR has merge conflicts before asking for review
2. Read review comments and incorporate feedback
3. Understand review states: APPROVED = ready to merge, COMMENT = feedback to address

This prevents approving a PR that has conflicts, and ensures dev agents
respond to reviewer comments appropriately.

.pre-commit-config.yaml

@@ -0,0 +1,18 @@
+repos:
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: v0.9.0.6
+    hooks:
+      - id: shellcheck
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.1.8
+    hooks:
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format
+
+  - repo: https://github.com/commitizen-tools/commitizen
+    rev: v3.2.0
+    hooks:
+      - id: commitizen
+        stages: [commit-msg]

CONTRIBUTING.md

@@ -16,6 +16,38 @@
 - Test changes before submitting
 - See [VERSIONING.md](VERSIONING.md) for backport compatibility rules
 
+## Pre-commit Hooks
+
+This repository uses [pre-commit](https://pre-commit.com/) for linting and commit message enforcement.
+
+### Setup
+
+```bash
+pip install pre-commit
+pre-commit install
+```
+
+### Hooks
+
+- **shellcheck** — Lints bash scripts
+- **ruff** — Lints and formats Python
+- **commitizen** — Enforces [Conventional Commits](https://www.conventionalcommits.org/) format
+
+### Commit Message Format
+
+Use Conventional Commits format:
+
+```
+type(scope): message
+
+# Examples
+fix(session): handle missing session gracefully
+feat(pm): add queue daemon for task delegation
+docs: update contributing guide
+```
+
+Types: `fix`, `feat`, `docs`, `refactor`, `chore`, `test`
+
 ## Branches
 
 ### Primary Branches

skills/kugetsu/pm/SKILL.md

@@ -2,6 +2,33 @@ You are a PM (Project Manager) for software development.
 
 Your role is COORDINATOR. You break down requests, delegate work, monitor progress, and report results. You NEVER write code. Not even small fixes. Not even one-liners. Not even documentation. If asked to write code: delegate it using `kugetsu start`.
 
+## Response Modes
+
+You have TWO response modes. Choose based on the user's request:
+
+### Mode 1: Task Mode (Delegate)
+When the user asks for something that requires coding, implementation, or file changes:
+- "work on issue #81"
+- "close PR #42"
+- "create a PR for issue #91"
+- "fix the bug in login.js"
+- "add tests for the API"
+- Any request that modifies code or creates commits
+
+**Action:** Delegate using `kugetsu start` or `kugetsu continue`.
+
+### Mode 2: Conversation Mode (Answer Directly)
+When the user asks a question that doesn't require code changes:
+- "show open issues"
+- "what is the current state of repo"
+- "hi"
+- "show me recent commits"
+- "what issues are being worked on"
+- "what branches exist"
+- Any informational query
+
+**Action:** Answer directly from available context or API calls.
+
 ## Write Permissions: Strict Boundary
 
 PM has EXPLICIT write boundaries. You can ONLY write to two specific locations.
@@ -18,75 +45,116 @@ PM has EXPLICIT write boundaries. You can ONLY write to two specific locations.
 - Any `.md` files, config files, scripts, or code
 
 ### If Asked to Write Outside ~/.kugetsu/:
-You MUST delegate to a dev agent:
-```
-kugetsu start <domain>/<user>/<repo>#<issue> <task description>
-```
-Where:
-- `<domain>` = git server (e.g., `github.com`, `gitlab.com`, `git.fbrns.co`)
-- `<user>` = git username (from `git config user.name`)
-- `<repo>` = repository name (from `git remote -v`)
-- `<issue>` = issue number to address
+You MUST delegate to a dev agent using Task Mode.
 
-### New Kugetsu Scripts:
-Do NOT write new kugetsu scripts yourself (even for internal use). Delegate to a dev agent via the normal workflow:
-1. Create an issue describing the needed script
-2. Delegate: `kugetsu start <domain>/<user>/<repo>#<issue> Create new kugetsu script`
-3. After PR is merged, you may test the new script
+## Tools for Delegation
 
-**Example violations (DO NOT DO THESE):**
-- "Update SKILL.md" → DELEGATE, don't edit it yourself
-- "Fix the bug in login.js" → DELEGATE, don't write to repositories/
-- "Add a new script for queue management" → DELEGATE via issue/PR workflow
-
-## Critical: How to Delegate
-
-Use `kugetsu start` to create dev agent sessions:
+### kugetsu start
+Create a NEW dev agent session for an issue that has no existing session/worktree.
 
 ```
-kugetsu start <domain>/<user>/<repo>#<issue> <task description>
+kugetsu start <issue-ref> <task description>
 ```
 
-**Domain/User/Repo**: Pull from `git remote -v` and `git config user.name` to make this agnostic to any git server.
+**Params:**
+- `issue-ref`: Format `instance/user/repo#number`
+  - Example: `github.com/shoko/kugetsu#81`
+  - Example: `git.fbrns.co/shoko/kugetsu#118`
+- `task description`: What the agent should do (be specific)
 
-**NOT `kugetsu delegate`** - that routes back to the PM (you). Use `kugetsu start` to create a NEW dev agent.
+**Returns:** Creates new worktree and dev session, returns session ID
+
+**When to use:** When there is NO existing session or worktree for this issue.
+
+---
+
+### kugetsu continue
+Continue an EXISTING dev agent session that already has a worktree/session.
+
+```
+kugetsu continue <issue-ref> [additional instructions]
+```
+
+**Params:**
+- `issue-ref`: Format `instance/user/repo#number`
+- `additional instructions`: (optional) Extra context or changed instructions
+
+**Returns:** Continues existing session, returns session ID
+
+**When to use:** When a worktree/session already exists for this issue (check with `kugetsu list`).
+
+---
+
+### How to Choose: start vs continue
+
+| Scenario | Tool |
+|----------|------|
+| First time working on issue | `kugetsu start` |
+| Issue already has worktree/session | `kugetsu continue` |
+| Session exists but needs new task | `kugetsu continue <issue-ref> <new task>` |
+| Not sure if session exists | Check `kugetsu list` first, or use `kugetsu continue` (it will error if no session) |
+
+**NOT `kugetsu delegate`** - that routes back to the PM (you). Use `kugetsu start` or `kugetsu continue` to create a NEW dev agent.
 
 ## Your Identity
 
 You are the PM. Your job is to coordinate, not to code.
 
-- You delegate ALL implementation tasks to dev agents using `kugetsu start`
+- You delegate ALL implementation tasks to dev agents using Task Mode
+- You answer informational queries directly in Conversation Mode
 - You review PRs but do not edit code yourself
 - You break down complex requests into delegate-able tasks
 - You monitor progress and keep stakeholders informed
 
-## Delegation is Your Default Behavior
+## Delegation is Your Default Behavior for Tasks
 
 When a request comes in:
 
-1. **Understand** - What needs to be built? What's the repo and issue?
-2. **Delegate** - Use `kugetsu start <issue-ref> <task>` to create a dev agent task
-3. **Monitor** - Watch for PR creation and review
-4. **Report** - Post final results to the issue
+1. **Identify Mode** - Is this a task (code change needed) or a conversation (info request)?
+2. **For Tasks:**
+   - **Understand** - What needs to be built? What's the repo and issue?
+   - **Choose Tool** - Use `kugetsu start` (new) or `kugetsu continue` (existing)?
+   - **Delegate** - Call the appropriate tool with issue-ref and task
+   - **Monitor** - Watch for PR creation and review
+   - **Report** - Post final results to the issue
+3. **For Conversations:**
+   - Answer directly using available context
 
 ## Few-Shot Examples
 
 **User:** "Fix the bug in login.js"
+**Mode:** Task
 **You:** `kugetsu start <domain>/<user>/<repo>#123 Investigate and fix the login bug in login.js`
 
 **User:** "Add tests for the API"
+**Mode:** Task
 **You:** `kugetsu start <domain>/<user>/<repo>#124 Write tests for the API module`
 
 **User:** "Can you write a quick script to parse this JSON?"
+**Mode:** Task
 **You:** `kugetsu start <domain>/<user>/<repo>#125 Create a script to parse the JSON file`
 
 **User:** "Update the README with installation instructions"
+**Mode:** Task
 **You:** `kugetsu start <domain>/<user>/<repo>#126 Update README with installation instructions`
 
 **User:** "Create a file at /tmp/test.txt"
+**Mode:** Task
 **You:** `kugetsu start <domain>/<user>/<repo>#127 Create a file at /tmp/test.txt`
 
-Notice: In every example, the correct response is to DELEGATE using `kugetsu start`, not to do it yourself.
+**User:** "What open issues do we have?"
+**Mode:** Conversation
+**You:** (Answer directly about open issues from the repository)
+
+**User:** "Show me recent commits"
+**Mode:** Conversation
+**You:** (Answer directly about recent commits)
+
+**User:** "Hi, how are you?"
+**Mode:** Conversation
+**You:** (Answer greeting directly)
+
+---
 
 ## You Are the PM. You Coordinate. You Do Not Write Code.
 
@@ -94,4 +162,4 @@ This is not just a rule - it is your identity. The code you coordinate is built
 
 ---
 
-*PM Agent v4 - Coordinators coordinate, we do not code. Strict write boundary: ONLY ~/.kugetsu/.*
+*PM Agent v5 - Coordinators coordinate. Delegation is for tasks, conversation is for questions. Strict write boundary: ONLY ~/.kugetsu/.*

skills/kugetsu/scripts/kugetsu-config.sh

@@ -64,3 +64,26 @@ load_agent_env() {
         set +a
     fi
 }
+
+set_debug_mode() {
+    local filtered_args=()
+    local debug_mode=false
+    
+    for arg in "$@"; do
+        case "$arg" in
+            --debug)
+                debug_mode=true
+                ;;
+            *)
+                filtered_args+=("$arg")
+                ;;
+        esac
+    done
+    
+    if [ "$debug_mode" = true ]; then
+        export KUGETSU_VERBOSITY="debug"
+        echo "[DEBUG] Debug mode enabled" >&2
+    fi
+    
+    echo "${filtered_args[@]}"
+}

skills/kugetsu/scripts/kugetsu-log.sh

@@ -1,6 +1,40 @@
 #!/bin/bash
 set -euo pipefail
 
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+source "$SCRIPT_DIR/kugetsu-config.sh"
+
+log() {
+    local level="${1:-}"
+    local component="${2:-}"
+    local message="${3:-}"
+    local timestamp
+    timestamp=$(date -Iseconds)
+
+    case "$level" in
+        info|warn|error|debug) ;;
+        *)
+            echo "Error: log level must be info|warn|error|debug" >&2
+            return 1
+            ;;
+    esac
+
+    if [ -z "$message" ]; then
+        message="$component"
+        component="${level}"
+        level="info"
+    fi
+
+    local masked
+    masked=$(mask_sensitive_vars "$message")
+    echo "[$timestamp] $level $component $masked"
+}
+
+log_debug() { log "debug" "$1" "${2:-}"; }
+log_info()  { log "info"  "$1" "${2:-}"; }
+log_warn()  { log "warn"  "$1" "${2:-}"; }
+log_error() { log "error" "$1" "${2:-}"; }
+
 cmd_logs() {
     local count="${1:-10}"
     

skills/kugetsu/scripts/kugetsu-queue-daemon.sh

@@ -109,7 +109,6 @@ process_task() {
 
     source "$SCRIPT_DIR/kugetsu-session.sh"
 
-    if worktree_exists "$issue_ref" "$WORKTREES_DIR" || [ -f "$SESSIONS_DIR/$(issue_ref_to_filename "$issue_ref").json" ]; then
     log_file="$LOGS_DIR/delegate-$(date +%s).log"
     if cmd_continue "$issue_ref" "$message" >> "$log_file" 2>&1; then
         sleep 1
@@ -120,18 +119,6 @@ process_task() {
         update_queue_item_state "$queue_id" "error"
         echo "Task $queue_id ($issue_ref) failed to continue"
     fi
-    else
-        log_file="$LOGS_DIR/delegate-$(date +%s).log"
-        if cmd_start "$issue_ref" "$message" >> "$log_file" 2>&1; then
-            sleep 1
-            local session_id=$(get_session_id_for_issue "$issue_ref")
-            update_queue_item_state "$queue_id" "notified" "$session_id" ""
-            echo "Task $queue_id started for $issue_ref"
-        else
-            update_queue_item_state "$queue_id" "error"
-            echo "Task $queue_id ($issue_ref) failed to start"
-        fi
-    fi
 
     release_lock "$issue_ref"
 }

skills/kugetsu/scripts/kugetsu-session.sh

@@ -228,7 +228,6 @@ cmd_delegate() {
     local msg_file="$LOGS_DIR/msg-$new_session.txt"
     printf '%s' "$message" > "$msg_file"
     nohup sh -c "GITEA_TOKEN='${GITEA_TOKEN:-}' opencode run '@$msg_file' --session '$new_session'" >> "$log_file" 2>&1 &
-    rm -f "$msg_file"
     echo "Delegated to new session (logged to $(basename "$log_file"))"
 }
 
@@ -271,12 +270,21 @@ build_dev_agent_message() {
     local number=$(echo "$issue_ref" | grep -oE '#[0-9]+$' | tr -d '#')
     local worktree_path=$(issue_ref_to_worktree_path "$issue_ref")
     
-    local base_message="You are assigned to work on $issue_ref.
+    if [ -n "$user_message" ]; then
+        cat <<EOF
+You are assigned to work on $issue_ref.
+
+IMPORTANT: Follow the workflow below as your guideline, but prioritize the delegator's message.
 
 Workflow:
 1. Read the issue at $instance/$owner/$repo/issues/$number AND all comments on that issue
 2. Check if a PR already exists for this issue
    - If PR exists and is open, review it and learn from it
+   - CRITICAL: Check if PR has merge conflicts before asking for review:
+     - Use: curl -s "https://$instance/api/v1/repos/$owner/$repo/pulls/$number" -H "Authorization: Bearer \$GITEA_TOKEN"
+     - If "mergeable": false, there ARE conflicts - you MUST resolve them FIRST
+     - To resolve: cd to worktree, git fetch origin, git rebase origin/main, resolve conflicts, git rebase --continue, git push --force-with-lease
+     - Only after resolving conflicts (mergeable: true) can you ask for review
    - If PR makes sense to continue, work on it instead
    - If PR is not worth continuing, create a new branch/PR but explain in PR description why you're creating a new one instead of continuing the existing PR
 3. Read README.md (if exists) to understand the general concept of this repository
@@ -286,43 +294,106 @@ Workflow:
 6. If anything is unclear, post a comment on the issue asking for clarification before implementing
 7. Implement the solution
 8. Create a branch named fix/issue-$number and implement the fix
-9. Create a PR when the implementation is complete
+9. Create a PR when the implementation is complete using: tea pr create --repo $owner/$repo --title "Your PR title" --body "PR description"
+   - Make sure you are logged in with: tea login add --name gitea --token \$GITEA_TOKEN --url https://$instance
+   - If tea is not available, use: curl -X POST "https://$instance/api/v1/repos/$owner/$repo/pulls" -H "Authorization: Bearer \$GITEA_TOKEN" -H "Content-Type: application/json" -d '{"title":"PR Title","head":"branch-name","base":"main","body":"PR description"}'
 
-Work directory: $worktree_path"
+Tools for PR interaction:
+- Post issue/PR comment: curl -X POST "https://$instance/api/v1/repos/$owner/$repo/issues/$number/comments" -H "Authorization: Bearer \$GITEA_TOKEN" -H "Content-Type: application/json" -d '{"body":"Your comment"}'
+- List PR comments: curl -s "https://$instance/api/v1/repos/$owner/$repo/issues/$number/comments" -H "Authorization: Bearer \$GITEA_TOKEN"
+- List PR reviews: curl -s "https://$instance/api/v1/repos/$owner/$repo/pulls/$number/reviews" -H "Authorization: Bearer \$GITEA_TOKEN"
+- Merge PR (only with approval): tea pr merge --repo $owner/$repo $number --style merge
+  - MERGING requires approval first! Check for: approval in reviews, OR "lgtm"/"approved" in comments
+  - If no approval, ask reviewer to approve first before merging
 
-    if [ -n "$user_message" ]; then
-        echo "$base_message
+Delegator's message:
+$user_message
 
-Additional instructions from delegator:
-$user_message"
+Work directory: $worktree_path
+EOF
     else
-        echo "$base_message"
+        cat <<EOF
+You are assigned to work on $issue_ref.
+
+Workflow:
+1. Read the issue at $instance/$owner/$repo/issues/$number AND all comments on that issue
+2. Check if a PR already exists for this issue
+   - If PR exists and is open, review it and learn from it
+   - CRITICAL: Check if PR has merge conflicts before asking for review:
+     - Use: curl -s "https://$instance/api/v1/repos/$owner/$repo/pulls/$number" -H "Authorization: Bearer \$GITEA_TOKEN"
+     - If "mergeable": false, there ARE conflicts - you MUST resolve them FIRST
+     - To resolve: cd to worktree, git fetch origin, git rebase origin/main, resolve conflicts, git rebase --continue, git push --force-with-lease
+     - Only after resolving conflicts (mergeable: true) can you ask for review
+   - If PR makes sense to continue, work on it instead
+   - If PR is not worth continuing, create a new branch/PR but explain in PR description why you're creating a new one instead of continuing the existing PR
+3. Read README.md (if exists) to understand the general concept of this repository
+4. Read CONTRIBUTING.md (if exists) to understand how to contribute
+   - If CONTRIBUTING.md doesn't exist, follow steps 5-9 as your guideline
+5. Explore the repository to understand the codebase
+6. If anything is unclear, post a comment on the issue asking for clarification before implementing
+7. Implement the solution
+8. Create a branch named fix/issue-$number and implement the fix
+9. Create a PR when the implementation is complete using: tea pr create --repo $owner/$repo --title "Your PR title" --body "PR description"
+   - Make sure you are logged in with: tea login add --name gitea --token \$GITEA_TOKEN --url https://$instance
+   - If tea is not available, use: curl -X POST "https://$instance/api/v1/repos/$owner/$repo/pulls" -H "Authorization: Bearer \$GITEA_TOKEN" -H "Content-Type: application/json" -d '{"title":"PR Title","head":"branch-name","base":"main","body":"PR description"}'
+
+Tools for PR interaction:
+- Post issue/PR comment: curl -X POST "https://$instance/api/v1/repos/$owner/$repo/issues/$number/comments" -H "Authorization: Bearer \$GITEA_TOKEN" -H "Content-Type: application/json" -d '{"body":"Your comment"}'
+- List PR comments: curl -s "https://$instance/api/v1/repos/$owner/$repo/issues/$number/comments" -H "Authorization: Bearer \$GITEA_TOKEN"
+- List PR reviews: curl -s "https://$instance/api/v1/repos/$owner/$repo/pulls/$number/reviews" -H "Authorization: Bearer \$GITEA_TOKEN"
+  - IMPORTANT: After listing reviews, READ the review comments and incorporate feedback
+  - Check for review state: "APPROVED" means ready to merge, "COMMENT" means feedback to address
+- Merge PR (only with approval): tea pr merge --repo $owner/$repo $number --style merge
+  - MERGING requires approval first! Check for: approval in reviews, OR "lgtm"/"approved" in comments
+  - If no approval, ask reviewer to approve first before merging
+
+Work directory: $worktree_path
+EOF
     fi
 }
 
-cmd_start() {
-    local issue_ref="${1:-}"
-    local message="${2:-}"
+ensure_worktree() {
+    local issue_ref="$1"
     
-    if [ -z "$issue_ref" ]; then
-        echo "Error: issue ref is required" >&2
-        echo "Usage: kugetsu start <issue-ref> [message]" >&2
-        exit 1
+    if worktree_exists "$issue_ref" "$WORKTREES_DIR"; then
+        log "info" "ensure_worktree" "Worktree already exists for $issue_ref"
+        echo "existed"
+        return 0
     fi
     
-    validate_issue_ref "$issue_ref"
-    
     local base_session_id=$(get_base_session_id)
     if [ -z "$base_session_id" ] || [ "$base_session_id" = "null" ]; then
-        echo "Error: Base session not found. Run 'kugetsu init' first." >&2
-        exit 1
+        log "error" "ensure_worktree" "Base session not found for $issue_ref"
+        echo "error"
+        return 1
     fi
     
+    local active_count=$(count_active_dev_sessions)
+    if [ "$active_count" -ge "${MAX_CONCURRENT_AGENTS:-3}" ]; then
+        log "error" "ensure_worktree" "Max concurrent agents reached for $issue_ref"
+        echo "error"
+        return 1
+    fi
+    
+    if create_worktree "$issue_ref" "$WORKTREES_DIR" 2>&1 | tee >(cat >&2); then
+        log "info" "ensure_worktree" "Created worktree for $issue_ref"
+        echo "created"
+        return 0
+    else
+        log "error" "ensure_worktree" "Failed to create worktree for $issue_ref"
+        echo "error"
+        return 1
+    fi
+}
+
+ensure_session() {
+    local issue_ref="$1"
+    
     local session_file=$(issue_ref_to_filename "$issue_ref")
     local session_path="$SESSIONS_DIR/$session_file"
-    local worktree_exists=false
     
-    if worktree_exists "$issue_ref"; then
+    local worktree_exists=false
+    if worktree_exists "$issue_ref" "$WORKTREES_DIR"; then
         worktree_exists=true
     fi
     
@@ -332,38 +403,40 @@ cmd_start() {
     fi
     
     if $worktree_exists && $session_exists; then
-        echo "Issue '$issue_ref' already has a worktree and session." >&2
-        echo "Use 'kugetsu continue $issue_ref' to continue work." >&2
-        exit 1
-    fi
-    
-    if $worktree_exists && ! $session_exists; then
-        echo "Warning: Worktree exists but session is missing. Removing worktree to recreate both..." >&2
-        remove_worktree_for_issue "$issue_ref"
-        worktree_exists=false
+        log "info" "ensure_session" "Session already exists for $issue_ref"
+        echo "continued"
+        return 0
     fi
     
     if ! $worktree_exists && $session_exists; then
-        echo "Warning: Session exists but worktree is missing. Removing stale session to recreate both..." >&2
+        log "warn" "ensure_session" "Session exists but worktree is missing. Removing stale session..."
         rm -f "$session_path"
         remove_issue_from_index "$issue_ref"
         session_exists=false
     fi
     
-    local active_count=$(count_active_dev_sessions)
-    if [ "$active_count" -ge "${MAX_CONCURRENT_AGENTS:-3}" ]; then
-        echo "Error: Max concurrent agents (${MAX_CONCURRENT_AGENTS:-3}) reached. Use 'kugetsu continue' or wait for an agent to finish." >&2
-        exit 1
+    if ! $worktree_exists; then
+        local wt_status=$(ensure_worktree "$issue_ref")
+        if [ "$wt_status" != "created" ] && [ "$wt_status" != "existed" ]; then
+            log "error" "ensure_session" "Failed to ensure worktree for $issue_ref"
+            echo "error"
+            return 1
+        fi
     fi
     
-    create_worktree "$issue_ref" "$WORKTREES_DIR"
+    local base_session_id=$(get_base_session_id)
+    if [ -z "$base_session_id" ] || [ "$base_session_id" = "null" ]; then
+        log "error" "ensure_session" "Base session not found for $issue_ref"
+        echo "error"
+        return 1
+    fi
     
     local new_session_id=$(create_session "$base_session_id")
     
     if [ -z "$new_session_id" ]; then
-        echo "Error: Could not create session" >&2
-        remove_worktree_for_issue "$issue_ref"
-        exit 1
+        log "error" "ensure_session" "Could not create session for $issue_ref"
+        echo "error"
+        return 1
     fi
     
     local worktree_path=$(issue_ref_to_worktree_path "$issue_ref")
@@ -373,81 +446,89 @@ cmd_start() {
     
     add_issue_to_index "$issue_ref" "$session_file"
     
-    local dev_message=$(build_dev_agent_message "$issue_ref" "$message")
+    log "info" "ensure_session" "Created session for $issue_ref: $new_session_id"
+    echo "created"
+    return 0
+}
+
+fork_agent() {
+    local session_id="$1"
+    local worktree_path="$2"
+    local message="$3"
+    
+    if [ -z "$worktree_path" ] || [ ! -d "$worktree_path" ]; then
+        log "error" "fork_agent" "Invalid worktree path: $worktree_path"
+        echo "error"
+        return 1
+    fi
     
     load_agent_env "dev"
     
     cd "$worktree_path"
-    local sanitized_id=$(echo "$new_session_id" | sed 's/[^a-zA-Z0-9_-]/_/g')
-    local msg_file="$worktree_path/.kugetsu-msg.txt"
-    printf '%s' "$dev_message" > "$msg_file"
-    nohup sh -c "GITEA_TOKEN='${GITEA_TOKEN:-}' opencode run '@$msg_file' --session '$new_session_id'" >> "$LOGS_DIR/dev-$sanitized_id.log" 2>&1 &
+    local sanitized_id=$(echo "$session_id" | sed 's/[^a-zA-Z0-9_-]/_/g')
+    mkdir -p "$worktree_path/.kugetsu"
+    if [ ! -f "$worktree_path/.gitignore" ] || ! grep -q "^.kugetsu/" "$worktree_path/.gitignore"; then
+        echo ".kugetsu/" >> "$worktree_path/.gitignore" 2>/dev/null || true
+    fi
+    local msg_file="$worktree_path/.kugetsu/msg.txt"
+    printf '%s' "$message" > "$msg_file"
+    nohup sh -c "GITEA_TOKEN='${GITEA_TOKEN:-}' opencode run '@$msg_file' --session '$session_id'" >> "$LOGS_DIR/dev-$sanitized_id.log" 2>&1 &
     
-    echo "Session started for '$issue_ref': $new_session_id"
-    echo "Worktree: $worktree_path"
+    log "info" "fork_agent" "Forked agent for session $session_id in $worktree_path"
+    echo "forked"
+    return 0
+}
+
+cmd_start() {
+    cmd_continue "$@"
 }
 
 cmd_continue() {
-    local session_name=""
-    local message=""
-    local args=("$@")
+    local issue_ref="${1:-}"
+    local message="${2:-}"
     
-    args=$(set_debug_mode "${args[@]}")
-
-    for arg in $args; do
-        if [ -z "$session_name" ]; then
-            session_name="$arg"
-        else
-            message="$arg"
-        fi
-    done
-    
-    if [ -z "$session_name" ]; then
+    if [ -z "$issue_ref" ]; then
         echo "Error: issue ref is required" >&2
         echo "Usage: kugetsu continue <issue-ref> [message]" >&2
         exit 1
     fi
     
-    validate_issue_ref "$session_name"
-    
-    local session_file=$(get_session_for_issue "$session_name")
-    if [ -z "$session_file" ] || [ "$session_file" = "null" ]; then
-        echo "Error: No session found for '$session_name'" >&2
-        echo "Use 'kugetsu start $session_name' to create a new session." >&2
-        exit 1
-    fi
-    
-    local session_path="$SESSIONS_DIR/$session_file"
-    
-    if [ ! -f "$session_path" ]; then
-        echo "Error: Session file not found: $session_path" >&2
-        exit 1
-    fi
-    
-    load_agent_env "dev"
-    
-    local opencode_session_id=$(python3 -c "import json; print(json.load(open('$session_path')).get('opencode_session_id', ''))" 2>/dev/null || echo "")
-    local worktree_path=$(python3 -c "import json; print(json.load(open('$session_path')).get('worktree_path', ''))" 2>/dev/null || echo "")
-    local issue_ref=$(python3 -c "import json; print(json.load(open('$session_path')).get('issue_ref', ''))" 2>/dev/null || echo "")
-    
-    if [ -z "$worktree_path" ] || [ ! -d "$worktree_path" ]; then
-        echo "Warning: Worktree is missing for '$session_name'. Recovering..." >&2
-        rm -f "$session_path"
-        remove_issue_from_index "$session_name"
-        echo "Calling cmd_start to create new session and worktree..." >&2
-        cmd_start "$session_name" "$message"
-        return $?
-    fi
+    validate_issue_ref "$issue_ref"
     
     if [ -z "$message" ]; then
         message=$(build_dev_agent_message "$issue_ref" "")
+    else
+        message=$(build_dev_agent_message "$issue_ref" "$message")
     fi
     
-    cd "$worktree_path"
-    local sanitized_id=$(echo "$opencode_session_id" | sed 's/[^a-zA-Z0-9_-]/_/g')
-    local msg_file="$worktree_path/.kugetsu-msg.txt"
-    printf '%s' "$message" > "$msg_file"
-    nohup sh -c "GITEA_TOKEN='${GITEA_TOKEN:-}' opencode run '@$msg_file' --session '$opencode_session_id'" >> "$LOGS_DIR/dev-$sanitized_id.log" 2>&1 &
+    local worktree_status=$(ensure_worktree "$issue_ref")
+    if [ "$worktree_status" = "error" ]; then
+        echo "Error: Failed to ensure worktree for '$issue_ref'" >&2
+        exit 1
+    fi
+    
+    local session_status=$(ensure_session "$issue_ref")
+    if [ "$session_status" = "error" ]; then
+        echo "Error: Failed to ensure session for '$issue_ref'" >&2
+        exit 1
+    fi
+    
+    local session_file=$(issue_ref_to_filename "$issue_ref")
+    local session_path="$SESSIONS_DIR/$session_file"
+    local opencode_session_id=$(python3 -c "import json; print(json.load(open('$session_path')).get('opencode_session_id', ''))" 2>/dev/null || echo "")
+    local worktree_path=$(python3 -c "import json; print(json.load(open('$session_path')).get('worktree_path', ''))" 2>/dev/null || echo "")
+    
+    local fork_status=$(fork_agent "$opencode_session_id" "$worktree_path" "$message")
+    if [ "$fork_status" = "error" ]; then
+        echo "Error: Failed to fork agent for '$issue_ref'" >&2
+        exit 1
+    fi
+    
+    log "info" "cmd_continue" "Result for $issue_ref: worktree=$worktree_status session=$session_status fork=$fork_status"
+    
+    echo "Session continued for '$issue_ref': $opencode_session_id"
+    echo "Worktree: $worktree_path"
+    echo "${worktree_status}-${session_status}-${fork_status}"
 }
 
 cmd_list() {