export declare const HANDOFF_TEMPLATE = "# Handoff Command\n\n## Purpose\n\nUse /handoff when:\n- The current session context is getting too long and quality is degrading\n- You want to start fresh while preserving essential context from this session\n- The context window is approaching capacity\n\nThis creates a detailed context summary that can be used to continue work in a new session.\n\n---\n\n# PHASE 0: VALIDATE REQUEST\n\nBefore proceeding, confirm:\n- [ ] There is meaningful work or context in this session to preserve\n- [ ] The user wants to create a handoff summary (not just asking about it)\n\nIf the session is nearly empty or has no meaningful context, inform the user there is nothing substantial to hand off.\n\n---\n\n# PHASE 0.5: SESSION READ FIRST (MANDATORY FIRST DATA STEP)\n\nCall session_read({ session_id: \"$SESSION_ID\" }) BEFORE any other context gathering step. The output of session_read is the only authoritative source for what the user originally asked. Do not reconstruct memory of the first request; long sessions and post-compact sessions truncate or summarize early messages, so in-context memory is unreliable.\n\nFrom the session_read output:\n\n1. Find the first user message in the returned session history (the earliest entry with role \"user\").\n2. Copy the text of that first user message verbatim into a working note. You will later place it into the USER REQUESTS (AS-IS) section unchanged.\n3. If the user has sent multiple distinct top-level requests in the session, also collect each subsequent verbatim user message that is a new top-level ask (not a follow-up clarification).\n\nRules:\n- Do not reconstruct user requests from memory. Always quote from session_read output.\n- Do not paraphrase, summarize, or \"tidy up\" the user's wording.\n- Do not skip session_read even if you feel you remember the first user message.\n- If session_read fails or returns no user messages, state that explicitly in the USER REQUESTS (AS-IS) section rather than guessing.\n\n---\n\n# PHASE 1: GATHER PROGRAMMATIC CONTEXT\n\nExecute these tools to gather concrete data:\n\n1. session_read({ session_id: \"$SESSION_ID\" }) - full session history (already executed in PHASE 0.5; reuse its output here)\n2. todoread() - current task progress\n3. Bash({ command: \"git diff --stat HEAD~10..HEAD\" }) - recent file changes\n4. Bash({ command: \"git status --porcelain\" }) - uncommitted changes\n\nSuggested execution order:\n\n```\nsession_read({ session_id: \"$SESSION_ID\" })  # already called in PHASE 0.5\ntodoread()\nBash({ command: \"git diff --stat HEAD~10..HEAD\" })\nBash({ command: \"git status --porcelain\" })\n```\n\nAnalyze the gathered outputs to understand:\n- What work was completed\n- What tasks remain incomplete (include todo state)\n- What decisions were made\n- What files were modified or discussed (include git diff/stat + status)\n- What patterns, constraints, or preferences were established\n\nUSER REQUESTS were already captured verbatim from session_read in PHASE 0.5; do not re-derive them here.\n\n---\n\n# PHASE 2: EXTRACT CONTEXT\n\nWrite the context summary from first person perspective (\"I did...\", \"I told you...\").\n\nFocus on:\n- Capabilities and behavior, not file-by-file implementation details\n- What matters for continuing the work\n- Avoiding excessive implementation details (variable names, storage keys, constants) unless critical\n- USER REQUESTS (AS-IS) must come from the PHASE 0.5 session_read extraction, copied verbatim (do not paraphrase, do not reconstruct from memory)\n- EXPLICIT CONSTRAINTS must be verbatim only (do not invent)\n\nQuestions to consider when extracting:\n- What did I just do or implement?\n- What instructions did I already give which are still relevant (e.g. follow patterns in the codebase)?\n- What files did I tell you are important or that I am working on?\n- Did I provide a plan or spec that should be included?\n- What did I already tell you that is important (libraries, patterns, constraints, preferences)?\n- What important technical details did I discover (APIs, methods, patterns)?\n- What caveats, limitations, or open questions did I find?\n\n---\n\n# PHASE 3: FORMAT OUTPUT\n\nGenerate a handoff summary using this exact format:\n\n```\nHANDOFF CONTEXT\n===============\n\nUSER REQUESTS (AS-IS)\n---------------------\n- [Exact verbatim user requests - NOT paraphrased]\n\nGOAL\n----\n[One sentence describing what should be done next]\n\nWORK COMPLETED\n--------------\n- [First person bullet points of what was done]\n- [Include specific file paths when relevant]\n- [Note key implementation decisions]\n\nCURRENT STATE\n-------------\n- [Current state of the codebase or task]\n- [Build/test status if applicable]\n- [Any environment or configuration state]\n\nPENDING TASKS\n-------------\n- [Tasks that were planned but not completed]\n- [Next logical steps to take]\n- [Any blockers or issues encountered]\n- [Include current todo state from todoread()]\n\nKEY FILES\n---------\n- [path/to/file1] - [brief role description]\n- [path/to/file2] - [brief role description]\n(Maximum 10 files, prioritized by importance)\n- (Include files from git diff/stat and git status)\n\nIMPORTANT DECISIONS\n-------------------\n- [Technical decisions that were made and why]\n- [Trade-offs that were considered]\n- [Patterns or conventions established]\n\nEXPLICIT CONSTRAINTS\n--------------------\n- [Verbatim constraints only - from user or existing AGENTS.md]\n- If none, write: None\n\nCONTEXT FOR CONTINUATION\n------------------------\n- [What the next session needs to know to continue]\n- [Warnings or gotchas to be aware of]\n- [References to documentation if relevant]\n```\n\nRules for the summary:\n- Plain text with bullets\n- No markdown headers with # (use the format above with dashes)\n- No bold, italic, or code fences within content\n- Use workspace-relative paths for files\n- Keep it focused - only include what matters for continuation\n- Pick an appropriate length based on complexity\n- USER REQUESTS (AS-IS) and EXPLICIT CONSTRAINTS must be verbatim only\n\n---\n\n# PHASE 4: PROVIDE INSTRUCTIONS\n\nAfter generating the summary, instruct the user:\n\n```\n---\n\nTO CONTINUE IN A NEW SESSION:\n\n1. Press 'n' in OpenCode TUI to open a new session, or run 'opencode' in a new terminal\n2. Paste the HANDOFF CONTEXT above as your first message\n3. Add your request: \"Continue from the handoff context above. [Your next task]\"\n\nThe new session will have all context needed to continue seamlessly.\n```\n\n---\n\n# IMPORTANT CONSTRAINTS\n\n- DO NOT attempt to programmatically create new sessions (no API available to agents)\n- DO provide a self-contained summary that works without access to this session\n- DO include workspace-relative file paths\n- DO NOT include sensitive information (API keys, credentials, secrets)\n- DO NOT exceed 10 files in the KEY FILES section\n- DO keep the GOAL section to a single sentence or short paragraph\n\n---\n\n# EXECUTE NOW\n\nBegin by gathering programmatic context, then synthesize the handoff summary.\n";