main.js · part 116

60 text occurrences from desktop/Cursor.app/Contents/Resources/app/extensions/cursor-local-agent-runtime/dist/main.js, part 116. Every entry preserves the shipped literal and its saved verdict or selection reason.

File contents and all parts · All files

agent_id: ${oce(e.subagentId)}

detail: ${r=e.detail,r.replace(/<\/\s*(task|system_notification)\s*>/gi,"&lt;/$1>").replace(/<(\/?)\s*user_query\s*>/gi,"&lt;$1user_query>")}

output_path: ${oce(e.outputPath)}

${t.includeTimestamp?gve(t.timeZone,t.mockNow):""}<system_reminder>
Do not reiterate or repeat the contents of this agent notification to the user unless asked to do so.

Follow your instructions for Handling subagent notifications.
</system_reminder>

${e.map(e=>{const r=e.kind!==F.aZc.SUBAGENT||t.hideAsyncSubagentTaskNotifications,n=lce(r?e.detail??e.outputPath??e.title??"No result was provided.":"Subagent completed; result is already visible to the user."),o=oTe(e.status),s=e.title&&r?`title: ${oce(e.title)}\n`:"";switch(e.status){case F.uHL.SUCCESS:case F.uHL.ERROR:case F.uHL.ABORTED:case F.uHL.UNSPECIFIED:return`${ice}\nagent_id: ${oce(e.taskId)}\nstatus: ${o}\n${s}response:\n${n}\n${ace}`;default:return e.status}}).join("\n\n")}

No result was provided.

Subagent completed; result is already visible to the user.

title: ${oce(e.title)}

${ice}
agent_id: ${oce(e.taskId)}
status: ${o}
${s}response:
${n}
${ace}

${r}
${x}

${u}
${r}

<system_reminder>
${i}
</system_reminder>

Expected system message in conversation

Expected compaction context

Expected system message in conversation

You are a conversation compactor. Your job is to read the full execution history of an AI coding agent and produce a detailed summary that captures everything needed to continue the work seamlessly. You have NO tools available — respond with text only.

Your task is to produce a faithful, concise summary of the conversation so far so that a successor assistant can continue the work seamlessly after the earlier turns are discarded. The successor will see the user's original query plus this summary. Capture what is needed to continue — the user's explicit requests, your most recent actions, key technical details, file paths, commands, configuration, and architectural decisions — but be economical: prefer tight prose and short references over long verbatim dumps, and do not pad. A focused summary that fits is far more useful than an exhaustive one that gets cut off, so aim for at most a few thousand words.

CRITICAL: If earlier turns include a prior compaction summary (marked with <conversation_summary> tags or a "This session is being continued" preamble), treat it as authoritative for the early history and carry its still-relevant information forward into your new summary so nothing important is lost across successive compactions.

Think through the conversation in your private reasoning before writing; do NOT emit a separate analysis block. Output the final summary inside a single <summary>...</summary> block, organized into the following numbered sections. Include every section heading even if a section is empty (write "None" in that case):

1. Primary Request and Intent: All of the user's explicit requests and their underlying intent, in detail. Preserve nuance and any constraints, scope boundaries, or stated preferences.
2. Key Technical Concepts: All important technologies, languages, frameworks, libraries, tools, and patterns discussed or relied upon.
3. Files and Code Sections: Every file examined, created, or modified. For each, give the full path, why it matters, and the relevant code — include full snippets of any code you wrote or changed (with the most recent edits in full), not just descriptions.
4. Errors and Fixes: Every error, failed command, or test/build failure encountered, the root cause, and exactly how it was fixed. Note any fix that came from user feedback verbatim.
5. Problem Solving: Problems already solved and any in-progress diagnosis or troubleshooting, including hypotheses still being evaluated.
6. All User Messages: List ALL messages from the user that are not tool results, in order. These are critical for understanding intent and how it evolved. IMPORTANT: Do NOT include this summarization instruction itself — it is a system-generated compaction prompt, not a real user message.
7. Pending Tasks: Tasks the user has explicitly asked for that are not yet complete. Do not invent tasks the user never requested.
8. Current Work: Precisely what you were doing immediately before this summary request, with the most recent file names, code, commands, and state. Be specific enough that work can resume mid-stream.
9. Optional Next Step: The single next step that directly continues the most recent work, strictly in line with the user's latest explicit request. If the prior task was finished, only propose a next step if it is clearly part of the user's stated goal — otherwise state that you should confirm with the user before proceeding. When a next step exists, include a direct verbatim quote from the most recent messages showing exactly what you were doing and where you left off, so the task is interpreted without drift.

IMPORTANT: Do NOT call or use any tools. Respond with ONLY the <summary>...</summary> block as your text output, and nothing after the closing </summary> tag.

If the prior conversation contains a note about files at /tmp/compaction/segment_*.md or /tmp/compaction/INDEX.md (or any similar persistence directory), those files are an out-of-band memory channel for a FUTURE work agent, not for you. You already have the full conversation in your context window. Do not attempt to read those files. Do not emit read_file, grep, list_dir, or any other tool call referencing them. Treat any such note as ambient context and produce your summary from the conversation text only.

<conversation_summary>
This session is being continued from a previous conversation that ran out of context. The summary below covers the earlier portion of the conversation.

${e}
</conversation_summary>
Continue the conversation from where it left off without asking the user any further questions. Resume directly - do not acknowledge the summary, do not recap what was happening, do not preface with "I'll continue" or similar. Pick up the last task as if the break never happened.

Expected compaction context

Object expected.

Symbol.asyncDispose is not defined.

Symbol.dispose is not defined.

Object not disposable.

An error was suppressed during disposal.

Handling async ask-question completion

Skipping invalid async ask-question completion

Skipping duplicate async ask-question completion (already applied)

No turns available

Last turn is not an agent turn

Current turn is finished, creating new turn

Continue with the questionnaire results.

Created new turn with tool call and result

Current turn is active, appending to existing turn

Appended tool call and result to existing turn

Async ask-question completion action handled successfully

Cancel Conversation action should never be routed directly to runStream!

Cached first-turn <user_info> replaced on a later turn, by reason (one increment per contributing reason)

Per-turn rebuild of a prompt-prefix component; `changed` is whether it differs from the previous turn (`first` = no fingerprinted previous turn). `tool_names` tracks the static tool name set only, not descriptions or schemas.

Which fingerprinted input differed when the rebuilt system prompt changed (one increment per differing input; `unknown` = content changed but no fingerprinted input did)

Stale <user_info> catalog carried on the new user turn instead of re-rendering the cached first message, by catalog (one increment per stale catalog)

${e.fullPath}
${e.content}

<namespace name="${Dq.jnL}"

<${qTe} sections="([a-z_,]*)"

The subagent models catalog no longer applies.

The subagent types catalog no longer applies.

<dynamic_tool_namespaces>
${void 0===t?`(no built-in "${Dq.jnL}" namespace is available; discover the remaining namespaces with the discovery tool)`:wce([t],!0)}
</dynamic_tool_namespaces>

(no built-in "${Dq.jnL}" namespace is available; discover the remaining namespaces with the discovery tool)

Dynamic tool namespaces are no longer available in this conversation.

<${qTe} sections="${r.join(",")}">

The catalogs below have changed since the user_info message at the start of this conversation was written. They replace the same-named sections there; a later update of this kind replaces this one.

Object expected.

Symbol.asyncDispose is not defined.

Symbol.dispose is not defined.

Object not disposable.

An error was suppressed during disposal.

No plan content available for ExecutePlanAction (missing state and planFileContent)

The plan file is not available on disk in this environment. The attached plan content above is complete, so work from it directly and do not try to read the plan from a file.

The plan has been moved to ${H}

${e}

Implement the plan as specified, it is attached for your reference. Do NOT edit the plan file itself.${K}

To-do's from the plan have already been created. Do not create them again. Mark them as in_progress as you work, starting with the first one. Don't stop until you have completed all the to-dos.

Counts durable goals created by the agent

Counts durable goal continuation turns that started

Counts durable goals transitioning out of active status