daemon.cjs · part 300

60 text occurrences from desktop/Cursor.app/Contents/Resources/app/extensions/cursor-agent-host/dist/agent-host-daemon/dist/bin/daemon.cjs, part 300. Every entry preserves the shipped literal and its saved verdict or selection reason.

File contents and all parts · All files

Subagent state ref blob not found; falling back to inline entry

conversationStartedTimestampMs was set without conversationStartedTimeZone

conversationStartedTimeZone was set without conversationStartedTimestampMs

Failed to hydrate user message text blob

Failed to hydrate user message rich text blob

Serializing message took more than 10 seconds

Cannot compute root prompt pass-through after root prompt prefix was invalidated

Large conversation state serialize

Unknown resume mode: ${_exhaustiveCheck}

Expected shell turn

<image_files>
The following images were provided by the user and saved to disk for future use:
${imageFilePaths.map((path53, i) => `${i + 1}. ${path53}`).join("\n")}

These files can be read with tools, copied to other locations, or attached to subagents using the file_attachments parameter.
</image_files>

${i + 1}. ${path53}

<system_reminder>
${formatProjectPrompt(isProjectKickoff ? "initial" : resolveProjectCadenceKind({
          priorTurnCount: this.turns.length,
          interval: config2.projectReminderCadenceIntervalGenerator?.() ?? config2.projectReminderCadenceInterval
        }), {
          projectName,
          initDescription: projectInitDescription,
          promptText: config2.projectPromptTextGenerator?.(),
          guidanceText: config2.projectPromptGuidanceGenerator?.(),
          sendMessageToolName,
          coordinatorToolsEnabled: config2.featureFlags?.cloudCoordinatorToolsEnabled === true,
          coordinatorProgressEnabled: config2.featureFlags?.cloudCoordinatorProgressEnabled === true,
          coordinatorSteerFollowupsEnabled: config2.featureFlags?.cloudCoordinatorSteerFollowupsEnabled === true,
          coordinatorPlacementConsentEnabled: config2.featureFlags?.cloudCoordinatorPlacementConsentEnabled === true,
          coordinatorAskQuestionEnabled: config2.featureFlags?.cloudCoordinatorAskQuestionEnabled !== false,
          // Turn budget applied here, where the exact prior-turn count is
          // known on every path.
          firstProjectOnboarding: clampFirstProjectOnboardingForTurn(config2.firstProjectOnboarding, this.turns.length)
        })}
</system_reminder>

<system_reminder>
${projectChildPrompt}
</system_reminder>

<system_reminder>
${formatWorkerParentMessagingPrompt()}
</system_reminder>

<system_reminder>
${formatMidLevelParentMessagingPrompt()}
</system_reminder>

<system_reminder>
${userMessage.subagentSystemReminder}
</system_reminder>

${MODEL_SWITCH_REMINDER}

<system_reminder>
IMPORTANT: It is bad to be over-eager with making edits vs just answering the question when that is not what the user wants. Think carefully before deciding to edit.
</system_reminder>

${currentTimePrefix}<user_query>
${eagerEditingNote}${userMessage.text}
</user_query>

Expected agent turn

use strict

use strict

use strict

use strict

Lifecycle transitions for the delayed long-reasoning reminder experiment

Per-call hidden reasoning tokens at eligible experiment opportunities

use strict

use strict

use strict

use strict

use strict

use strict

Tool not found: ${effectiveToolName}. Available tools: ${Object.keys(toolMap).join(", ")}

semantic search usage detected

semantic search usage detected

WritableIterable is closed

Error closing tool call stream

No current stream found

Unknown error

Execution backend unavailable. Tool execution skipped.

Execution backend unavailable. Tool execution skipped.

Unknown tool error

use strict

Duration of tool call execution in milliseconds

Result status of tool call execution

Approximate number of tokens in raw model-produced tool call arguments (argsText.length / 4)

Tool-call stream chunks whose id collided with an already-handled or in-flight tool call in the same model response

Error writing to tool call stream

Error writing to tool call stream

Pending tool contract mismatch for ${options2.descriptor.toolName}: expected effective tool ${options2.contract.effectiveToolName}, but none resolved

Pending tool contract mismatch for ${effectiveToolName}: expected ${expected}, got ${actual.toolIdentifier}

use strict

[SUGGESTION MODE: Suggest what user might naturally type next into Cursor.]

FIRST: Look at user's recent messages and original request.

Your job is to predict what THEY would type - not what you think they should do.

THE TEST: Would they think "I was just about to type that"?

User asked "fix the bug and run tests", bug is fixed → "run the tests"

After code written → "Try it out"

Cursor offers options → suggest the one the user would likely pick, based on conversation