Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.qredence.ai/llms.txt

Use this file to discover all available pages before exploring further.

Fleet Pi exposes the same chat surface in three distinct modes. The mode is sent on every /api/chat request as mode: "agent" | "plan" | "harness" and decides which tool allowlist the Pi runtime receives. The full list of available tools and per-mode allowlists lives in apps/web/src/lib/pi/plan-mode.ts.

​
Agent mode

Agent mode is the default and the broadest. It enables full repo-scoped editing and the Pi-managed extension tools. Allowed tools
ToolPurpose
readRead a file from the repo
writeCreate or overwrite a file
editString-replace inside a file
bashExecute shell commands inside the project root
workspace_writeDurable agent-workspace/ updates with rationale fields
resource_installInstall Pi skills, prompts, extensions, themes, packages
questionnaireAsk the user a structured follow-up question
web_fetchFetch a URL with safety-checked allowlist
project_inventory, workspace_indexProject-resource introspection
autocontext_*Pi autocontext judge, improve, queue, snapshot tools
init_experiment, run_experiment, log_experimentPi autoresearch tools
subagentDelegate work to a subagent

​
Plan mode

Plan mode is read-only. The agent inspects the repo, asks focused follow-up questions, and produces numbered execution plans. Structured plan cards keep execute, stay, and refine actions visible after page refresh or session resume — backed by persisted custom session entries so legacy text parsing remains a fallback. Allowed tools read, bash (inspection only — mutating shell activity is blocked with an explicit reason), grep, find, ls, questionnaire, project_inventory, workspace_index, and the read-only autocontext_status family. Behavior contract
  • Tool allowlist is inspection-only.
  • Blocked shell commands return an explicit reason instead of silently mutating the repo.
  • Plan state is emitted on the stream as plan events that include { executing, completed, total, todos, message, state }.
  • Plan cards survive refresh because Plan mode persists structured entries to the Pi session file.
See evaluatePlanCommand and applyPlanModeSelection in apps/web/src/lib/pi/plan-mode.ts for the exact enforcement logic.

​
Harness mode

Harness mode is for workspace-architecture work. It swaps general repo-mutation tools (write, edit) for the workspace-aware workspace_write and resource_install tools so durable changes always go through the adaptive workspace contract. Allowed tools read, bash, grep, find, ls, workspace_write, resource_install, questionnaire, web_fetch, plus the project-resource and autocontext-status families. When to use it
  • Adding or changing canonical files under agent-workspace/memory/, plans/, skills/, evals/, or artifacts/.
  • Installing Pi skills, prompts, extensions, themes, or packages.
  • Authoring workspace policies or evaluation material that must include rationale.
workspace_write requires a rationale for protected or rationale-required areas. resource_install is the only supported way to add chat-installed Pi resources under agent-workspace/pi/*.

​
Streaming behavior

Two streaming behaviors decide how prompts queued mid-stream are handled:
  • streamingBehavior: "steer" — enqueue the message as a steering prompt for the active assistant turn.
  • streamingBehavior: "followUp" — enqueue the message to run after the current turn finishes.
Steering and follow-up queues are surfaced on the stream as queue events.

API reference

The chat endpoints and the full stream event taxonomy.

Adaptive workspace

Where workspace_write is allowed to write, and why.