Skip to main content

​
Managing Context

**Screenshot: Context meter in the chat header — show it at ~65% capacity with the “Compact now” suggestion tooltip visible.
Every chat session has a context window — the amount of conversation history and injected context the model can hold at once. ADE shows the context fill level as a meter in the chat header.
When the context meter reaches 70%, ADE suggests compaction. If auto-compaction is enabled (configured in Settings → Chat → Auto-compact threshold), ADE compacts automatically without prompting.Compaction summarizes older messages while preserving:
  • Key decisions made in the session
  • File paths and code blocks from recent turns
  • Current task state and open questions
  • Tool call results from the last few turns
Compaction is lossy by design — exact wording of older messages is not preserved. If there is something in the conversation you want the agent to remember verbatim (e.g., a specific constraint), call it out explicitly before compacting: “Remember: the API must remain backwards compatible with v1 clients.”

​
Context Doc Preferences

ADE generates context docs (PRD, architecture overview) from your codebase to seed agent sessions with project-level knowledge. You can configure how these docs are generated in Settings > Context:
  • Model — choose which AI model generates the docs
  • Reasoning effort — control the depth of analysis
  • Auto-refresh events — select which project events trigger a doc regeneration (e.g., on commit, on PR create, on mission start)
Preferences are saved automatically and persist across sessions. Changes take effect the next time context docs are regenerated, either manually or via a configured event trigger.

​
MCP Tool Visibility and Control

The chat header shows a badge indicating how many MCP tools are active for the current session. Click it to open the MCP tool panel:
  • View all configured MCP servers and their available tools
  • Toggle individual tool groups on or off for this session
  • See which tools have been called in the current session and their call counts
Disabling a tool group mid-session takes effect immediately — the agent will not invoke those tools in subsequent turns, though any in-flight tool calls complete normally.
MCP tool changes are session-scoped. They do not affect the lane’s default configuration. To change defaults, go to Settings → MCP Servers.

​
Working with Artifacts

At the end of a session (or mid-session when the agent produces notable outputs), artifacts are surfaced for your review.

​
Artifact types produced in chat

ArtifactWhen it appears
File changesAfter any file write tool call
ScreenshotsAfter any computer-use visual capture
Browser tracesAfter browser automation sequences
PR linksAfter a PR is created
Test reportsAfter test runner tool calls
NotesWhen the agent explicitly attaches a note

​
What you can do with artifacts

1

Keep — attach to lane pack

Promotes the artifact into the lane’s persistent context. Future chat sessions and missions will have access to it via context injection.
2

Attach to Mission / PR / Linear issue

Links the artifact to an existing Mission, opens it for attachment to a PR description, or creates a Linear issue attachment.
3

Download

Saves the artifact to your local filesystem (useful for screenshots and browser traces).
4

Dismiss

Removes the artifact from the session’s artifact list. It remains accessible in the session’s History entry but is not promoted.

​
Chat History and Sessions

Every chat session is stored with its full transcript, tool call log, timing data, and attached artifacts. Access sessions from the History tab within a Lane view. Each entry shows:
  • Session start time and duration
  • Message count and token total
  • Model used
  • Number of tool calls
  • Artifacts produced
Click any session to open its transcript in read-only view. Click Resume to open a new chat session seeded with the previous session’s summary.

​
Troubleshooting

The agent’s file access is always live — it reads from the filesystem at the time of the tool call. If your changes are not reflected, check:
  1. Are the changes saved? The agent reads saved files, not editor buffers.
  2. Is the agent working in the correct lane? Confirm the lane selector in the chat header.
  3. Ask the agent explicitly: “Re-read src/foo.ts and tell me what you see.”
If the session context is very large (deeply nested tool call results, very long files), compaction may not free enough space. Options:
  • Start a new session — previous context is preserved in History
  • Ask the agent to summarize key decisions and start fresh with that summary
  • Switch to a model with a larger context window in the model selector
The computer-use monitoring panel only appears when a computer-use tool is actively being invoked. If the panel is not showing:
  • Confirm the session’s computer-use policy is not CU Off
  • Check Settings → Computer Use to confirm a backend (Ghost OS, agent-browser) is connected
  • Verify the agent’s task actually requires visual interaction — the agent will not invoke computer use for purely code-based tasks even in CU On mode unless a visual task is present
If an external MCP tool call fails consistently:
  1. Open the MCP tool panel from the chat header and check the server’s status indicator.
  2. Go to Settings → MCP Servers and click Test connection for the failing server.
  3. Check the server’s logs — ADE surfaces MCP server stderr in the settings panel.
  4. Disable the failing tool group for the session to unblock the agent while you investigate.
PR creation uses the lane’s current branch. If the agent created a PR on the wrong branch:
  1. Close or update the PR in GitHub directly.
  2. In the chat, tell the agent: “You created the PR on the wrong branch. The correct branch is feature/xyz. Please update or re-create the PR.”
  3. To prevent this in future sessions, use an explicit branch name when asking for a PR: “create a PR from feature/xyz to main.”
This usually indicates the agent is not seeing the tool’s output correctly, or the task goal is ambiguous. Try:
  1. Press Escape to interrupt the current turn.
  2. Clarify the goal: “Stop. The issue is X. I need you to Y instead.”
  3. If the loop continues after clarification, start a new session with a more explicit initial prompt.