🤖 refactor: move compaction logic to backend #670

ethanndickson · 2025-11-18T07:02:15Z

Generated with mux

Stack

Summary

Moves history compaction handling from WorkspaceStore (frontend) to agentSession (backend) to centralize server-side operations and fix race conditions.

Relates to #651.

Changes

Backend (agentSession.ts)

Added handleCompactionCompletion() - detects compaction stream-end, extracts summary from event.parts, performs history replacement
Added handleCompactionAbort() - handles Ctrl+A (accept early with [truncated]) and Ctrl+C (cancel) flows
Added performCompaction() - atomically replaces chat history with summary message including cumulative usage
Implemented abandonPartial flag flow from IPC through to StreamAbortEvent
Extracts truncated message content from history instead of partialService

Frontend (WorkspaceStore.ts)

Removed handleCompactionCompletion() and handleCompactionAbort() methods
Removed performCompaction() method
Removed processedCompactionRequestIds Set
Simplified cancelCompaction() - just calls interruptStream with abandonPartial: true
Fixed Ctrl+A keybind to pass abandonPartial: false for early accept

Shared

Updated StreamAbortEvent to include abandonPartial?: boolean
historyService.clearHistory() now returns deleted sequence numbers
Created calculateCumulativeUsage() utility in displayUsage.ts to extract and sum usage from messages

Testing

Manual: /compact completes successfully
Manual: Ctrl+A during compaction accepts early with [truncated]
Manual: Ctrl+C during compaction cancels and enters edit mode
Verify cumulative usage preserved across multiple compactions

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

src/node/services/agentSession.ts

ethanndickson · 2025-11-18T07:15:40Z

@codex review

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

src/node/services/agentSession.ts

ethanndickson · 2025-11-18T07:29:13Z

@codex review

src/common/utils/tokens/displayUsage.ts

src/browser/utils/compaction/handler.ts

src/node/services/agentSession.ts

ethanndickson · 2025-11-19T02:40:45Z

tests/ipcMain/sendMessage.test.ts


          // Wait for first stream to complete
          const collector1 = createEventCollector(env.sentEvents, workspaceId);
-          await collector1.waitForEvent("stream-end", 30000);


This was flaking on Thomas' PRs too, so I've bumped the timeout

src/node/services/compactionHandler.ts

src/common/utils/tokens/displayUsage.ts

ibetitsmike

lgtm but I'd add some testing

## Stack 1. #685 1. #683 1. #670 1. #650 ⬅ This PR (base) ## Problem Compact continue messages were handled by a frontend hook that watched workspace states and manually sent continue messages after compaction. This was complex, had potential race conditions, and poor separation of concerns. Relates to #651. ## Solution Use the existing message queue system: - Backend queues continue message when compaction starts - Queue auto-sends when stream ends (existing behavior) - Clear queue on error paths **Benefits:** Simpler (-134 lines), more reliable, better UX (continue message visible in queue). _Generated with `mux`_

Move history compaction handling from WorkspaceStore to agentSession to centralize server-side operations. Backend changes: - Added handleCompactionCompletion() to detect and handle compaction stream-end events - Added handleCompactionAbort() to handle Ctrl+A (accept early with [truncated]) and Ctrl+C (cancel) flows - Added performCompaction() to atomically replace chat history with summary message - Added processedCompactionRequestIds Set to dedupe repeated compaction events - Implemented abandonPartial flag flow from IPC through to StreamAbortEvent - Extract truncated message content from history instead of partialService - Wrap compaction handlers in try-catch to ensure stream events always forwarded - Made performCompaction return Result type for proper error handling Frontend changes: - Removed compaction handlers from WorkspaceStore - Simplified cancelCompaction() to just call interruptStream with abandonPartial flag - Fixed Ctrl+A keybind to pass abandonPartial: false for early accept Shared changes: - Updated StreamAbortEvent to include abandonPartial flag - historyService.clearHistory() now returns deleted sequence numbers - Created calculateCumulativeUsage() utility to extract and sum usage from messages - aiService respects abandonPartial flag - skips committing when true

Move compaction handling from agentSession to dedicated CompactionHandler class. Changes: - Created src/node/services/compactionHandler.ts with CompactionHandler class - Extracted handleAbort, handleCompletion, and performCompaction methods - Updated agentSession.ts to delegate to CompactionHandler - Moved frontend compaction handler to browser utils - Reduced agentSession.ts from 764 to 589 lines Benefits: - Better separation of concerns - Easier to test compaction logic independently - Cleaner session orchestration code _Generated with `mux`_

## Stack 1. #685 1. #683 ⬅ This PR 1. #670 1. #650 (base) ## Summary Adds automatic context compaction that triggers at 70% usage, with progressive countdown warnings starting at 60%. <img width="905" height="155" alt="image" src="https://github.com/user-attachments/assets/b0db20c5-c377-44bb-891c-f8ddadd561c8" /> <img width="891" height="194" alt="image" src="https://github.com/user-attachments/assets/6385cfd2-5e3c-45ec-afce-935dae56ad1a" /> Relates to #651. ## Key Changes **Auto-Compaction:** - Triggers automatically when current context usage reaches 70% of model's context window - Queues user's message to send after compaction completes - Includes image parts in continue messages **Progressive Warnings:** - Shows countdown at 60-69% usage: "Context left until Auto-Compact: X% remaining" - Shows urgent message at 70%+: "⚠️ Approaching context limit. Next message will trigger auto-compaction." **Implementation:** - New `shouldAutoCompact()` utility centralizes threshold logic with configurable constants - Returns `{ shouldShowWarning, usagePercentage, thresholdPercentage }` - Uses **last usage entry** (current context size) to match UI token meter display - Excludes historical usage from threshold check to prevent infinite compaction loops - `ContinueMessage` type now includes optional `imageParts` ## Technical Details **Usage Calculation:** The auto-compaction check uses the most recent usage entry from `usageHistory` to calculate the current context size. This matches the percentage displayed in the UI token meter and correctly handles post-compaction scenarios: - **Before compaction**: Last entry represents full context → triggers at 70% correctly - **After compaction**: Last entry excludes historical usage → resets to actual context size - **Historical usage preserved**: Remains in usage history for cost tracking, but not used for threshold calculations This prevents the infinite loop where post-compaction workspaces would continuously re-compact because historical usage tokens were being included in the threshold check. ## Future Work Future PRs will add user settings to configure auto-compaction (enable/disable, custom threshold). _Generated with `mux`_

## Stack 1. #685 ⬅ This PR 1. #683 1. #670 1. #650 (base) Relates to #651. Adds per-workspace settings for auto-compaction (any percentage between 50 and 90): <img width="305" height="130" alt="image" src="https://github.com/user-attachments/assets/039e19d9-d95c-4249-8274-6a34116ee062" /> <img width="295" height="163" alt="image" src="https://github.com/user-attachments/assets/6095b100-732e-4c2c-bc39-3e66298245e4" /> **New Features:** - Toggle to enable/disable auto-compaction - Configurable threshold percentage (50-90%, default 70%) - Settings persist to localStorage and sync across tabs - UI integrated into right sidebar below existing settings **Implementation:** - Extracted threshold constants to `ui.ts` for DRY - Created reusable `useClampedNumberInput` hook for numeric input validation - Updated `shouldAutoCompact` to accept settings parameters - Follows existing patterns (uses `HelpIndicator` for tooltips) Settings are forked with workspace and cleaned up on workspace deletion. _Generated with `mux`_

ethanndickson force-pushed the fix-compaction-message-race branch from b186d47 to 7d2df23 Compare November 18, 2025 07:02

chatgpt-codex-connector bot reviewed Nov 18, 2025

View reviewed changes

src/node/services/agentSession.ts Outdated Show resolved Hide resolved

ethanndickson changed the base branch from main to compact-messages-queue-system November 18, 2025 07:08

ethanndickson force-pushed the fix-compaction-message-race branch from 7d2df23 to 2b2b2fc Compare November 18, 2025 07:08

ethanndickson mentioned this pull request Nov 18, 2025

🤖 refactor: use message queue for compact continue messages #650

Merged

chatgpt-codex-connector bot reviewed Nov 18, 2025

View reviewed changes

src/node/services/agentSession.ts Outdated Show resolved Hide resolved

This comment was marked as resolved.

Sign in to view

ethanndickson force-pushed the fix-compaction-message-race branch 2 times, most recently from 1eda7a1 to 4560627 Compare November 18, 2025 10:51

ethanndickson requested a review from ammario November 18, 2025 15:57

ammario requested changes Nov 18, 2025

View reviewed changes

src/common/utils/tokens/displayUsage.ts Outdated Show resolved Hide resolved

src/browser/utils/compaction/handler.ts Show resolved Hide resolved

src/node/services/agentSession.ts Outdated Show resolved Hide resolved

src/node/services/agentSession.ts Outdated Show resolved Hide resolved

ethanndickson requested a review from ammario November 19, 2025 02:38

ethanndickson commented Nov 19, 2025

View reviewed changes

This was referenced Nov 19, 2025

🤖 feat: add auto-compaction when approaching context limits #679

Closed

🤖 feat: add auto-compaction with progressive warnings #683

Merged

🤖 feat: add auto-compaction configuration UI #685

Merged

ibetitsmike reviewed Nov 20, 2025

View reviewed changes

src/node/services/compactionHandler.ts Show resolved Hide resolved

ibetitsmike reviewed Nov 20, 2025

View reviewed changes

src/common/utils/tokens/displayUsage.ts Outdated Show resolved Hide resolved

ibetitsmike requested changes Nov 20, 2025

View reviewed changes

Base automatically changed from compact-messages-queue-system to main November 21, 2025 00:43

ethanndickson added 7 commits November 21, 2025 11:46

fixup

e0be9f3

bump test timeout

f30a4f5

rename

8ae0980

dont fetch messages twice during compaction

72f1512

fixup

7f3a1df

add tests

f93f212

ethanndickson force-pushed the fix-compaction-message-race branch from e72e057 to f93f212 Compare November 21, 2025 00:46

ethanndickson enabled auto-merge November 21, 2025 00:47

ethanndickson added this pull request to the merge queue Nov 21, 2025

Merged via the queue into main with commit 9e1f0aa Nov 21, 2025
18 of 19 checks passed

ethanndickson deleted the fix-compaction-message-race branch November 21, 2025 01:15

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

🤖 refactor: move compaction logic to backend #670

🤖 refactor: move compaction logic to backend #670

Uh oh!

ethanndickson commented Nov 18, 2025 •

edited

Loading

Uh oh!

chatgpt-codex-connector bot left a comment

Uh oh!

Uh oh!

ethanndickson commented Nov 18, 2025

Uh oh!

chatgpt-codex-connector bot left a comment

Uh oh!

Uh oh!

ethanndickson commented Nov 18, 2025

Uh oh!

This comment was marked as resolved.

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

ethanndickson Nov 19, 2025

Uh oh!

Uh oh!

Uh oh!

ibetitsmike left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

🤖 refactor: move compaction logic to backend #670

🤖 refactor: move compaction logic to backend #670

Uh oh!

Conversation

ethanndickson commented Nov 18, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Stack

Summary

Changes

Backend (agentSession.ts)

Frontend (WorkspaceStore.ts)

Shared

Testing

Uh oh!

chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

ethanndickson commented Nov 18, 2025

Uh oh!

chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

ethanndickson commented Nov 18, 2025

Uh oh!

This comment was marked as resolved.

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

ethanndickson Nov 19, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

ibetitsmike left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

ethanndickson commented Nov 18, 2025 •

edited

Loading