圧縮リファレンス

contextTokens > contextWindow - reserveTokens

Before compaction:

  entry:  0     1     2     3      4     5     6      7      8     9
        ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬─────┐
        │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool│
        └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴─────┘
                └────────┬───────┘ └──────────────┬──────────────┘
               messagesToSummarize            kept messages
                                   ↑
                          firstKeptEntryId (entry 4)

After compaction (new entry appended):

  entry:  0     1     2     3      4     5     6      7      8     9     10
        ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬─────┬─────┐
        │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool│ cmp │
        └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴─────┴─────┘
               └──────────┬──────┘ └──────────────────────┬───────────────────┘
                 not sent to LLM                    sent to LLM
                                                         ↑
                                              starts from firstKeptEntryId

What the LLM sees:

  ┌────────┬─────────┬─────┬─────┬──────┬──────┬─────┬──────┐
  │ system │ summary │ usr │ ass │ tool │ tool │ ass │ tool │
  └────────┴─────────┴─────┴─────┴──────┴──────┴─────┴──────┘
       ↑         ↑      └─────────────────┬────────────────┘
    prompt   from cmp          messages from firstKeptEntryId

persist final assistant response
→ extension/public turn_end
→ extension/public agent_end
→ append context_edit omissions for the selected attempt
→ for overflow/length: run session_before_compact and append compaction on success
→ start the retry as a fresh run

Split user-message span (one span exceeds budget):

  entry:  0     1     2      3     4      5      6     7      8
        ┌─────┬─────┬─────┬──────┬─────┬──────┬──────┬─────┬──────┐
        │ hdr │ usr │ ass │ tool │ ass │ tool │ tool │ ass │ tool │
        └─────┴─────┴─────┴──────┴─────┴──────┴──────┴─────┴──────┘
                ↑                                     ↑
         turnStartIndex = 1                  firstKeptEntryId = 7
                │                                     │
                └──── turnPrefixMessages (1-6) ───────┘
                                                      └── kept (7-8)

  isSplitTurn = true
  messagesToSummarize = []  (no earlier user-message spans)
  turnPrefixMessages = [usr, ass, tool, ass, tool, tool]

interface CompactionEntry<T = unknown> {
  type: "compaction";
  id: string;
  parentId: string | null;
  timestamp: string;
  summary: string;
  firstKeptEntryId: string;
  tokensBefore: number;
  usage?: Usage;       // LLM usage that generated the summary
  fromHook?: boolean;  // true if provided by extension (legacy field name)
  details?: T;         // implementation-specific data
}

// Default compaction uses this for details (from compaction.ts):
interface CompactionDetails {
  readFiles: string[];
  modifiedFiles: string[];
}

Tree before navigation:

         ┌─ B ─ C ─ D (old leaf, being abandoned)
    A ───┤
         └─ E ─ F (target)

Common ancestor: A
Entries to summarize: B, C, D

After navigation with summary:

         ┌─ B ─ C ─ D
    A ───┤
         └─ E ─ F ─ [summary of B,C,D] (new leaf)

interface BranchSummaryEntry<T = unknown> {
  type: "branch_summary";
  id: string;
  parentId: string | null;
  timestamp: string;
  summary: string;
  fromId: string;      // Entry we navigated from
  usage?: Usage;       // LLM usage that generated the summary
  fromHook?: boolean;  // true if provided by extension (legacy field name)
  details?: T;         // implementation-specific data
}

// Default branch summarization uses this for details (from branch-summarization.ts):
interface BranchSummaryDetails {
  readFiles: string[];
  modifiedFiles: string[];
}

## Goal
[What the user is trying to accomplish]

## Constraints & Preferences
- [Requirements mentioned by user]

## Progress
### Done
- [x] [Completed tasks]

### In Progress
- [ ] [Current work]

### Blocked
- [Issues, if any]

## Key Decisions
- **[Decision]**: [Rationale]

## Next Steps
1. [What should happen next]

## Critical Context
- [Data needed to continue]

<read-files>
path/to/file1.ts
path/to/file2.ts
</read-files>

<modified-files>
path/to/changed.ts
</modified-files>

[User]: What they said
[Assistant thinking]: Internal reasoning
[Assistant]: Response text
[Assistant tool calls]: read(path="foo.ts"); edit(path="bar.ts", ...)
[Tool result]: Output from tool

pi.on("session_before_compact", async (event, ctx) => {
  const { preparation, branchEntries, customInstructions, reason, willRetry, signal } = event;

  // preparation.messagesToSummarize - messages to summarize
  // preparation.turnPrefixMessages - user-message-span prefix (if isSplitTurn)
  // preparation.previousSummary - previous compaction summary
  // preparation.fileOps - extracted file operations
  // preparation.tokensBefore - context tokens before compaction
  // preparation.firstKeptEntryId - where kept messages start
  // preparation.settings - effective settings after applying model overrides

  // branchEntries - all entries on current branch (for custom state)
  // reason - "manual" (/compact), "threshold", or "overflow"
  // willRetry - whether the aborted turn is retried after compaction (overflow recovery)
  // signal - AbortSignal (pass to LLM calls)

  // Cancel:
  return { cancel: true };

  // Custom summary:
  return {
    compaction: {
      summary: "Your summary...",
      firstKeptEntryId: preparation.firstKeptEntryId,
      tokensBefore: preparation.tokensBefore,
      // usage: summaryResponse.usage, // Optional; included in session totals
      details: { /* custom data */ },
    }
  };
});

import { convertToLlm, serializeConversation } from "@earendil-works/pi-coding-agent";

pi.on("session_before_compact", async (event, ctx) => {
  const { preparation } = event;
  
  // Convert AgentMessage[] to Message[], then serialize to text
  const conversationText = serializeConversation(
    convertToLlm(preparation.messagesToSummarize)
  );
  // Returns:
  // [User]: message text
  // [Assistant thinking]: thinking content
  // [Assistant]: response text
  // [Assistant tool calls]: read(path="..."); bash(command="...")
  // [Tool result]: output text

  // Now send to your model for summarization
  const { summary, usage } = await myModel.summarize(conversationText);
  
  return {
    compaction: {
      summary,
      firstKeptEntryId: preparation.firstKeptEntryId,
      tokensBefore: preparation.tokensBefore,
      usage,
    }
  };
});

pi.on("session_compact_failed", async (event, ctx) => {
  const { reason, errorMessage, aborted, willRetry, fromExtension } = event;
  // reason - "manual" (/compact), "threshold", or "overflow"
  // errorMessage - present for non-abort failures
  // aborted - true for canceled/aborted compactions
  // willRetry - whether the aborted turn would have retried after compaction
  // fromExtension - whether extension-provided compaction content was being used
});

pi.on("session_before_tree", async (event, ctx) => {
  const { preparation, signal } = event;

  // preparation.targetId - where we're navigating to
  // preparation.oldLeafId - current position (being abandoned)
  // preparation.commonAncestorId - shared ancestor
  // preparation.entriesToSummarize - entries that would be summarized
  // preparation.userWantsSummary - whether user chose to summarize

  // Cancel navigation entirely:
  return { cancel: true };

  // Provide custom summary (only used if userWantsSummary is true):
  if (preparation.userWantsSummary) {
    return {
      summary: {
        summary: "Your summary...",
        // usage: summaryResponse.usage, // Optional; included in session totals
        details: { /* custom data */ },
      }
    };
  }
});

{
  "compaction": {
    "enabled": true,
    "reserveTokens": 16384,
    "keepRecentTokens": 20000
  }
}

{
  "compaction": {
    "reserveTokens": 16384,
    "keepRecentTokens": 20000,
    "modelOverrides": {
      "some-provider/big-model": {
        "reserveTokens": 400000
      }
    }
  }
}