oh-my-pi/docs/compaction.md

# Compaction and Branch Summaries

Compaction and branch summaries are the two mechanisms that keep long sessions usable without losing prior work context.

- **Compaction** rewrites old history into a summary on the current branch.
- **Branch summary** captures abandoned branch context during `/tree` navigation.

Both are persisted as session entries and converted back into user-context messages when rebuilding LLM input.

## Key implementation files

- `packages/agent/src/compaction/compaction.ts` (context-full summarization and handoff generation)
- `packages/snapcompact/src/snapcompact.ts` (snapcompact strategy: history archived as dense bitmap images)
- `packages/agent/src/compaction/branch-summarization.ts`
- `packages/agent/src/compaction/pruning.ts`
- `packages/agent/src/compaction/utils.ts`
- `packages/agent/src/compaction/openai.ts`
- `packages/coding-agent/src/session/session-manager.ts`
- `packages/coding-agent/src/session/agent-session.ts`
- `packages/coding-agent/src/session/messages.ts`
- `packages/coding-agent/src/extensibility/hooks/types.ts`
- `packages/coding-agent/src/config/settings-schema.ts`

## Session entry model

Compaction and branch summaries are first-class session entries, not plain assistant/user messages.

- `CompactionEntry`
  - `type: "compaction"`
  - `summary`, optional `shortSummary`
  - `firstKeptEntryId` (compaction boundary)
  - `tokensBefore`
  - optional `details`, `preserveData`, `fromExtension`
- `BranchSummaryEntry`
  - `type: "branch_summary"`
  - `fromId`, `summary`
  - optional `details`, `fromExtension`

When context is rebuilt (`buildSessionContext`):

1. Latest compaction on the active path is converted to one `compactionSummary` message.
2. Kept entries from `firstKeptEntryId` to the compaction point are re-included.
3. Later entries on the path are appended.
4. `branch_summary` entries are converted to `branchSummary` messages.
5. `custom_message` entries are converted to `custom` messages.

Those custom roles are then transformed into LLM-facing messages in `convertToLlm()`: `compactionSummary` and `branchSummary` become user messages rendered through the static templates

- `packages/agent/src/compaction/prompts/compaction-summary-context.md`
- `packages/agent/src/compaction/prompts/branch-summary-context.md`

while `custom` messages pass through as developer messages with their raw content (no template).

## Compaction pipeline

### Triggers

Compaction/context maintenance can run in five ways:

1. **Manual context compaction**: `/compact [instructions]` calls `AgentSession.compact(...)`.
2. **Automatic overflow recovery**: after a same-model assistant error that matches context overflow.
3. **Automatic incomplete-output recovery**: after a same-model assistant message ends with `stopReason === "length"` (OpenAI/Codex `response.incomplete`).
4. **Automatic threshold maintenance**: after a successful turn when context exceeds the resolved threshold.
5. **Idle maintenance**: `runIdleCompaction()` can invoke the same auto-maintenance path with reason `"idle"`.

### Compaction shape (visual)

```text
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
```

### Overflow/incomplete recovery vs threshold/idle maintenance

The automatic paths are intentionally different:

- **Overflow recovery**
  - Trigger: current-model assistant error is detected as context overflow and the error is not older than the latest compaction.
  - The failing assistant error message is removed from active agent state before retry.
  - Context promotion is tried first; if a configured larger model is available, the agent switches model and retries without compacting.
  - If promotion is unavailable and compaction is enabled, context-full compaction runs with `reason: "overflow"` and `willRetry: true`; handoff strategy is not used for overflow because the handoff request would reuse the overflowing input.
  - On success, `agent.continue()` is scheduled to retry the turn.

- **Incomplete-output recovery**
  - Trigger: same-model assistant message ends with `stopReason === "length"` and the message is not older than the latest compaction.
  - The incomplete assistant message is removed from active agent state before recovery.
  - Context promotion is tried first.
  - If promotion is unavailable and compaction is enabled, auto maintenance runs with `reason: "incomplete"` and `willRetry: true`.
  - Unlike overflow, `compaction.strategy: "handoff"` is allowed for incomplete-output recovery because the input context is still usable.
  - On context-full success, `agent.continue()` is scheduled to retry the turn.

- **Threshold maintenance**
  - Trigger: successful, non-error assistant message whose adjusted context tokens exceed `resolveThresholdTokens(...)`.
  - Tool-output pruning can reduce the measured token count before threshold comparison.
  - Context promotion is tried before compaction.
  - If promotion is unavailable, auto maintenance runs with `reason: "threshold"` and `willRetry: false`.
  - With `compaction.strategy: "handoff"`, threshold maintenance normally schedules a post-prompt auto-handoff task instead of writing a compaction entry; pre-prompt checks run it inline to avoid racing the next turn. If handoff returns no document without aborting, it falls back to context-full compaction.
  - On success, if `compaction.autoContinue !== false`, schedules an agent-authored developer auto-continue prompt from `prompts/system/auto-continue.md`.

- **Idle maintenance**
  - Trigger: `runIdleCompaction()` when not streaming or already compacting.
  - Uses `reason: "idle"` and does not auto-continue afterward.

### Snapcompact strategy

`compaction.strategy: "snapcompact"` replaces the LLM summarization call with a local, deterministic archival pass (`compact` from `@oh-my-pi/snapcompact`):

- The discarded history is serialized, whitespace-collapsed, and printed onto model-aware PNG frames (frame width fixed per shape; frame height hugs the rows actually printed) using bundled public-domain pixel fonts. The shape — and frame size — resolve from the **model id** when the model line was measured: Claude reads X.org `8x13` glyphs on an 11px advance (extra letter-spacing, black ink — `11on16-bw`; high-res lines — Opus 4.7+, Fable, Mythos — get 1932px frames under Anthropic's 4,784 visual-token cap, older lines stay at 1568px), Gemini reads `8x13` glyphs on a 22px pitch (extra leading, black ink — `8on22-bw` at 2048px, since Gemini 3.x bills a fixed 1,120-token budget per image at any pixel size), GPT/Codex read the same `8on22-bw` shape at 1568px (patch billing is area-proportional, so larger frames cannot improve chars per token), and Kimi/GLM read `8x13` glyphs on a 16px pitch (`8on16-bw` at 1568px — kimi's processor downscales past 1792px). A Claude routed through Vertex or OpenRouter keeps its Claude shape. Unmeasured models fall back to their wire API family (Anthropic-family/unknown → `11on16-bw`, Google → `8on22-bw`, OpenAI-compatible → `8on22-bw`); billing (per-family patch/budget formulas, OpenAI's `detail: "original"` hint) always follows the API carrying the request, computed for the resolved frame size. The `snapcompact.shape` setting (default `auto`) forces one of the research-eval variants instead: square grids (`8x8r`/`8x8u`/`6x6u`/`5x8` × sentence-hue/black ink) or the per-model eval winners (`6x12-dim`, `8x13-bw`, `8on16-bw`, `8on22-bw`, `11on16-bw`, and the two-column word-wrapped `doc-8on16-bw`/`-sent`/`-sent-dim`, where `dim` prints stopwords in gray). A forced variant keeps its geometry but is re-priced for the target provider's image billing. The same setting governs inline system-prompt/tool-result imaging (`snapcompact.systemPrompt`, `snapcompact.toolResults`).
- Serialization keeps the archive conversation-dense: tool results are truncated head+tail (default 2,000 chars at a 0.6 head ratio), tool-call argument values are capped per value (500) and per call (2,000), and tool output is printed in dim gray ink so conversation reads louder than tool noise. All budgets and the dimming are configurable via `SerializeOptions` (`toolResultMaxChars`, `toolArgMaxChars`, `toolCallMaxChars`, `truncateHeadRatio`, `dimToolResults`).
- Frames persist under `CompactionEntry.preserveData.snapcompact` and are re-attached to the `compactionSummary` message as image blocks on every context rebuild; the entry's `summary` is a deterministic reading guide (grid geometry, role tags, truncation notes) plus the usual file-operation lists.
- Later compactions carry earlier frames forward. The frame budget is provider-aware (`providerFrameBudget`): the per-provider image cap clamped to 8 (`MAX_FRAMES`) — OpenRouter hard-caps requests at 8 images and silently drops the excess, unknown providers get a safe floor of 5. Beyond the budget the archive fades from the middle out: the earliest frame (session head — the original request, or the filmed summary of older history) is pinned, and the oldest *unpinned* frames are evicted. Pages of the *current* compaction that no longer fit are never rendered or dropped — the newest unframed slice survives verbatim as a text tail on the summary (`Archive.textTail`, capped at two frame capacities with middle elision) and is folded back into frames by the next compaction. If the previous compaction was text-based, its summary is printed at the head of the frame archive as `[Summary of earlier history]`.
- No model, API key, or network is involved, so snapcompact is also safe for overflow recovery. It requires a vision-capable current model (`model.input` includes `"image"`); otherwise the run falls back to context-full and emits a warning notice (auto and manual paths). Manual `/compact` honors the strategy unless custom instructions are given (those imply a directed LLM summary).
- Rationale: the shape table comes from the snapcompact 200k-token evals in `packages/snapcompact`, where bitmap frames preserved QA recall at lower billed-token cost than raw text for vision-capable models.

### Display transcript

Compaction no longer visually restarts the conversation. The TUI renders the **display transcript** (`buildSessionContext({ transcript: true })` / `AgentSession.buildTranscriptSessionContext()`): every path entry in chronological order, with each compaction shown inline as a slim divider — `── 📷 compacted · ctrl+o ──` — at the point it fired. Expanding (ctrl+o) reveals the summary. Only the LLM context resets at the compaction boundary; the scrollback above the divider stays intact, including across session resume.

### Pre-compaction pruning

Before compaction checks, tool-result pruning may run (`pruneToolOutputs`).

Default prune policy:

- Protect newest `40_000` tool-output tokens.
- Require at least `20_000` total estimated savings.
- Never blank a result below `50` tokens (`MIN_PRUNE_TOKENS`): the `[Output truncated - N tokens]` placeholder costs ~8 tokens, so pruning a sub-floor result would grow the context and churn the prompt cache for nothing. (Superseded and useless results keep their own rules — the useless collector already drops no-savings candidates; superseded reads prune for correctness regardless of size.)
- Never prune `skill` tool results, `read` results of `skill://` paths, or reads of the active plan reference file (added via `AgentSession`'s plan protection).

Pruned tool results are replaced with:

- `[Output truncated - N tokens]`

If pruning changes entries, session storage is rewritten and agent message state is refreshed before compaction decisions.

### Useless-result elision

Tools can flag a finished result as contextually useless — a search with zero matches, a `job` poll that timed out with everything still running, an empty `irc` inbox drain. The flag originates on the tool result (`AgentToolResult.useless`, set via `ToolResultBuilder.useless()` or directly on the returned object), is copied by the agent loop onto the persisted `ToolResultMessage` (never together with `isError` — errors always win), and is consumed in three places:

- **Per-turn stale-result pass** (`pruneSupersededToolResults`, gated by `compaction.dropUseless`, default on): flagged results are blanked to the exact placeholder `[Uneventful result elided]` (`USELESS_NOTICE`) with the same cache-aware timing as superseded reads — only when the suffix after the candidate is small (≤ ~8k tokens) or the session has idled past the provider prompt-cache lifetime. Results smaller than the notice itself are never blanked (no savings), and protected tools are exempt.
- **Threshold prune** (`pruneToolOutputs`): flagged results bypass the protect-recent window, same as superseded reads, and receive `USELESS_NOTICE` instead of the token-count placeholder.
- **Summary serialization**: `serializeConversation` (agent and snapcompact) drops the whole tool call/result pair from summarizer/archive input — the source region is discarded after summarization anyway, so the exclusion costs no cache.

The flag never reaches provider wire formats, and flagged pairs are never removed from history (only blanked in place), so tool-call/result pairing and provider-native history replay stay intact.

### Boundary and cut-point logic

`prepareCompaction()` only considers entries since the last compaction entry (if any).

1. Find previous compaction index.
2. Compute `boundaryStart = prevCompactionIndex + 1`.
3. Adapt `keepRecentTokens` using measured usage ratio when available.
4. Run `findCutPoint()` over the boundary window.

Valid cut points include:

- message entries with roles: `user`, `assistant`, `bashExecution`, `hookMessage`, `branchSummary`, `compactionSummary`
- `custom_message` entries
- `branch_summary` entries

Hard rule: never cut at `toolResult`.

If there are non-message metadata entries immediately before the cut point (`model_change`, `thinking_level_change`, labels, etc.), they are pulled into the kept region by moving cut index backward until a message or compaction boundary is hit.

### Split-turn handling

If cut point is not at a user-turn start, compaction treats it as a split turn.

Turn start detection treats these as user-turn boundaries:

- `message.role === "user"`
- `message.role === "bashExecution"`
- `custom_message` entry
- `branch_summary` entry

Split-turn compaction generates two summaries:

1. History summary (`messagesToSummarize`)
2. Turn-prefix summary (`turnPrefixMessages`)

Final stored summary is merged as:

```markdown
<history summary>

---

**Turn Context (split turn):**

<turn prefix summary>
```

### Summary generation

`compact(...)` builds summaries from serialized conversation text:

1. Convert messages via `convertToLlm()`.
2. Serialize with `serializeConversation()`.
3. Wrap in `<conversation>...</conversation>`.
4. Optionally include `<previous-summary>...</previous-summary>`.
5. Optionally inject extension hook context and active memory-backend compaction context as `<additional-context>` entries.
6. Execute summarization prompt with `SUMMARIZATION_SYSTEM_PROMPT`.

Prompt selection:

- first compaction: `compaction-summary.md`
- iterative compaction with prior summary: `compaction-update-summary.md`
- split-turn second pass: `compaction-turn-prefix.md`
- short UI summary: `compaction-short-summary.md`
- handoff document: `handoff-document.md` (used by `generateHandoff(...)`, not serialized compaction)

Remote summarization modes:

- If `compaction.remoteEndpoint` is set and remote compaction is enabled, local summary generation POSTs:
  - `{ systemPrompt, prompt }`
- Expects JSON containing at least `{ summary }`.
- For OpenAI/OpenAI Codex models, compaction first tries the provider-native `/responses/compact` endpoint when remote compaction is enabled. It preserves provider replacement history in `preserveData.openaiRemoteCompaction` and falls back to local summarization if that native request fails.

### Handoff generation

`packages/agent/src/compaction/compaction.ts` also exports `generateHandoff(...)`. Handoff generation uses the same `completeSimple(...)` oneshot style as summarization, but it preserves the live agent cache prefix by sending the active system prompt, tool array, and real LLM message history, then appending one agent-attributed `user` message containing the handoff prompt. It forces `toolChoice: "none"` and returns joined text blocks directly.

Handoff does not write a `CompactionEntry`. `AgentSession.handoff()` owns the session transition: it starts a new session, injects the generated document as a visible `custom_message` with `customType: "handoff"`, and rebuilds agent messages from that new session.

### File-operation context in summaries

Compaction tracks cumulative file activity using assistant tool calls:

- `read(path)` → read set
- `write(path)` → modified set
- `edit(path)` → modified set

Cumulative behavior:

- Includes prior compaction details only when prior entry is pi-generated (`fromExtension !== true`).
- In split turns, includes turn-prefix file ops too.
- `details.readFiles` excludes files also modified; `details.modifiedFiles` carries the rest (persisted shape is unchanged).

Summary text gets one `<files>` tag appended via prompt template: a grouped, prefix-folded directory tree (find-tool shape) with a per-file access marker — `(Read)` for read-only files, `(Write)` for modified files never read, `(RW)` for modified files also present in the cumulative read set. Capped at 20 files with an `… (N more files omitted)` line.

```xml
<files>
# packages/agent/src/compaction/
compaction.ts (Read)
utils.ts (RW)
## prompts/
file-operations.md (Write)
</files>
```

Legacy `<read-files>`/`<modified-files>` tags from summaries written by earlier versions are stripped (alongside `<files>`) before re-appending, so old summaries self-heal on the next compaction.

### Persist and reload

After summary generation (or hook-provided summary), agent session:

1. Appends `CompactionEntry` with `appendCompaction(...)` for context-full maintenance; handoff strategy creates a new session and injects a handoff `custom_message` instead.
2. Rebuilds display context from the active leaf via `buildDisplaySessionContext()`.
3. Replaces live agent messages with rebuilt context.
4. Synchronizes active todo phases from the rebuilt branch and closes provider sessions whose history was rewritten.
5. Emits `session_compact` hook event.

## Branch summarization pipeline

Branch summarization is tied to tree navigation, not token overflow.

### Trigger

During `navigateTree(...)`:

1. Compute abandoned entries from old leaf to common ancestor using `collectEntriesForBranchSummary(...)`.
2. If caller requested summary (`options.summarize`), generate summary before switching leaf.
3. If summary exists, attach it at the navigation target using `branchWithSummary(...)`.

Operationally this is commonly driven by `/tree` flow when `branchSummary.enabled` is enabled.

### Branch switch shape (visual)

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

### Preparation and token budget

`generateBranchSummary(...)` computes budget as:

- `tokenBudget = model.contextWindow - branchSummary.reserveTokens`

`prepareBranchEntries(...)` then:

1. First pass: collect cumulative file ops from all summarized entries, including prior pi-generated `branch_summary` details.
2. Second pass: walk newest → oldest, adding messages until token budget is reached.
3. Prefer preserving recent context.
4. May still include large summary entries near budget edge for continuity.

Compaction entries are included as messages (`compactionSummary`) during branch summarization input.

### Summary generation and persistence

Branch summarization:

1. Converts and serializes selected messages.
2. Wraps in `<conversation>`.
3. Uses custom instructions if supplied, otherwise `branch-summary.md`.
4. Calls summarization model with `SUMMARIZATION_SYSTEM_PROMPT`.
5. Prepends `branch-summary-preamble.md`.
6. Appends file-operation tags.

Result is stored as `BranchSummaryEntry` with optional details (`readFiles`, `modifiedFiles`).

## Extension and hook touchpoints

### `session_before_compact`

Pre-compaction hook.

Can:

- cancel compaction (`{ cancel: true }`)
- provide full custom compaction payload (`{ compaction: CompactionResult }`)

### `session.compacting`

Prompt/context customization hook for default compaction.

Can return:

- `prompt` (override base summary prompt)
- `context` (extra context lines injected into `<additional-context>`)
- `preserveData` (stored on compaction entry)

### `session_compact`

Post-compaction notification with saved `compactionEntry` and `fromExtension` flag.

### `session_before_tree`

Runs on tree navigation before default branch summary generation.

Can:

- cancel navigation
- provide custom `{ summary: { summary, details } }` used when user requested summarization

### `session_tree`

Post-navigation event exposing new/old leaf and optional summary entry.

## Runtime behavior and failure semantics

- Manual compaction aborts current agent operation first.
- `abortCompaction()` cancels manual compaction, auto-compaction, and handoff generation controllers.
- Auto compaction emits start/end session events for UI/state updates.
- Auto compaction can try multiple model candidates and retry transient failures; long retry delays prefer the next candidate when one is available.
- Overflow errors are excluded from generic retry path because they are handled by context promotion/compaction.
- If auto-compaction fails:
  - overflow path emits `Context overflow recovery failed: ...`
  - incomplete-output path emits `Incomplete response recovery failed: ...`
  - threshold/idle paths emit `Auto-compaction failed: ...`
- Branch summarization can be cancelled via abort signal (e.g., Escape), returning canceled/aborted navigation result.

## Settings and defaults

From `settings-schema.ts`:

- `compaction.enabled` = `true`
- `compaction.strategy` = `"context-full"` (`"handoff"`, `"shake"`, `"snapcompact"`, and `"off"` are also supported)
- `compaction.reserveTokens` = `16384`
- `compaction.keepRecentTokens` = `20000`
- `compaction.autoContinue` = `true`
- `compaction.remoteEnabled` = `true`
- `compaction.remoteEndpoint` = `undefined`
- `compaction.thresholdPercent` = `-1` and `compaction.thresholdTokens` = `-1`; when no positive override is set, the threshold is `contextWindow - max(15% of contextWindow, reserveTokens)`
- `compaction.idleEnabled` = `false`
- `compaction.idleThresholdTokens` = `200000`
- `compaction.idleTimeoutSeconds` = `300`
- `branchSummary.enabled` = `false`
- `branchSummary.reserveTokens` = `16384`

These values are consumed at runtime by `AgentSession` and compaction/branch summarization modules.