Context Recall

---
name: context-recall
description: >
  Retrieve full pre-compaction conversation history from saved transcript
  files when the compact summary is insufficient or earlier session details
  are missing. Use when asked about past decisions, tool results, or content
  that predates the latest compaction; when mapping Done to Working Intent /
  Recent User Requests after compaction; before ui__reportResult(success) if
  intent or Completion Criteria are incomplete or unverified; when the agent
  would say it does not remember; or when the compact summary's Context
  recovery / fallback note names a transcript path. Triggers: "what did we
  discuss earlier", "before the context was reset", "older messages",
  "pre-compaction", "context recall", "recover history", "before declaring
  done", "컴팩션 이전 대화", "과거 히스토리", "예전에 뭐라고 했지", "아까 정한",
  "아까 뭐였지".
---

# Context Recall

Compaction already saves transcripts on disk. Prefer those files over guessing
or redoing work. This skill complements the compact summary's
`### Context recovery` suffix — it does not replace it.

After compaction, empty Active Request is not a Done signal. Before
`ui__reportResult(success)`, restate Working Intent / Recent User Requests
against Completion Criteria; if uncertain, read the latest epoch file first.

## Workflow

If the answer is still visible in the current context, just answer from it. Only when it is not
(a compact summary is present, or earlier content is missing) and no explicit path was given, run
the `workspace__globFiles` call in step 2 first, before grepping the workspace. This is the case for
questions like "아까 정한 거 뭐였지".

### 1. Prefer an explicit path from the compact summary

- If `### Context recovery` names `.libragent/pre_compaction_epoch_{N}.md`,
  read that path with `workspace__readFile`.
- If a fallback note names
  `.libragent/tool-results/compaction/fallback-….md`, read that **exact**
  path. Those files live under internal `tool-results` and are **not**
  discoverable via `globFiles` — do not try to browse for
  them.

### 2. Otherwise discover epoch transcripts

```
workspace__globFiles(path=".libragent", filePattern="pre_compaction_epoch_*.md")
```

Epoch numbers are **monotonic** (`1`, `2`, `3`, …). Retention keeps only the
newest ~3 files, so `pre_compaction_epoch_1.md` may already be gone. Always
read the **highest N** first (most recent compaction).

### 3. Read concrete paths only

```
workspace__readFile(path=".libragent/pre_compaction_epoch_{N}.md")
```

Epoch files are chronological: the latest requests and work are at the **end**.
Read the tail first with a negative `size`:

```
workspace__readFile(path=".libragent/pre_compaction_epoch_{N}.md", size=-200)
```

Then read earlier parts (default top-down read) only if needed.

Never pass globs to `workspace__readFile`. Read older epochs only if the
newest file is insufficient.

## What's Inside

Each epoch file is Markdown with:

- `# Pre-compaction Transcript` header and session id
- `---\n[timestamp] ROLE` separators
- User/assistant text (truncated ~1500 bytes per block)
- Thinking blocks (truncated ~1500 bytes)
- `[TOOL CALL] name(args)` lines — **not** tool result bodies

For tool outputs, inspect workspace files those tools wrote (or other session
artifacts). Do not expect result payloads inside the epoch file.

If the tail is only assistant text and tool calls, find the latest user request by
searching for the last `] USER` separator line (`workspace__grepFiles`, or
`grep -n '\] USER' <path> | tail -1`). User text can also contain `] USER`, so
check that the match is followed by a `---` separator above it.

## Do Not

- Hard-code `epoch_1` / `epoch_2` — discover first, then pick highest N
- Pass wildcards to `workspace__readFile`
- Assume fallback paths under `.libragent/tool-results/` are listable
- Re-research from scratch when an epoch file exists
- Answer "I don't remember" when an epoch or fallback path is available