Forge
markdowna5f71db5
1# 3. Summarization protocol
2
3Summarization is inevitable in long conversations.
4The problem isn't summarization itself, but that after it the agent often "loses itself."
5
6## Goal of the protocol
7
8Ensure that after context is cut the agent doesn't become a new instance with zero memory.
9
10## Protocol (short version)
11
121. Capture in notes:
13 - what we did,
14 - what decisions we made,
15 - what's unfinished,
16 - which working rules were confirmed.
172. First step in the new chat: read notes.
183. Confirm that context is restored.
194. Continue from the current point, not from the beginning.
20
21## What must be in the summary
22
23- target task and current status;
24- changed files / artifacts;
25- open risks and blockers;
26- working hypotheses already tested;
27- the next step explicitly stated.
28
29## Recovery protocol (human ↔ agent interaction)
30
311. The human triggers summarization manually (or it happens automatically).
322. The human reminds: "summarization happened, read your notes."
333. The agent calls `read_agent_notes` and restores context.
34
35Key point: initiative is on the human side, but recovery is on the agent side. Without an explicit reminder the agent after summarization may not realize it lost context.
36
37## Common mistakes
38
39- A "pretty retelling" without operational details;
40- no explicitly stated next step;
41- recording only facts without decision logic.
42
43## Success criterion
44
45After summarization the agent returns to working context in 1-2 messages without quality loss and without unnecessary clarifications.
46
View only · write via MCP/CIDE