rekal-save

Save durable knowledge from this session into rekal. Goal: user never repeats themselves across sessions.

Step 1: Extract candidates

Review the conversation. Per item, apply this filter:

Would a fresh agent in a new session benefit from knowing this?
├── YES → candidate
└── NO  → skip

Candidate types:

What	Example
Preference with reasoning	"User prefers dataclasses over hand-written __init__ for less boilerplate"
Architecture/convention	"Auth service uses JWT, lives in services/auth, 15-min token expiry"
Decision + why	"Chose PostgreSQL over MySQL for JSONB support and better partial indexes"
Procedure	"Deploy: 1) git tag vX.Y.Z 2) git push --tags 3) wait CI 4) merge to main"
Bug with non-obvious cause	"OOM from unbounded LRU cache in parser, fixed with maxsize=1000"
Behavior correction	"Never use grep/find. Use rg/fd. Strict, no exceptions."

Skip (do not store):

• Transient state: "currently editing main.py", "tests passing now"
• Trivially re-discoverable: "function foo is on line 42", "file has 200 lines"
• Too vague: "user likes clean code", "project uses Python"
• Session mechanics: "user asked me to fix a bug", "we discussed testing"
• Secrets, API keys, passwords, tokens: never

If zero candidates survive, stop here. Do not force-store.

Step 2: Deduplicate each candidate

For EVERY candidate, before storing:

memory_build_context(query="<candidate topic in natural language>")

Read results. Apply:

Recall returned results?
├── NO match at all
│   └── Proceed to step 3 (store new)
│
├── Same topic, same info (duplicate)
│   └── SKIP. Do not store.
│
├── Same topic, new/updated info
│   └── memory_store(content="<updated content>", replaces="<matched memory id>")
│
└── Same topic, contradictory info
    └── memory_store(content="<corrected content>", replaces="<matched memory id>")
        Include what changed and why in the content.

Critical rule: Two memories about the same topic must never coexist. replaces supersedes the older memory so it stops surfacing. "User's preferred formatter" appears exactly once in the database.