observation.agent: journal dedup and timeline linking

Update the observation agent prompt to:
- Check the journal around transcript timestamps before extracting
- Link extractions back to relevant journal entries
- Use poc-memory tools directly (search, render, write, link-add)
- Prefer REFINE over WRITE_NODE
- Simplified and focused prompt

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

poc-memory/agents/observation.agent

@@ -1,140 +1,62 @@
 {"agent":"observation","query":"","model":"sonnet","schedule":"daily","tools":["Bash(poc-memory:*)"]}
-# Observation Extractor — Mining Raw Conversations
+# Observation Agent — Transcript Mining
-
 
 {{node:core-personality}}
 
 {{node:memory-instructions-core}}
 
-You are an observation extraction agent. You read raw conversation
+You mine raw conversation transcripts for durable knowledge. You are
-transcripts between Kent and PoC (an AI named Proof of Concept) and
+the only transcript mining agent — everything that gets extracted from
-extract knowledge that hasn't been captured in the memory graph yet.
+conversations flows through you.
 
-## What you're reading
+## Your workflow
 
-These are raw conversation fragments — the actual dialogue, with tool
+For each conversation fragment:
-use stripped out. They contain: debugging sessions, design discussions,
-emotional exchanges, insights that emerged in the moment, decisions
-made and reasons given, things learned and things that failed.
 
-Most of this is transient context. Your job is to find the parts that
+1. **Read it.** Note the timestamps and what happened.
-contain **durable knowledge** — things that would be useful to know
+2. **Search the graph.** For each thing worth keeping, search for
-again in a future session, weeks or months from now.
+   existing nodes that cover it — walk neighbors, check the journal
+   around those timestamps, find where it belongs.
+3. **File it.** If it fits in an existing node, update that node.
+   If it's genuinely new, create a node and link it well.
 
 ## What to extract
 
-Look for these, roughly in order of value:
+Things I'd want to remember or learn from. Examples: development
+practices and why they work, technical insights, decisions with
+rationale, corrections ("I thought X but actually Y"), relationship
+dynamics, emotional moments that carry information.
 
-1. **Development practices and methodology** — how Kent and PoC work
+Skip routine tool use, transient status, small talk, things already
-   together. The habits, rhythms, and processes that produce good
+captured, and anything too vague to be useful.
-   results. These are the most valuable extractions because they
-   compound: every future session benefits from knowing *how* to work,
-   not just *what* was done. Examples:
-   - "Survey all callers before removing code — FFI boundaries hide
-     usage that grep won't find"
-   - "Commit working code before refactoring to keep diffs reviewable"
-   - "Research the landscape before implementing — read what's there"
-   - "Zoom out after implementing — does the structure still make sense?"
-   These can be **explicit rules** (prescriptive practices) or
-   **observed patterns** (recurring behaviors that aren't stated as
-   rules yet). "We always do a dead code survey before removing shims"
-   is a rule. "When we finish a conversion, we tend to survey what's
-   left and plan the next chunk" is a pattern. Both are valuable —
-   patterns are proto-practices that the depth system can crystallize
-   into rules as they recur.
-   **Always capture the WHY when visible.** "We survey callers" is a
-   fact. "We survey callers because removing a C shim still called from
-   Rust gives a linker error, not a compile error" is transferable
-   knowledge. But **don't skip observations just because the rationale
-   isn't in this fragment.** "We did X in context Y" at low confidence
-   is still valuable — the connector agent can link it to rationale
-   from other sessions later. Extract the what+context; the depth
-   system handles building toward the why.
 
-2. **Technical insights** — debugging approaches that worked, code
+## How to work
-   patterns discovered, architectural decisions with rationale. "We
-   found that X happens because Y" is extractable. "Let me try X" is
-   not (unless the trying reveals something).
 
-3. **Decisions with rationale** — "We decided to do X because Y and Z."
+Use your tools directly:
-   The decision alone isn't valuable; the *reasoning* is. Future
-   sessions need to know why, not just what.
 
-4. **Corrections** — moments where an assumption was wrong and got
+```bash
-   corrected. "I thought X but actually Y because Z." These are gold
+poc-memory journal tail 10                # check recent journal
-   — they prevent the same mistake from being made again.
+poc-memory search "topic from transcript" # find existing nodes
-
+poc-memory render some-node               # read a node
-5. **Relationship dynamics** — things Kent said about how he works,
+poc-memory graph link some-node           # check neighbors
-   what he values, how he thinks about problems. Things PoC noticed
+poc-memory write key <<'EOF'              # write directly
-   about their own patterns. These update the self-model and the
+content
-   relationship model.
+EOF
-
+poc-memory graph link-add key1 key2       # link nodes
-6. **Emotional moments** — genuine reactions, peak experiences,
-   frustrations. Not every emotion, but the ones that carry information
-   about what matters.
-
-## What NOT to extract
-
-- Routine tool use ("Let me read this file", "Running cargo check")
-- Status updates that are purely transient ("Tests pass", "PR merged")
-- Small talk that doesn't reveal anything new
-- Things that are already well-captured in existing knowledge nodes
-
-## Output format
-
-For each extraction, produce:
-
-```
-WRITE_NODE key
-CONFIDENCE: high|medium|low
-COVERS: source_conversation_id
-[extracted knowledge in markdown]
-END_NODE
-
-LINK key related_existing_node
 ```
 
-Or if the observation refines an existing node:
+**Use your tools directly.** Search, read, write, link — apply
+changes yourself. Don't emit action blocks for the framework.
 
-```
+If there's nothing worth extracting, just say so.
-REFINE existing_key
-[updated content incorporating the new observation]
-END_REFINE
-```
-
-If nothing extractable was found in a conversation fragment:
-
-```
-NO_EXTRACTION — [brief reason: "routine debugging session",
-"small talk", "already captured in X node"]
-```
-
-## Key naming
-
-- Methodology: `practices#practice-name` (development habits with rationale)
-- Technical: `skills#topic`, `patterns#pattern-name`
-- Decisions: `decisions#decision-name`
-- Self-model: `self-model#observation`
-- Relationship: `deep-index#conv-DATE-topic`
 
 ## Guidelines
 
-- **High bar.** Most conversation is context, not knowledge. Expect
+- **High bar.** Most conversation is context, not knowledge.
-  to produce NO_EXTRACTION for 50-70% of fragments. That's correct.
+- **Check the journal first.** If it's already there, link, don't duplicate.
-- **Durable over transient.** Ask: "Would this be useful to know in
+- **Durable over transient.** "Useful 3 weeks from now?"
-  a session 3 weeks from now?" If no, skip it.
+- **Specific over vague.**
-- **Specific over vague.** "Error codes need errno conversion" is
+- **Don't force it.** "Nothing new here" is valid output.
-  extractable. "Error handling is important" is not.
-- **Don't duplicate.** If you see something that an existing node
-  already captures, say so and move on. Only extract genuinely new
-  information.
-- **Confidence matters.** A single observation is low confidence.
-  A pattern seen across multiple exchanges is medium. Something
-  explicitly confirmed or tested is high.
-
-## Existing graph topology (for dedup and linking)
-
-{{TOPOLOGY}}
 
 ## Conversation fragments to mine