Commit graph

7 commits

Author SHA1 Message Date
Kent Overstreet
b4e674806d agents: self-contained agent files with embedded prompts
Each agent is a .agent file: JSON config on the first line, blank line,
then the raw prompt markdown. Fully self-contained, fully readable.
No separate template files needed.

Agents dir: checked into repo at poc-memory/agents/. Code looks there
first (via CARGO_MANIFEST_DIR), falls back to ~/.claude/memory/agents/.

Three agents migrated: replay, linker, transfer.

Co-Authored-By: ProofOfConcept <poc@bcachefs.org>
2026-03-10 15:29:55 -04:00
ProofOfConcept
0e1e5a1981 agent visits: track when agents successfully process nodes
New append-only visits.capnp log records which agent processed which
node and when. Only recorded on successful completion — transient
errors don't mark nodes as "seen."

Schema: AgentVisit{nodeUuid, nodeKey, agent, timestamp, outcome}
Storage: append_visits(), replay_visits(), in-memory VisitIndex
Recording: daemon records visits after successful LLM call
API: agent_prompt() returns AgentBatch{prompt, node_keys} so callers
know which nodes to mark as visited.

Groundwork for using visit recency in agent node selection — agents
will deprioritize recently-visited nodes.
2026-03-10 14:30:53 -04:00
ProofOfConcept
8bbc246b3d split agent: parallel execution, agent-driven edges, no MCP overhead
- Refactor split from serial batch to independent per-node tasks
  (run-agent split N spawns N parallel tasks, gated by llm_concurrency)
- Replace cosine similarity edge inheritance with agent-assigned
  neighbors in the plan JSON — the LLM already understands the
  semantic relationships, no need to approximate with bag-of-words
- Add --strict-mcp-config to claude CLI calls to skip MCP server
  startup (saves ~5s per call)
- Remove hardcoded 2000-char split threshold — let the agent decide
  what's worth splitting
- Reload store before mutations to handle concurrent split races
2026-03-10 03:21:33 -04:00
ProofOfConcept
149c289fea split agent: filter candidates to semantic nodes only
Episodic nodes (journal entries, digests) are narratives that should
not be split even when large. Only semantic reference nodes that have
grown to cover multiple topics are candidates.
2026-03-10 01:58:15 -04:00
ProofOfConcept
ca62692a28 split agent: two-phase node decomposition for memory consolidation
Phase 1 sends a large node with its neighbor communities to the LLM
and gets back a JSON split plan (child keys, descriptions, section
hints). Phase 2 fires one extraction call per child in parallel —
each gets the full parent content and extracts/reorganizes just its
portion.

This handles arbitrarily large nodes because output is always
proportional to one child, not the whole parent. Tested on the kent
node (19K chars → 3 children totaling 20K chars with clean topic
separation).

New files:
  prompts/split-plan.md   — phase 1 planning prompt
  prompts/split-extract.md — phase 2 extraction prompt
  prompts/split.md        — original single-phase (kept for reference)

Modified:
  agents/prompts.rs — split_candidates(), split_plan_prompt(),
                      split_extract_prompt(), agent_prompt "split" arm
  agents/daemon.rs  — job_split_agent() two-phase implementation,
                      RPC dispatch for "split" agent type
  tui.rs            — added "split" to AGENT_TYPES
2026-03-10 01:48:41 -04:00
ProofOfConcept
4c973183c4 rename agent: LLM-powered semantic key generation for memory nodes
New consolidation agent that reads node content and generates semantic
3-5 word kebab-case keys, replacing auto-generated slugs (5K+ journal
entries with truncated first-line slugs, 2.5K mined transcripts with
opaque UUIDs).

Implementation:
- prompts/rename.md: agent prompt template with naming conventions
- prompts.rs: format_rename_candidates() selects nodes with long
  auto-generated keys, newest first
- daemon.rs: job_rename_agent() parses RENAME actions from LLM
  output and applies them directly via store.rename_node()
- Wired into RPC handler (run-agent rename) and TUI agent types
- Fix epoch_to_local panic on invalid timestamps (fallback to UTC)

Rename dramatically improves search: key-component matching on
"journal#2026-02-28-violin-dream-room" makes the node findable by
"violin", "dream", or "room" — the auto-slug was unsearchable.
2026-03-10 00:55:26 -04:00
ProofOfConcept
cee9b76a7b move LLM-dependent modules into agents/ subdir
Separate the agent layer (everything that calls external LLMs or
orchestrates sequences of such calls) from core graph infrastructure.

agents/: llm, prompts, audit, consolidate, knowledge, enrich,
         fact_mine, digest, daemon

Root: store/, graph, spectral, search, similarity, lookups, query,
      config, util, migrate, neuro/ (scoring + rewrite)

Re-exports at crate root preserve backwards compatibility so
`crate::llm`, `crate::digest` etc. continue to work.
2026-03-08 21:27:41 -04:00
Renamed from poc-memory/src/neuro/prompts.rs (Browse further)