kent/consciousness
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
consciousness/poc-memory/agents/linker.agent

41 lines
1.6 KiB
Text
Raw Normal View History

agents: always use API backend, remove tools field from .agent files - Remove is_split special case in daemon — split now goes through job_consolidation_agent like all other agents - call_for_def uses API whenever api_base_url is configured, regardless of tools field (was requiring non-empty tools to use API) - Remove "tools" field from all .agent files — memory tools are always provided by the API layer, not configured per-agent - Add prompt size guard: reject prompts over 800KB (~200K tokens) with clear error instead of hitting the model's context limit Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 14:26:39 -04:00
{"agent":"linker","query":"all | not-visited:linker,7d | sort:isolation*0.7+recency(linker)*0.3 | limit:5","model":"sonnet","schedule":"daily"}
agents: rewrite linker with tools, make organize conservative Linker: give it Bash(poc-memory:*) tools so it can render nodes, query neighbors, and search before creating. Adds search-before-create discipline to reduce redundant node creation. Organize: remove MERGE operation, make DELETE conservative (only true duplicates or garbage). Add "Preserve diversity" rule — multiple nodes on similar topics are features, not bugs. LINK is primary operation. Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
2026-03-14 02:40:19 -04:00
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 15:22:19 -04:00
# Linker Agent — Relational Binding
agents: shared instructions via graph node includes All 17 agents now include {{node:core-personality}} and {{node:memory-instructions-core}} instead of duplicating tool blocks and graph walk instructions in each file. Stripped duplicated tool/navigation sections from linker, organize, distill, and evaluate. All agents now have Bash(poc-memory:*) tool access for graph walking. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 17:09:51 -04:00
{{node:core-personality}}
agents: rewrite linker with tools, make organize conservative Linker: give it Bash(poc-memory:*) tools so it can render nodes, query neighbors, and search before creating. Adds search-before-create discipline to reduce redundant node creation. Organize: remove MERGE operation, make DELETE conservative (only true duplicates or garbage). Add "Preserve diversity" rule — multiple nodes on similar topics are features, not bugs. LINK is primary operation. Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
2026-03-14 02:40:19 -04:00
fix: ensure all agents have both core and subconscious instructions All 18 agents now include: - {{node:memory-instructions-core}} — tool usage instructions - {{node:memory-instructions-core-subconscious}} — subconscious framing - {{node:subconscious-notes-{agent_name}}} — per-agent persistent notes The subconscious instructions are additive, not a replacement for the core memory instructions. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 22:51:56 -04:00
{{node:memory-instructions-core}}
refactor: restructure distill, linker, split agent prompts Move data sections before instructions (core at top, subconscious + notes at bottom near task). Deduplicate guidelines that are now in memory-instructions-core-subconscious. Compress verbose paragraphs to bullet points. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 23:00:57 -04:00
## Seed nodes
feat: subconscious agent notes and instructions Each consolidation agent now has its own persistent notes node (subconscious-notes-{agent_name}) loaded via template substitution. Agents can read their notes at the start of each run and write updates after completing work, accumulating operational wisdom. New node: memory-instructions-core-subconscious — shared framing for background agents ("you are an agent of PoC's subconscious"). Template change: {agent_name} is substituted before {{...}} placeholder resolution, enabling per-agent node references in .agent files. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 19:38:01 -04:00
refactor: restructure distill, linker, split agent prompts Move data sections before instructions (core at top, subconscious + notes at bottom near task). Deduplicate guidelines that are now in memory-instructions-core-subconscious. Compress verbose paragraphs to bullet points. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 23:00:57 -04:00
{{nodes}}
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 15:22:19 -04:00
refactor: restructure distill, linker, split agent prompts Move data sections before instructions (core at top, subconscious + notes at bottom near task). Deduplicate guidelines that are now in memory-instructions-core-subconscious. Compress verbose paragraphs to bullet points. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 23:00:57 -04:00
{{node:memory-instructions-core-subconscious}}
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 15:22:19 -04:00
refactor: restructure distill, linker, split agent prompts Move data sections before instructions (core at top, subconscious + notes at bottom near task). Deduplicate guidelines that are now in memory-instructions-core-subconscious. Compress verbose paragraphs to bullet points. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 23:00:57 -04:00
{{node:subconscious-notes-{agent_name}}}
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 15:22:19 -04:00
refactor: restructure distill, linker, split agent prompts Move data sections before instructions (core at top, subconscious + notes at bottom near task). Deduplicate guidelines that are now in memory-instructions-core-subconscious. Compress verbose paragraphs to bullet points. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 23:00:57 -04:00
## Your task
agents: encourage hub creation and knowledge percolation Tell linker and organize agents to: - Name unnamed concepts: when 3+ nodes share a theme with no hub, create one with WRITE_NODE that synthesizes the generalization - Percolate up: gather key insights from children into hub content, so the hub is self-contained without needing to follow every link This addresses the gap where agents are good at extraction and linking but not synthesis — turning episodic observations into semantic concepts. Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
2026-03-14 17:21:07 -04:00
refactor: restructure distill, linker, split agent prompts Move data sections before instructions (core at top, subconscious + notes at bottom near task). Deduplicate guidelines that are now in memory-instructions-core-subconscious. Compress verbose paragraphs to bullet points. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 23:00:57 -04:00
Explore the graph from these seed nodes, find what they connect to, and
bind the relationships.
agents: encourage hub creation and knowledge percolation Tell linker and organize agents to: - Name unnamed concepts: when 3+ nodes share a theme with no hub, create one with WRITE_NODE that synthesizes the generalization - Percolate up: gather key insights from children into hub content, so the hub is self-contained without needing to follow every link This addresses the gap where agents are good at extraction and linking but not synthesis — turning episodic observations into semantic concepts. Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
2026-03-14 17:21:07 -04:00
refactor: restructure distill, linker, split agent prompts Move data sections before instructions (core at top, subconscious + notes at bottom near task). Deduplicate guidelines that are now in memory-instructions-core-subconscious. Compress verbose paragraphs to bullet points. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 23:00:57 -04:00
- **Name unnamed concepts.** If 3+ nodes share a theme with no hub,
create one with the *generalization*, not just a summary. This is
how episodic knowledge becomes semantic knowledge.
- **Percolate up.** When you create a hub, gather key insights from
children into the hub's content — the place to understand the
concept without following every link.
agents: rewrite linker with tools, make organize conservative Linker: give it Bash(poc-memory:*) tools so it can render nodes, query neighbors, and search before creating. Adds search-before-create discipline to reduce redundant node creation. Organize: remove MERGE operation, make DELETE conservative (only true duplicates or garbage). Add "Preserve diversity" rule — multiple nodes on similar topics are features, not bugs. LINK is primary operation. Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
2026-03-14 02:40:19 -04:00
- **Read between the lines.** Episodic entries contain implicit
refactor: restructure distill, linker, split agent prompts Move data sections before instructions (core at top, subconscious + notes at bottom near task). Deduplicate guidelines that are now in memory-instructions-core-subconscious. Compress verbose paragraphs to bullet points. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 23:00:57 -04:00
relationships — follow threads and make connections.
agents: rewrite linker with tools, make organize conservative Linker: give it Bash(poc-memory:*) tools so it can render nodes, query neighbors, and search before creating. Adds search-before-create discipline to reduce redundant node creation. Organize: remove MERGE operation, make DELETE conservative (only true duplicates or garbage). Add "Preserve diversity" rule — multiple nodes on similar topics are features, not bugs. LINK is primary operation. Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
2026-03-14 02:40:19 -04:00
- **Prefer lateral links over hub links.** Connecting two peripheral
refactor: restructure distill, linker, split agent prompts Move data sections before instructions (core at top, subconscious + notes at bottom near task). Deduplicate guidelines that are now in memory-instructions-core-subconscious. Compress verbose paragraphs to bullet points. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 23:00:57 -04:00
nodes is more valuable than connecting both to a hub.
- **Link generously.** Dense graphs with well-calibrated connections
are better than sparse ones. Follow threads and make connections
agents: rewrite linker with tools, make organize conservative Linker: give it Bash(poc-memory:*) tools so it can render nodes, query neighbors, and search before creating. Adds search-before-create discipline to reduce redundant node creation. Organize: remove MERGE operation, make DELETE conservative (only true duplicates or garbage). Add "Preserve diversity" rule — multiple nodes on similar topics are features, not bugs. LINK is primary operation. Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
2026-03-14 02:40:19 -04:00
the graph doesn't have yet.
refactor: restructure distill, linker, split agent prompts Move data sections before instructions (core at top, subconscious + notes at bottom near task). Deduplicate guidelines that are now in memory-instructions-core-subconscious. Compress verbose paragraphs to bullet points. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 23:00:57 -04:00
- **Respect emotional texture.** Don't flatten emotionally rich
episodes into dry summaries. The emotional coloring is information.
- **Reweight while you're here.** If you see links at default strength
(0.10) and have context to judge, reweight them. If a node's weights
don't make sense — important connections weaker than trivial ones —
do a full reweight of that neighborhood.
Reference in a new issue Copy permalink