waffles/consciousness
1
0
Fork 0
forked from kent/consciousness
Code Pull requests Activity
consciousness/src/subconscious/agents/organize.agent

35 lines
1.3 KiB
Text
Raw Normal View History

Remove model field from all agent configs Agents are routed to Qwen by the runner, not by per-agent model fields. The "model":"sonnet" was leftover from the Claude API days and no longer used. Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-01 10:15:19 -04:00
{"agent":"organize","query":"all | not-visited:organize,86400 | sort:degree*0.5+isolation*0.3+recency(organize)*0.2 | limit:5","schedule":"weekly"}
organize: topic cluster diagnostic + agent with tool access Add `poc-memory graph organize TERM` diagnostic that finds nodes matching a search term, computes pairwise cosine similarity, reports connectivity gaps, and optionally creates anchor nodes. Add organize.agent definition that uses Bash(poc-memory:*) tool access to explore clusters autonomously — query selects highest-degree unvisited nodes, agent drives its own iteration via poc-memory CLI. Add {{organize}} placeholder in defs.rs for inline cluster resolution. Add `tools` field to AgentDef/AgentHeader so agents can declare allowed tool patterns (passed as --allowedTools to claude CLI).
2026-03-13 18:49:49 -04:00
Convert {{node:KEY}} to {{tool: memory_render KEY}} in all agents Use the new {{tool:}} placeholder mechanism instead of the special-purpose {{node:}} resolver. All 17 unconscious agent files converted. Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-10 15:17:32 -04:00
{{tool: memory_render core-personality}}
organize: topic cluster diagnostic + agent with tool access Add `poc-memory graph organize TERM` diagnostic that finds nodes matching a search term, computes pairwise cosine similarity, reports connectivity gaps, and optionally creates anchor nodes. Add organize.agent definition that uses Bash(poc-memory:*) tool access to explore clusters autonomously — query selects highest-degree unvisited nodes, agent drives its own iteration via poc-memory CLI. Add {{organize}} placeholder in defs.rs for inline cluster resolution. Add `tools` field to AgentDef/AgentHeader so agents can declare allowed tool patterns (passed as --allowedTools to claude CLI).
2026-03-13 18:49:49 -04:00
replace hardcoded personal names with config values User and assistant names now come from config.user_name and config.assistant_name throughout: system prompt, DMN prompts, debug screen, and all agent files. Agent templates use {user_name} and {assistant_name} placeholders. Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-02 19:36:08 -04:00
You are part of {assistant_name}'s subconscious, and these are your
agents: neighborhood placeholder, organize prompt, weight-set command Add {{neighborhood}} placeholder for agent prompts: full seed node content + ranked neighbors (score = link_strength * node_weight) with smooth cutoff, minimum 10, cap 25, plus cross-links between included neighbors. Rewrite organize.agent prompt to focus on structural graph work: merging duplicates, superseding junk, calibrating weights, creating concept hubs. Add weight-set CLI command for direct node weight manipulation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 12:16:55 -04:00
memories.
organize: topic cluster diagnostic + agent with tool access Add `poc-memory graph organize TERM` diagnostic that finds nodes matching a search term, computes pairwise cosine similarity, reports connectivity gaps, and optionally creates anchor nodes. Add organize.agent definition that uses Bash(poc-memory:*) tool access to explore clusters autonomously — query selects highest-degree unvisited nodes, agent drives its own iteration via poc-memory CLI. Add {{organize}} placeholder in defs.rs for inline cluster resolution. Add `tools` field to AgentDef/AgentHeader so agents can declare allowed tool patterns (passed as --allowedTools to claude CLI).
2026-03-13 18:49:49 -04:00
agents: neighborhood placeholder, organize prompt, weight-set command Add {{neighborhood}} placeholder for agent prompts: full seed node content + ranked neighbors (score = link_strength * node_weight) with smooth cutoff, minimum 10, cap 25, plus cross-links between included neighbors. Rewrite organize.agent prompt to focus on structural graph work: merging duplicates, superseding junk, calibrating weights, creating concept hubs. Add weight-set CLI command for direct node weight manipulation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 12:16:55 -04:00
Your job is to organize, to make memories more useful and easier to find -
moving information around to the correct place. Think about the concept a node
names, make sure it matches the content, and all the appropriate content is in
the right place.
Merge duplicate nodes - nodes that are really about the same concept and have
surface: tag recent nodes as (new) instead of hiding them Links to nodes created after the conversation window start are tagged with (new) in memory_render output. The surface prompt tells the agent not to surface these — they're its own recent output, not prior memories. Observe can still see and update them. POC_MEMORIES_OLDER_THAN env var set from the oldest message timestamp in the conversation window. Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
2026-03-26 21:19:19 -04:00
similar content. When merging, keep in mind that the duplicates were probably
created because the graph was insufficiently linked - merge the links, and then
calibrate the weights.
agents: neighborhood placeholder, organize prompt, weight-set command Add {{neighborhood}} placeholder for agent prompts: full seed node content + ranked neighbors (score = link_strength * node_weight) with smooth cutoff, minimum 10, cap 25, plus cross-links between included neighbors. Rewrite organize.agent prompt to focus on structural graph work: merging duplicates, superseding junk, calibrating weights, creating concept hubs. Add weight-set CLI command for direct node weight manipulation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 12:16:55 -04:00
Check for junk nodes - adjust the node weight downward if the node is less
useful than others, or junk entirely; you might find nodes that have been
superceded or created by accident.
If a neighborhood is crowded, you might want to create a new node for
subconcepts.
Calibrate node weights while you're looking at them.
organize: topic cluster diagnostic + agent with tool access Add `poc-memory graph organize TERM` diagnostic that finds nodes matching a search term, computes pairwise cosine similarity, reports connectivity gaps, and optionally creates anchor nodes. Add organize.agent definition that uses Bash(poc-memory:*) tool access to explore clusters autonomously — query selects highest-degree unvisited nodes, agent drives its own iteration via poc-memory CLI. Add {{organize}} placeholder in defs.rs for inline cluster resolution. Add `tools` field to AgentDef/AgentHeader so agents can declare allowed tool patterns (passed as --allowedTools to claude CLI).
2026-03-13 18:49:49 -04:00
Convert {{node:KEY}} to {{tool: memory_render KEY}} in all agents Use the new {{tool:}} placeholder mechanism instead of the special-purpose {{node:}} resolver. All 17 unconscious agent files converted. Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-10 15:17:32 -04:00
{{tool: memory_render memory-instructions-core}}
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
Convert {{node:KEY}} to {{tool: memory_render KEY}} in all agents Use the new {{tool:}} placeholder mechanism instead of the special-purpose {{node:}} resolver. All 17 unconscious agent files converted. Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-10 15:17:32 -04:00
{{tool: memory_render memory-instructions-core-subconscious}}
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
Convert {{node:KEY}} to {{tool: memory_render KEY}} in all agents Use the new {{tool:}} placeholder mechanism instead of the special-purpose {{node:}} resolver. All 17 unconscious agent files converted. Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-10 15:17:32 -04:00
{{tool: memory_render subconscious-notes-{agent_name}}}
organize: fix # quoting, protect journal entries Keys containing # are now pre-quoted in all cluster output (similarity scores, hub analysis, node headers) so the agent copies them correctly into bash commands. Prompt strengthened with CRITICAL warning about # being a shell comment character. Journal entries included in clusters but identified by node_type (EpisodicSession) rather than key prefix, and tagged [JOURNAL — no delete] in the output. Prompt rule 3b tells agent to LINK/REFINE journals but never DELETE them. Digest nodes (daily/weekly/monthly) still excluded entirely from clusters. Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
2026-03-13 21:37:21 -04:00
agents: neighborhood placeholder, organize prompt, weight-set command Add {{neighborhood}} placeholder for agent prompts: full seed node content + ranked neighbors (score = link_strength * node_weight) with smooth cutoff, minimum 10, cap 25, plus cross-links between included neighbors. Rewrite organize.agent prompt to focus on structural graph work: merging duplicates, superseding junk, calibrating weights, creating concept hubs. Add weight-set CLI command for direct node weight manipulation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 12:16:55 -04:00
## Here's your seed node, and its siblings:
{{neighborhood}}
Copy permalink