kent/consciousness
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

scoring: configurable agent_budget, squared Elo distribution

Browse source 
agent_budget config (default 1000) replaces health-metric-computed
totals. The budget is the total agent runs per cycle — use it all.

Elo distribution is squared for power-law unfairness: top-rated agents
get disproportionately more runs. If linker has Elo 1123 and connector
has 876, linker gets ~7x more runs (squared ratio) vs ~3.5x (linear).

Minimum 2 runs per type so underperformers still get evaluated.

No Elo file → equal distribution as fallback.

Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
This commit is contained in:
ProofOfConcept 2026-03-14 20:05:53 -04:00
parent e9791991a7
commit 46b4f6f434
2 changed files with 50 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

6
poc-memory/src/config.rs
View file

@ -51,6 +51,8 @@ pub struct Config {
pub context_groups: Vec<ContextGroup>,
/// Max concurrent LLM calls in the daemon.
pub llm_concurrency: usize,
/// Total agent runs per consolidation cycle.
pub agent_budget: usize,
/// Directory containing prompt templates for agents.
pub prompts_dir: PathBuf,
/// Separate Claude config dir for background agent work (daemon jobs).
@ -83,6 +85,7 @@ impl Default for Config {
},
],
llm_concurrency: 1,
agent_budget: 1000,
prompts_dir: home.join("poc/memory/prompts"),
agent_config_dir: None,
}
@ -141,6 +144,9 @@ impl Config {
if let Some(n) = cfg.get("llm_concurrency").and_then(|v| v.as_u64()) {
config.llm_concurrency = n.max(1) as usize;
}
if let Some(n) = cfg.get("agent_budget").and_then(|v| v.as_u64()) {
config.agent_budget = n as usize;
}
if let Some(s) = cfg.get("prompts_dir").and_then(|v| v.as_str()) {
config.prompts_dir = expand_home(s);
}