rohit/probo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Tune tracker workers and bound agent budgets

Browse Source 
The tracker-mapping and common-pattern-enrichment workers ran with the
kit/worker defaults (interval 10s, max-concurrency 5 each) and dropped
the resolved per-agent max-tokens/temperature, so up to ten LLM
pipelines could run unbounded on one OpenAI client. The mapping worker
also held a FOR UPDATE transaction across the LLM and Firecrawl calls
while its DB search tools acquired a second pooled connection, risking
pool exhaustion under concurrency.

Plumb max-tokens, temperature, agent timeout, and per-worker max-turns
through TrackerAgentsConfig and DisambiguationConfig into all three
agent builders, replacing the hard-coded constants with config-fed
fields and package fallbacks. Expose worker interval, concurrency,
stale-after, agent timeout, and max-turns as config (env, Helm values,
deployment template) mirroring the evidence-describer pattern, and
apply them at registration.

Refactor Process into deterministic-read, agent (no transaction), and
persist phases so neither the mapping agent nor disambiguation runs
inside an open transaction, removing the row locks held across network
latency and the nested-connection pressure.

Signed-off-by: Émile Ré <emile@probo.com>
This commit is contained in:
Émile Ré
2026-05-29 16:37:32 +02:00
parent 50c5454681
commit 55302d18f0
17 changed files with 818 additions and 339 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
pkg/bootstrap/builder.go
View File

@@ -207,10 +207,13 @@ func (b *Builder) Build() (*probodconfig.FullConfig, error) {
MaxTokens: b.getEnvIntPtr("AGENT_EVIDENCE_DESCRIBER_MAX_TOKENS"),
},
TrackerMapping: probodconfig.LLMAgentConfig{
Provider: b.getEnvOrDefault("AGENT_TRACKER_MAPPING_PROVIDER", ""),
ModelName: b.getEnvOrDefault("AGENT_TRACKER_MAPPING_MODEL_NAME", ""),
Provider: b.getEnvOrDefault("AGENT_TRACKER_MAPPING_PROVIDER", ""),
ModelName: b.getEnvOrDefault("AGENT_TRACKER_MAPPING_MODEL_NAME", ""),
// The tracker agents emit tiny structured JSON, so
// they default to a smaller token budget than the
// shared default rather than inheriting it.
Temperature: b.getEnvFloatPtr("AGENT_TRACKER_MAPPING_TEMPERATURE"),
MaxTokens: b.getEnvIntPtr("AGENT_TRACKER_MAPPING_MAX_TOKENS"),
MaxTokens: new(b.getEnvIntOrDefault("AGENT_TRACKER_MAPPING_MAX_TOKENS", 1024)),
},
Tools: probodconfig.AgentToolsConfig{
FirecrawlAPIKey: b.getEnv("FIRECRAWL_API_KEY"),
@@ -242,6 +245,19 @@ func (b *Builder) Build() (*probodconfig.FullConfig, error) {
StaleAfter: b.getEnvIntOrDefault("EVIDENCE_DESCRIBER_STALE_AFTER", 300),
MaxConcurrency: b.getEnvIntOrDefault("EVIDENCE_DESCRIBER_MAX_CONCURRENCY", 10),
},
TrackerMappingWorker: probodconfig.TrackerMappingWorkerConfig{
Interval: b.getEnvIntOrDefault("TRACKER_MAPPING_INTERVAL", 10),
MaxConcurrency: b.getEnvIntOrDefault("TRACKER_MAPPING_MAX_CONCURRENCY", 3),
AgentTimeout: b.getEnvIntOrDefault("TRACKER_MAPPING_AGENT_TIMEOUT", 45),
AgentMaxTurns: b.getEnvIntOrDefault("TRACKER_MAPPING_AGENT_MAX_TURNS", 4),
},
CommonPatternEnrichmentWorker: probodconfig.CommonPatternEnrichmentWorkerConfig{
Interval: b.getEnvIntOrDefault("COMMON_PATTERN_ENRICHMENT_INTERVAL", 10),
MaxConcurrency: b.getEnvIntOrDefault("COMMON_PATTERN_ENRICHMENT_MAX_CONCURRENCY", 2),
StaleAfter: b.getEnvIntOrDefault("COMMON_PATTERN_ENRICHMENT_STALE_AFTER", 600),
AgentTimeout: b.getEnvIntOrDefault("COMMON_PATTERN_ENRICHMENT_AGENT_TIMEOUT", 45),
AgentMaxTurns: b.getEnvIntOrDefault("COMMON_PATTERN_ENRICHMENT_AGENT_MAX_TURNS", 3),
},
Branding: b.getEnvBoolOrDefault("BRANDING", true),
},
}