Compare commits

..
Author SHA1 Message Date
Sharang ParnerkarandClaude Opus 4.8 6ae5d9a07f fix(orchestrator): run semantic control mapping on PLC findings
CI / Check (pull_request) Successful in 5m40s
CI / Detect Changes (pull_request) Skipped
CI / Deploy Agent (pull_request) Skipped
CI / Deploy Dashboard (pull_request) Skipped
CI / Deploy Docs (pull_request) Skipped
CI / Deploy MCP (pull_request) Skipped
CI / Check (push) Skipped
run_plc_scan is a separate path from run_pipeline and never called the
control-mapping passes, so IEC 61131-3 (pump_station.st etc.) findings were
persisted with empty control_refs even with mapping enabled. PLC findings carry
file_path/line/cwe, so the semantic pass now runs per source (its region is read
under that source's working path) and stamps master-control refs. LUT + grounded
passes are code-pattern/CRA-specific and don't apply to control logic, so only the
semantic pass runs on the PLC path.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-22 15:09:48 +02:00
sharang 5bdc35ee92 fix(orchestrator): refresh control_refs on existing findings during re-scan (#228)
CI / Check (push) Skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 4m13s
CI / Deploy Dashboard (push) Skipped
CI / Deploy Docs (push) Skipped
CI / Deploy MCP (push) Skipped
2026-07-22 12:24:36 +00:00
sharang ea516cc054 docs(control-mapping): MCP emission loop + default-on flags (#227)
CI / Check (push) Skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Skipped
CI / Deploy Docs (push) Successful in 57s
CI / Deploy Dashboard (push) Skipped
CI / Deploy MCP (push) Skipped
2026-07-22 11:23:51 +00:00
+35 -2
View File
@@ -277,8 +277,10 @@ impl PipelineOrchestrator {
}
}
// Dedup against existing findings and insert new ones
// Dedup against existing findings: insert first-seen ones, and refresh the
// control mappings on ones we've seen before.
let mut new_count = 0u32;
let mut refreshed_count = 0u32;
let mut new_findings: Vec<Finding> = Vec::new();
for mut finding in all_findings {
finding.scan_run_id = Some(scan_run_id.to_string());
@@ -293,8 +295,25 @@ impl PipelineOrchestrator {
finding.id = result.inserted_id.as_object_id();
new_findings.push(finding);
new_count += 1;
} else if !finding.control_refs.is_empty() {
// Re-scan refresh: a mapping pass (newly enabled or tuned) computed
// control_refs for a finding first seen before mapping ran. Persist
// them onto the existing row — the insert path alone never would.
self.db
.findings()
.update_one(
doc! { "fingerprint": &finding.fingerprint },
doc! { "$set": { "control_refs": finding.control_refs.clone() } },
)
.await?;
refreshed_count += 1;
}
}
if refreshed_count > 0 {
tracing::info!(
"[{repo_id}] Refreshed control_refs on {refreshed_count} existing findings"
);
}
// Remove stale SBOM entries for this repo before reinserting
if !sbom_entries.is_empty() {
@@ -567,7 +586,21 @@ impl PipelineOrchestrator {
let Some(path) = ingest_set.get(&a.id).and_then(|ia| ia.working_path.clone()) else {
continue;
};
all_findings.extend(crate::pipeline::plc::analyze_tree(&path, target_id));
let mut source_findings = crate::pipeline::plc::analyze_tree(&path, target_id);
// Control mapping for the PLC path (run_plc_scan is separate from
// run_pipeline, which does its own mapping). PLC findings carry
// file_path/line/cwe, so the semantic pass reads each region under this
// source's `path` and stamps master-control refs. The LUT + grounded
// surface passes are code-pattern / CRA-specific and don't apply to
// IEC 61131-3 control logic, so only the semantic pass runs here.
crate::controls::semantic_stamp_findings(
&self.config,
self.llm.clone(),
&path,
&mut source_findings,
)
.await;
all_findings.extend(source_findings);
// Control-application SBOM: CODESYS libraries + runtime from a
// `.projectarchive` (uploaded, or committed in the working tree).
let archive = a