perf(db): batch coverage-graph lookups and index icp scope probes

BuildCoverageGraph issued one QueryRow per connector root domain and one per company: 221 statements for a task scoped by 800 subdomains over 200 roots and 20 companies. Fetch them with one ANY() query each. The coverage target join probes task_scope once per asset, and the icp branch fell back to uq_task_scope_v2 with only kind as index condition; migration 0003 adds a partial index on task_scope(value) for icp rows. Large-fixture invariants test and benchmark included.

.github/workflows/ci.yml

@@ -45,8 +45,9 @@ jobs:
         # keeps the database state deterministic.
         run: go test -p 1 ./...
       - name: go test -race
-        # Race detector on the packages that pass under -race today. ./server is
-        # left out until it has been checked with -race against postgres.
+        # Race detector on the packages that pass under -race today. ./server
+        # joined once its suite was checked with -race against postgres and its
+        # test teardown fixed (#227, #228).
         # Its own database: the plain run above leaves rows behind and the db tests
         # are not idempotent across runs (duplicate llm_profiles names).
         env:
@@ -54,7 +55,8 @@ jobs:
 
         run: >-
           go test -race -p 1 ./agent ./cmd/artex ./config ./db ./evidence ./guard
-          ./intercept ./llmpool ./llmrec ./mcphttp ./notify ./sidequestion ./traffic
+          ./intercept ./llmpool ./llmrec ./mcphttp ./notify ./server ./sidequestion
+          ./traffic
 
   shell:
     runs-on: ubuntu-latest

CHANGELOG.md

@@ -2,6 +2,12 @@
 
 All notable changes to this project are documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
+## [Unreleased]
+
+### Changed
+
+- **Untrusted-output boundary is now on by default**: Norma frames tool results for the worker, planner, chat and main agent unless `ARTEX_UNTRUSTED_BOUNDARY` is set to `0`, `false`, `off` or `no`. It was opt-in via `ARTEX_UNTRUSTED_BOUNDARY=1` in 0.6.0 (#166).
+
 ## [0.6.0] - 2026-11-12
 
 Machine-checked finding verification (S1), intercept decisions traced to their actor, configurable notification limits, prompt hardening and goal guards from the #124 agentic audit, the target gate (S3b phase 1 and step 2.1, off by default and API-only), intent claim leases, and checksum-verified tool downloads in the Docker image.

Dockerfile

@@ -178,7 +178,7 @@ COPY --from=build /out/artex /app/artex
 COPY start.sh /app/start.sh
 RUN chmod +x /app/artex /app/start.sh && mkdir -p /app/keys
 COPY skills/ /app/skills/
-# persistence points: data/ (SQLite, task files) and keys/ (jwt.key, via ARTEX_JWT_KEY_DIR)
+# persistence points: data/ (traffic index, task files, transcripts) and keys/ (jwt.key, secret.key, via ARTEX_JWT_KEY_DIR)
 VOLUME ["/app/data", "/app/keys"]
 EXPOSE 8787 8788
 ENTRYPOINT ["/app/start.sh"]

README.md

@@ -161,7 +161,7 @@ CGO_ENABLED=0 go build -tags embedui -o artex ./cmd/artex
 
 ```bash
 ./build.sh --release
-# output: dist/artex-0.3.3-*.zip
+# output: dist/artex-<version>-*.zip
 ```
 
 UPX self-extracting binaries may be incompatible with some Linux kernels, virtualization environments, or security policies, so they are disabled by default. Use `ARTEX_TARGETS` to customize the targets; when you have confirmed the target runtime is compatible, explicitly pass `--upx` to further shrink the binary:
@@ -207,7 +207,7 @@ Daily cron example (03:20, operator crontab):
 
 ## Updating and upgrading
 
-> Upgrading only swaps the program and never touches data: the Postgres volume `pgdata`, `./data` (SQLite, task files, etc.), `./keys` (jwt.key), and `./skills` are all preserved. **No manual database migration is needed**: `artex` idempotently re-runs `schema.sql` on every start (with `ADD COLUMN` / `CREATE INDEX IF NOT EXISTS`), i.e. "restart equals migrate". It is still recommended to back up `./data` and the database before upgrading.
+> Upgrading only swaps the program and never touches data: the Postgres volume `pgdata`, `./data` (traffic index, task files, transcripts, etc.), `./keys` (jwt.key, secret.key), and `./skills` are all preserved. **No manual database migration is needed**: `artex` idempotently re-runs `schema.sql` on every start (with `ADD COLUMN` / `CREATE INDEX IF NOT EXISTS`), i.e. "restart equals migrate". It is still recommended to back up `./data` and the database before upgrading.
 
 **Update banner (opt-in, off by default)**: start ARTEX with `ARTEX_UPDATE_CHECK=1` to have the backend ask the public GitHub releases API for the latest ARTEX tag, at most once per 24 hours (cached in memory; a failed check is not retried within that window). When the release is newer than the running version, the web UI shows a small dismissible strip linking to the Releases page. The request sends only the `User-Agent: artex-update-check` header. Unset, ARTEX makes no update request and shows no banner.
 

SECURITY.md

@@ -0,0 +1,81 @@
+# Security Policy
+
+## Supported Versions
+
+ARTEX is an autonomous penetration-testing tool. Security fixes are provided only for the latest official release line. The `main` branch is not considered a stable release and may change at any time.
+
+Only the latest release line receives security fixes. Older releases do not receive fixes; please upgrade to the latest release.
+
+Notes:
+- Please upgrade to the latest release before reporting a vulnerability.
+- Forks, custom builds from arbitrary commits, and modified versions are not covered by official support.
+
+## Reporting a Vulnerability
+
+**Do not open a public issue for a security vulnerability.**
+
+Report through **GitHub Security Advisories**: **Security** tab → **Report a vulnerability** in the `BaaRai/ARTEX` repository. This is the only reporting channel.
+
+Please include:
+- A description of the vulnerability and its expected impact.
+- The ARTEX version and/or commit hash.
+- Runtime environment (OS, Docker/local, PostgreSQL, LLM provider, etc.).
+- Minimal reproduction steps (PoC).
+- Logs, screenshots, or sample traffic with **sensitive data removed**.
+- Suggested remediation, if available.
+
+**Do not send** real third-party data, credentials, tokens, customer data, or unredacted sensitive content.
+
+## Scope and Authorized Testing
+
+ARTEX is an offensive-security tool. Test only against:
+- Your own ARTEX deployment in a lab or local environment;
+- Systems you own;
+- Targets explicitly authorized in writing (bug bounty, pentest contract, etc.).
+
+Testing, scanning, or exploiting third-party systems without explicit authorization is strictly prohibited. Reports that violate this principle may be closed without action.
+
+## What to Expect
+
+This is an open-source project maintained on a best-effort basis. We aim to acknowledge a report within about a week and keep you updated, but we cannot guarantee specific response or fix timeframes.
+
+## If a Report Is Accepted
+
+- We will open a private **GitHub Security Advisory** for coordination.
+- We will identify the release containing the fix when it is published.
+- We may request a **CVE** if the vulnerability qualifies.
+- We will credit you or your organization in the advisory if you wish.
+- Default disclosure timing: **90 days** after a fix is available, or earlier by mutual agreement. If the vulnerability is being exploited in the wild, we may disclose earlier.
+
+## If a Report Is Declined
+
+We will explain the reason, for example:
+- It is not a security vulnerability but intended behavior.
+- It is outside ARTEX’s scope (e.g., an issue in an LLM provider, PostgreSQL, Docker, or a browser).
+- There is insufficient information to reproduce it.
+- The report only states that “the tool can be misused” without identifying a specific technical flaw in ARTEX.
+
+Where appropriate, we may convert the report into a public hardening issue or feature request.
+
+## Out of Scope
+
+The following are generally **not** considered ARTEX security vulnerabilities:
+- Attacks or scans against systems you do not own or are not authorized to test.
+- Self-XSS, spam, or brute-force without real impact.
+- Large-scale DoS/DDoS or resource-exhaustion attacks.
+- Social engineering targeting maintainers or users.
+- Issues that exist only in third-party dependencies and do not affect ARTEX.
+- Reports that “ARTEX can be used to attack systems” when the user has valid authorization — this is the nature of a penetration-testing tool, not a vulnerability.
+- Missing headers or hardening configuration without a concrete security impact.
+
+## Safe Harbor
+
+We welcome ethical security research. If you follow this policy and test only within authorized scope, we will not pursue legal action against you for good-faith research. This does not exempt you from applicable laws in your jurisdiction.
+
+## Disclosure Policy
+
+- Do not publicly disclose vulnerability details before a fix is available or before the coordinated disclosure period ends.
+- Do not publish a public PoC without maintainer consent.
+- If you do not receive a response within a reasonable time, please ping the contact channel above before disclosing.
+
+Thank you for helping make ARTEX safer.

agent/assembly.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"log"
 	"runtime/debug"
+	"sync"
 
 	actool "github.com/Autumn-27/norma/tool"
 )
@@ -23,15 +24,36 @@ type DeferredInfo struct {
 	UnlockSkill     func(skillName string)
 }
 
-// ToolAugment, if set, returns the EXTRA tools an agent should see beyond its
-// built-in base set — the agent's visible skills (packed into one Skill meta-tool)
+// ToolAugmentFunc is the ToolAugment hook. If set, it returns the EXTRA tools
+// an agent should see beyond its built-in base set — the agent's visible skills (packed into one Skill meta-tool)
 // and visible MCP servers (expanded to mcp__server__tool). It also returns the
 // DeferredInfo describing how those MCP tools are deferred/gated. The server wires
 // it to the PG agent_visibility table. cleanup releases any spawned MCP clients.
 //
 // When nil, agents run with only their built-in tools — behavior is unchanged
 // until a user assigns a skill/MCP to the agent in the UI.
-var ToolAugment func(ctx context.Context, agentKey string) (extra []actool.CoreTool, def DeferredInfo, cleanup func())
+type ToolAugmentFunc func(ctx context.Context, agentKey string) (extra []actool.CoreTool, def DeferredInfo, cleanup func())
+
+// The hook is set by server wiring while restored tasks may already be
+// assembling tools on other goroutines, so every access goes through the lock.
+var (
+	toolAugmentMu sync.RWMutex
+	toolAugment   ToolAugmentFunc
+)
+
+// SetToolAugment installs (or, with nil, removes) the ToolAugment hook.
+func SetToolAugment(f ToolAugmentFunc) {
+	toolAugmentMu.Lock()
+	toolAugment = f
+	toolAugmentMu.Unlock()
+}
+
+// ToolAugment returns the current ToolAugment hook, or nil when none is set.
+func ToolAugment() ToolAugmentFunc {
+	toolAugmentMu.RLock()
+	defer toolAugmentMu.RUnlock()
+	return toolAugment
+}
 
 // AugmentTools returns base plus the agent's visible skill/MCP tools, the
 // DeferredInfo, and a cleanup func the caller must defer (closes MCP clients).
@@ -42,10 +64,11 @@ func AugmentTools(ctx context.Context, agentKey string, base []actool.CoreTool)
 		cleanup = func() {}
 		out     = base
 	)
-	if ToolAugment != nil {
+	// Copy each hook once under its lock, then call it outside the lock.
+	if augment := ToolAugment(); augment != nil {
 		var extra []actool.CoreTool
 		var cl func()
-		extra, def, cl = ToolAugment(ctx, agentKey)
+		extra, def, cl = augment(ctx, agentKey)
 		if cl != nil {
 			cleanup = cl
 		}
@@ -57,8 +80,8 @@ func AugmentTools(ctx context.Context, agentKey string, base []actool.CoreTool)
 	// agent isn't bound to (or that are disabled) and swap in overridden
 	// descriptions/schemas + default injection. MCP/skill/host tools have no row
 	// and pass through untouched, so deferred/unlock wiring stays consistent.
-	if ToolResolve != nil {
-		out = ToolResolve(ctx, agentKey, out)
+	if resolve := ToolResolve(); resolve != nil {
+		out = resolve(ctx, agentKey, out)
 	}
 	// Tool RAG (off by default): lexical projection of the bound list; only removes.
 	out = applyToolRAG(ctx, agentKey, out, def.Deferred, bm25Score)

agent/assembly_test.go

@@ -0,0 +1,87 @@
+package agent
+
+import (
+	"context"
+	"sync"
+	"testing"
+
+	actool "github.com/Autumn-27/norma/tool"
+)
+
+// Server wiring installs the hooks while restored tasks may already be assembling
+// tools, rendering prompts and building settlement configs on other goroutines.
+// Readers and writers run concurrently here, so under -race any unsynchronised
+// hook access is reported regardless of scheduling.
+func TestAgentHooksConcurrentSwap(t *testing.T) {
+	oldAugment, oldResolve, oldPolicy := ToolAugment(), ToolResolve(), FindingTrafficBindingEnabled()
+	oldPrompt, oldWrapup, oldWrapupTurns := PromptOverride(), WrapupOverride(), WrapupMaxTurnsOverride()
+	oldTimeout, oldTimeoutTurns := WrapupTaskTimeoutOverride(), WrapupTaskTimeoutTurnsOverride()
+	t.Cleanup(func() {
+		SetToolAugment(oldAugment)
+		SetToolResolve(oldResolve)
+		SetFindingTrafficBindingEnabled(oldPolicy)
+		SetPromptOverride(oldPrompt)
+		SetWrapupOverride(oldWrapup)
+		SetWrapupMaxTurnsOverride(oldWrapupTurns)
+		SetWrapupTaskTimeoutOverride(oldTimeout)
+		SetWrapupTaskTimeoutTurnsOverride(oldTimeoutTurns)
+	})
+	augment := func(context.Context, string) ([]actool.CoreTool, DeferredInfo, func()) {
+		return nil, DeferredInfo{}, nil
+	}
+	resolve := func(_ context.Context, _ string, in []actool.CoreTool) []actool.CoreTool { return in }
+	policy := func() bool { return false }
+	text := func(string) (string, bool) { return "", false }
+	turns := func(string) (int, bool) { return 0, false }
+	setAll := func(on bool) {
+		if on {
+			SetToolAugment(augment)
+			SetToolResolve(resolve)
+			SetFindingTrafficBindingEnabled(policy)
+			SetPromptOverride(text)
+			SetWrapupOverride(text)
+			SetWrapupMaxTurnsOverride(turns)
+			SetWrapupTaskTimeoutOverride(text)
+			SetWrapupTaskTimeoutTurnsOverride(turns)
+			return
+		}
+		SetToolAugment(nil)
+		SetToolResolve(nil)
+		SetFindingTrafficBindingEnabled(nil)
+		SetPromptOverride(nil)
+		SetWrapupOverride(nil)
+		SetWrapupMaxTurnsOverride(nil)
+		SetWrapupTaskTimeoutOverride(nil)
+		SetWrapupTaskTimeoutTurnsOverride(nil)
+	}
+
+	const rounds = 200
+	var wg sync.WaitGroup
+	for range 4 {
+		wg.Go(func() {
+			for range rounds {
+				out, _, cleanup := AugmentTools(context.Background(), "worker", nil)
+				cleanup()
+				if len(out) != 0 {
+					t.Errorf("AugmentTools(nil base) = %d tools, want 0", len(out))
+					return
+				}
+				if got := renderSystem("planner", "DEFAULT", PlannerVars{}); got != "DEFAULT" {
+					t.Errorf("renderSystem = %q, want the default", got)
+					return
+				}
+				if st := wrapupSettlementForTask("worker", nil, true); st.Prompt != WrapupDefault("worker") {
+					t.Errorf("settlement prompt = %q, want the default", st.Prompt)
+					return
+				}
+			}
+		})
+	}
+	wg.Go(func() {
+		for range rounds {
+			setAll(true)
+			setAll(false)
+		}
+	})
+	wg.Wait()
+}

agent/finding_recorder_test.go

@@ -51,9 +51,9 @@ func TestReportFindingOptionalTrafficWithoutCapture(t *testing.T) {
 }
 
 func TestReportFindingAtomicContract(t *testing.T) {
-	old := FindingTrafficBindingEnabled
-	FindingTrafficBindingEnabled = func() bool { return true }
-	t.Cleanup(func() { FindingTrafficBindingEnabled = old })
+	old := FindingTrafficBindingEnabled()
+	SetFindingTrafficBindingEnabled(func() bool { return true })
+	t.Cleanup(func() { SetFindingTrafficBindingEnabled(old) })
 	d := testDB(t)
 	defer d.Close()
 	task, err := d.CreateTask("report contract", "fixture", nil, 0, 0)

agent/finding_workflow.go

@@ -3,6 +3,7 @@ package agent
 import (
 	"encoding/json"
 	"fmt"
+	"sync"
 
 	"github.com/Autumn-27/artex/db"
 	actool "github.com/Autumn-27/norma/tool"
@@ -13,10 +14,29 @@ const findingIDGuidance = "\n\n**Finding ID conventions**: finding_id is the sta
 // The server supplies the persisted setting. A missing setting/host is off.
 // Consulted at assembly and again on writes so an already-running session
 // cannot keep binding after the user switches the feature off.
-var FindingTrafficBindingEnabled func() bool
+// Guarded by a lock for the same reason as the tool hooks.
+var (
+	findingTrafficBindingMu   sync.RWMutex
+	findingTrafficBindingHook func() bool
+)
+
+// SetFindingTrafficBindingEnabled installs (or, with nil, removes) the hook.
+func SetFindingTrafficBindingEnabled(f func() bool) {
+	findingTrafficBindingMu.Lock()
+	findingTrafficBindingHook = f
+	findingTrafficBindingMu.Unlock()
+}
+
+// FindingTrafficBindingEnabled returns the current hook, or nil when none is set.
+func FindingTrafficBindingEnabled() func() bool {
+	findingTrafficBindingMu.RLock()
+	defer findingTrafficBindingMu.RUnlock()
+	return findingTrafficBindingHook
+}
 
 func findingTrafficBindingEnabled() bool {
-	return FindingTrafficBindingEnabled != nil && FindingTrafficBindingEnabled()
+	f := FindingTrafficBindingEnabled()
+	return f != nil && f()
 }
 
 // Applied after ToolResolve: user descriptions and prompts remain intact, while

agent/finding_workflow_test.go

@@ -10,19 +10,23 @@ import (
 )
 
 func TestFindingWorkflowSharedAssemblyAndSwitch(t *testing.T) {
-	oldPolicy, oldResolve, oldAugment := FindingTrafficBindingEnabled, ToolResolve, ToolAugment
-	t.Cleanup(func() { FindingTrafficBindingEnabled, ToolResolve, ToolAugment = oldPolicy, oldResolve, oldAugment })
-	ToolAugment = nil
+	oldPolicy, oldResolve, oldAugment := FindingTrafficBindingEnabled(), ToolResolve(), ToolAugment()
+	t.Cleanup(func() {
+		SetFindingTrafficBindingEnabled(oldPolicy)
+		SetToolResolve(oldResolve)
+		SetToolAugment(oldAugment)
+	})
+	SetToolAugment(nil)
 	on := false
-	FindingTrafficBindingEnabled = func() bool { return on }
+	SetFindingTrafficBindingEnabled(func() bool { return on })
 	ts := NewToolSet(nil, "fixture")
-	ToolResolve = func(_ context.Context, _ string, base []actool.CoreTool) []actool.CoreTool {
+	SetToolResolve(func(_ context.Context, _ string, base []actool.CoreTool) []actool.CoreTool {
 		out := make([]actool.CoreTool, len(base))
 		for i, tool := range base {
 			out[i] = DecorateTool(tool, "CUSTOM DESCRIPTION", tool.InputSchema())
 		}
 		return out
-	}
+	})
 	for _, role := range []string{"worker", "planner", "mainagent", "auto", "pentest", "custom-agent"} {
 		for _, enabled := range []bool{false, true, false} {
 			on = enabled
@@ -59,7 +63,7 @@ func TestFindingWorkflowSharedAssemblyAndSwitch(t *testing.T) {
 		}
 	}
 	on = true
-	ToolResolve = func(context.Context, string, []actool.CoreTool) []actool.CoreTool { return nil }
+	SetToolResolve(func(context.Context, string, []actool.CoreTool) []actool.CoreTool { return nil })
 	out, def, cleanup := AugmentTools(t.Context(), "planner", []actool.CoreTool{ts.addFinding()})
 	defer cleanup()
 	if len(out) != 0 || def.FindingGuidance != "" {

agent/prompt.go

@@ -2,6 +2,7 @@ package agent
 
 import (
 	"bytes"
+	"sync"
 	"text/template"
 	"time"
 )
@@ -10,7 +11,25 @@ import (
 // key and whether one exists. The server wires it to the PG agent_prompts table.
 // When nil or no override exists, agents use their built-in default prompt — so
 // behavior is identical until a user edits a prompt in the UI.
-var PromptOverride func(agentKey string) (string, bool)
+// Guarded by a lock: server wiring can run while agents render prompts.
+var (
+	promptOverrideMu sync.RWMutex
+	promptOverride   func(agentKey string) (string, bool)
+)
+
+// SetPromptOverride installs (or, with nil, removes) the PromptOverride hook.
+func SetPromptOverride(f func(agentKey string) (string, bool)) {
+	promptOverrideMu.Lock()
+	promptOverride = f
+	promptOverrideMu.Unlock()
+}
+
+// PromptOverride returns the current hook, or nil when none is set.
+func PromptOverride() func(agentKey string) (string, bool) {
+	promptOverrideMu.RLock()
+	defer promptOverrideMu.RUnlock()
+	return promptOverride
+}
 
 // Prompt-variable structs — fields mirror each agent's catalog (docs §5a) so a
 // user template referencing a catalog variable renders; referencing anything else
@@ -38,8 +57,8 @@ func nowStr() string { return time.Now().Format("2006-01-02 15:04:05 MST") }
 // the DB body.
 func renderSystem(agentKey, def string, vars any) string {
 	tmpl := def
-	if PromptOverride != nil {
-		if t, ok := PromptOverride(agentKey); ok && t != "" {
+	if override := PromptOverride(); override != nil {
+		if t, ok := override(agentKey); ok && t != "" {
 			tmpl = t
 		}
 	}

agent/prompt_injection_seed_test.go

@@ -18,9 +18,9 @@ func TestPromptSeedsDoNotCarryInjectionBlock(t *testing.T) {
 // tail: the #49 block for the roles that read target output, the untrusted-data
 // rule for the planner and the cold-digest compactor.
 func TestInjectionTailSurvivesPromptOverride(t *testing.T) {
-	prev := PromptOverride
-	t.Cleanup(func() { PromptOverride = prev })
-	PromptOverride = func(string) (string, bool) { return "BARE BODY", true }
+	prev := PromptOverride()
+	t.Cleanup(func() { SetPromptOverride(prev) })
+	SetPromptOverride(func(string) (string, bool) { return "BARE BODY", true })
 
 	content := map[string]string{
 		"worker":    workerSystem("", "", "/data", "/run"),
@@ -64,8 +64,8 @@ func TestInjectionTailSurvivesPromptOverride(t *testing.T) {
 // A body that already carries the block (a DB row seeded before the move) does
 // not get it twice; the code defaults carry it exactly once.
 func TestInjectionTailNotDuplicated(t *testing.T) {
-	prev := PromptOverride
-	t.Cleanup(func() { PromptOverride = prev })
+	prev := PromptOverride()
+	t.Cleanup(func() { SetPromptOverride(prev) })
 
 	render := func() map[string]string {
 		return map[string]string{
@@ -78,16 +78,16 @@ func TestInjectionTailNotDuplicated(t *testing.T) {
 		}
 	}
 
-	PromptOverride = func(string) (string, bool) {
+	SetPromptOverride(func(string) (string, bool) {
 		return "LEGACY BODY\n\n" + untrustedContentRules + "\n\nMore rules.", true
-	}
+	})
 	for role, sys := range render() {
 		if n := strings.Count(sys, untrustedContentRules); n != 1 {
 			t.Errorf("legacy %s: untrusted-content block rendered %d times, want 1", role, n)
 		}
 	}
 
-	PromptOverride = nil
+	SetPromptOverride(nil)
 	for role, sys := range render() {
 		if n := strings.Count(sys, untrustedContentRules); n != 1 {
 			t.Errorf("default %s: untrusted-content block rendered %d times, want 1", role, n)

agent/prompt_now_test.go

@@ -10,15 +10,15 @@ import (
 // (chat) agent prompt referencing it renders the live server time each turn, rather
 // than failing template execution and falling back to DefaultAssistantPrompt.
 func TestChatNowVarRenders(t *testing.T) {
-	prev := PromptOverride
-	defer func() { PromptOverride = prev }()
+	prev := PromptOverride()
+	defer func() { SetPromptOverride(prev) }()
 
-	PromptOverride = func(key string) (string, bool) {
+	SetPromptOverride(func(key string) (string, bool) {
 		if key == "tec_benchmark" {
 			return "Current time: {{.Now}}", true
 		}
 		return "", false
-	}
+	})
 
 	out := chatSystem("tec_benchmark", "/app/data", "/tmp/x")
 	if !strings.Contains(out, "Current time: ") {
@@ -34,12 +34,12 @@ func TestChatNowVarRenders(t *testing.T) {
 // a custom prompt referencing it renders the server data root (s.m.dir), rather
 // than failing template execution and falling back to DefaultAssistantPrompt.
 func TestChatDataDirVarRenders(t *testing.T) {
-	prev := PromptOverride
-	defer func() { PromptOverride = prev }()
+	prev := PromptOverride()
+	defer func() { SetPromptOverride(prev) }()
 
-	PromptOverride = func(key string) (string, bool) {
+	SetPromptOverride(func(key string) (string, bool) {
 		return "Data root: {{.DataDir}}", true
-	}
+	})
 
 	out := chatSystem("tec_benchmark", "/app/data", "/tmp/x")
 	if !strings.Contains(out, "Data root: /app/data") {
@@ -50,12 +50,12 @@ func TestChatDataDirVarRenders(t *testing.T) {
 // TestChatUnknownVarFallsBack verifies an out-of-catalog {{.X}} still degrades
 // safely to the default assistant prompt (never a half-rendered prompt).
 func TestChatUnknownVarFallsBack(t *testing.T) {
-	prev := PromptOverride
-	defer func() { PromptOverride = prev }()
+	prev := PromptOverride()
+	defer func() { SetPromptOverride(prev) }()
 
-	PromptOverride = func(key string) (string, bool) {
+	SetPromptOverride(func(key string) (string, bool) {
 		return "References a nonexistent variable: {{.Bogus}}", true
-	}
+	})
 
 	out := chatSystem("whatever", "/app/data", "/tmp/x")
 	if strings.Contains(out, "References a nonexistent variable") {

agent/prompt_test.go

@@ -6,27 +6,27 @@ import (
 )
 
 func TestRenderSystemOverrideAndFallback(t *testing.T) {
-	t.Cleanup(func() { PromptOverride = nil })
+	t.Cleanup(func() { SetPromptOverride(nil) })
 
 	// no override → built-in default
-	PromptOverride = nil
+	SetPromptOverride(nil)
 	if got := renderSystem("planner", "DEFAULT", PlannerVars{Goal: "g"}); got != "DEFAULT" {
 		t.Fatalf("no override should give default, got %q", got)
 	}
 
 	// override → rendered with vars
-	PromptOverride = func(k string) (string, bool) {
+	SetPromptOverride(func(k string) (string, bool) {
 		if k == "planner" {
 			return "Goal:{{.Goal}} Scope:{{.Scope}}", true
 		}
 		return "", false
-	}
+	})
 	if got := renderSystem("planner", "DEFAULT", PlannerVars{Goal: "capture X", Scope: "*.x.com"}); got != "Goal:capture X Scope:*.x.com" {
 		t.Fatalf("override render: %q", got)
 	}
 
 	// override referencing a non-catalog var → execution error → fallback to default
-	PromptOverride = func(k string) (string, bool) { return "{{.NotInCatalog}}", true }
+	SetPromptOverride(func(k string) (string, bool) { return "{{.NotInCatalog}}", true })
 	if got := renderSystem("planner", "DEFAULT", PlannerVars{Goal: "x"}); got != "DEFAULT" {
 		t.Fatalf("bad var should fall back to default, got %q", got)
 	}
@@ -34,7 +34,7 @@ func TestRenderSystemOverrideAndFallback(t *testing.T) {
 	// full plannerSystem path: DB body [A] is honored, then the code-owned tail
 	// [C] (intermediate artifact output rules) is ALWAYS appended — editing the body
 	// can't drop it.
-	PromptOverride = func(k string) (string, bool) { return "PLANNER {{.Goal}}", true }
+	SetPromptOverride(func(k string) (string, bool) { return "PLANNER {{.Goal}}", true })
 	got := plannerSystem("capture X", "/data", "/data")
 	if !strings.HasPrefix(got, "PLANNER capture X") {
 		t.Fatalf("plannerSystem body not honored: %q", got)
@@ -48,9 +48,9 @@ func TestRenderSystemOverrideAndFallback(t *testing.T) {
 	// the traffic_* tools exist), [C] artifact spec always present. The trafficTool
 	// block is gated on the CA (arg 2), NOT on ProxyAddr — a global egress proxy
 	// with capture off routes traffic but records nothing.
-	PromptOverride = func(k string) (string, bool) {
+	SetPromptOverride(func(k string) (string, bool) {
 		return "{{if .ProxyAddr}}via proxy {{.ProxyAddr}}{{else}}manual{{end}}", true
-	}
+	})
 	recording := workerSystem("127.0.0.1:8080", "/ca.pem", "/data", "/data")
 	if !strings.HasPrefix(recording, "via proxy 127.0.0.1:8080") {
 		t.Fatalf("worker proxy branch body: %q", recording)

agent/provider.go

@@ -1,5 +1,5 @@
 // Package agent wires real LLM-driven planner and work agents (on top of the
-// agent-core SDK) to the dual SQLite graph. See the ARTEX architecture design doc
+// agent-core SDK) to the dual PostgreSQL graph. See the ARTEX architecture design doc
 // §4.3 (planner) and §4.4 (work agent).
 //
 // Provider configuration is read from the environment so the system runs with

agent/toolcatalog.go

@@ -3,6 +3,7 @@ package agent
 import (
 	"context"
 	"encoding/json"
+	"sync"
 
 	actool "github.com/Autumn-27/norma/tool"
 )
@@ -121,13 +122,34 @@ func BuiltinToolSeeds() []ToolSeed {
 	return out
 }
 
-// ToolResolve, if set, post-processes an agent's fully-assembled tool list against
+// ToolResolveFunc is the ToolResolve hook. If set, it post-processes an agent's
+// fully-assembled tool list against
 // the DB tools table: it drops tools not bound to this agent (or globally disabled)
 // and wraps the rest so the model sees the DB-overridden description/schema and
 // default inputs get injected. Tools with no matching DB row (MCP/skill/host tools
 // like traffic) pass through untouched. nil = tools unchanged. Wired in
 // server/assembly.go.
-var ToolResolve func(ctx context.Context, agentKey string, tools []actool.CoreTool) []actool.CoreTool
+type ToolResolveFunc func(ctx context.Context, agentKey string, tools []actool.CoreTool) []actool.CoreTool
+
+// Guarded like toolAugment: wiring can run while tasks assemble tools.
+var (
+	toolResolveMu sync.RWMutex
+	toolResolve   ToolResolveFunc
+)
+
+// SetToolResolve installs (or, with nil, removes) the ToolResolve hook.
+func SetToolResolve(f ToolResolveFunc) {
+	toolResolveMu.Lock()
+	toolResolve = f
+	toolResolveMu.Unlock()
+}
+
+// ToolResolve returns the current ToolResolve hook, or nil when none is set.
+func ToolResolve() ToolResolveFunc {
+	toolResolveMu.RLock()
+	defer toolResolveMu.RUnlock()
+	return toolResolve
+}
 
 // DecorateTool wraps t so Description()/InputSchema() report the DB overrides and
 // Call() injects scalar parameter defaults (from schema's "default" props) whenever

agent/toolrag_test.go

@@ -82,12 +82,17 @@ func TestToolRAGCoreKeptAndKRespected(t *testing.T) {
 // The projection runs after ToolResolve, so a tool the binding/enabled filter
 // dropped is never selected even when it is the best lexical match.
 func TestToolRAGNeverSelectsUnboundOrDisabled(t *testing.T) {
-	oldResolve, oldAugment, oldPolicy := ToolResolve, ToolAugment, FindingTrafficBindingEnabled
-	t.Cleanup(func() { ToolResolve, ToolAugment, FindingTrafficBindingEnabled = oldResolve, oldAugment, oldPolicy })
-	ToolAugment, FindingTrafficBindingEnabled = nil, nil
+	oldResolve, oldAugment, oldPolicy := ToolResolve(), ToolAugment(), FindingTrafficBindingEnabled()
+	t.Cleanup(func() {
+		SetToolResolve(oldResolve)
+		SetToolAugment(oldAugment)
+		SetFindingTrafficBindingEnabled(oldPolicy)
+	})
+	SetToolAugment(nil)
+	SetFindingTrafficBindingEnabled(nil)
 	t.Setenv(toolRAGEnv, "on")
 	t.Setenv(toolRAGTopKEnv, "2")
-	ToolResolve = func(_ context.Context, _ string, in []actool.CoreTool) []actool.CoreTool {
+	SetToolResolve(func(_ context.Context, _ string, in []actool.CoreTool) []actool.CoreTool {
 		var out []actool.CoreTool
 		for _, tool := range in {
 			if tool.Name() != "sql_injection_exploit" {
@@ -95,7 +100,7 @@ func TestToolRAGNeverSelectsUnboundOrDisabled(t *testing.T) {
 			}
 		}
 		return out
-	}
+	})
 	base := append(ragCatalog(25), ragTool("sql_injection_exploit", "Exploit SQL injection in web login form", "url"))
 	out, _, cleanup := AugmentTools(WithToolQuery(t.Context(), ragQuery), "worker", base)
 	defer cleanup()

agent/wrapup.go

@@ -2,6 +2,7 @@ package agent
 
 import (
 	"strings"
+	"sync"
 
 	"github.com/Autumn-27/norma/harness"
 )
@@ -17,15 +18,47 @@ import (
 // [prompt body] is editable; which tools are disabled and how many turns the
 // wrap-up itself gets are code-fixed policy.
 
-// WrapupOverride, if set, returns the stored wrap-up prompt for an agent key and
+// wrapupHooksMu guards the four wrap-up hooks in this file: server wiring can run
+// while agents build their settlement config on other goroutines.
+var wrapupHooksMu sync.RWMutex
+
+// wrapupOverride, if set, returns the stored wrap-up prompt for an agent key and
 // whether a non-empty one exists. Wired by the server to the agents table (like
 // PromptOverride for system prompts). nil / empty → the built-in default is used.
-var WrapupOverride func(agentKey string) (string, bool)
+var wrapupOverride func(agentKey string) (string, bool)
 
-// WrapupMaxTurnsOverride, if set, returns the admin-configured turn budget for the
+// SetWrapupOverride installs (or, with nil, removes) the WrapupOverride hook.
+func SetWrapupOverride(f func(agentKey string) (string, bool)) {
+	wrapupHooksMu.Lock()
+	wrapupOverride = f
+	wrapupHooksMu.Unlock()
+}
+
+// WrapupOverride returns the current hook, or nil when none is set.
+func WrapupOverride() func(agentKey string) (string, bool) {
+	wrapupHooksMu.RLock()
+	defer wrapupHooksMu.RUnlock()
+	return wrapupOverride
+}
+
+// wrapupMaxTurnsOverride, if set, returns the admin-configured turn budget for the
 // wrap-up phase of an agent and whether a positive one exists. Wired to the agents
 // table. nil / ≤0 → the built-in per-agent default (wrapupTurnDefaults) is used.
-var WrapupMaxTurnsOverride func(agentKey string) (int, bool)
+var wrapupMaxTurnsOverride func(agentKey string) (int, bool)
+
+// SetWrapupMaxTurnsOverride installs (or, with nil, removes) the WrapupMaxTurnsOverride hook.
+func SetWrapupMaxTurnsOverride(f func(agentKey string) (int, bool)) {
+	wrapupHooksMu.Lock()
+	wrapupMaxTurnsOverride = f
+	wrapupHooksMu.Unlock()
+}
+
+// WrapupMaxTurnsOverride returns the current hook, or nil when none is set.
+func WrapupMaxTurnsOverride() func(agentKey string) (int, bool) {
+	wrapupHooksMu.RLock()
+	defer wrapupHooksMu.RUnlock()
+	return wrapupMaxTurnsOverride
+}
 
 // Built-in default wrap-up prompts, keyed by agent key. worker reuses the
 // historically hardcoded settleWrapUpPrompt (defined in worker.go); planner and
@@ -75,8 +108,8 @@ func WrapupTurnsDefault(agentKey string) int {
 // resolveWrapup returns the effective wrap-up prompt: the DB override (if set and
 // non-empty) over the built-in default.
 func resolveWrapup(agentKey string) string {
-	if WrapupOverride != nil {
-		if t, ok := WrapupOverride(agentKey); ok && strings.TrimSpace(t) != "" {
+	if override := WrapupOverride(); override != nil {
+		if t, ok := override(agentKey); ok && strings.TrimSpace(t) != "" {
 			return t
 		}
 	}
@@ -86,8 +119,8 @@ func resolveWrapup(agentKey string) string {
 // resolveWrapupTurns returns the effective wrap-up turn budget: a positive DB
 // override over the built-in per-agent default.
 func resolveWrapupTurns(agentKey string) int {
-	if WrapupMaxTurnsOverride != nil {
-		if v, ok := WrapupMaxTurnsOverride(agentKey); ok && v > 0 {
+	if override := WrapupMaxTurnsOverride(); override != nil {
+		if v, ok := override(agentKey); ok && v > 0 {
 			return v
 		}
 	}
@@ -117,11 +150,40 @@ func wrapupSettlement(agentKey string, disabledTools []string) *harness.Settleme
 // WrapupTaskTimeoutOverride / …TurnsOverride: DB overrides for the task-timeout
 // wrap-up prompt and turns (wired to agents.task_timeout_wrapup_prompt /
 // _max_turns, worker/planner only).
+// Guarded by wrapupHooksMu, like the per-run hooks above.
 var (
-	WrapupTaskTimeoutOverride      func(agentKey string) (string, bool)
-	WrapupTaskTimeoutTurnsOverride func(agentKey string) (int, bool)
+	wrapupTaskTimeoutOverride      func(agentKey string) (string, bool)
+	wrapupTaskTimeoutTurnsOverride func(agentKey string) (int, bool)
 )
 
+// SetWrapupTaskTimeoutOverride installs (or, with nil, removes) the hook.
+func SetWrapupTaskTimeoutOverride(f func(agentKey string) (string, bool)) {
+	wrapupHooksMu.Lock()
+	wrapupTaskTimeoutOverride = f
+	wrapupHooksMu.Unlock()
+}
+
+// WrapupTaskTimeoutOverride returns the current hook, or nil when none is set.
+func WrapupTaskTimeoutOverride() func(agentKey string) (string, bool) {
+	wrapupHooksMu.RLock()
+	defer wrapupHooksMu.RUnlock()
+	return wrapupTaskTimeoutOverride
+}
+
+// SetWrapupTaskTimeoutTurnsOverride installs (or, with nil, removes) the hook.
+func SetWrapupTaskTimeoutTurnsOverride(f func(agentKey string) (int, bool)) {
+	wrapupHooksMu.Lock()
+	wrapupTaskTimeoutTurnsOverride = f
+	wrapupHooksMu.Unlock()
+}
+
+// WrapupTaskTimeoutTurnsOverride returns the current hook, or nil when none is set.
+func WrapupTaskTimeoutTurnsOverride() func(agentKey string) (int, bool) {
+	wrapupHooksMu.RLock()
+	defer wrapupHooksMu.RUnlock()
+	return wrapupTaskTimeoutTurnsOverride
+}
+
 var taskTimeoutWrapupDefaults = map[string]string{
 	"worker":  workerTaskTimeoutDefault,
 	"planner": plannerTaskTimeoutDefault,
@@ -141,8 +203,8 @@ func TaskTimeoutWrapupDefault(agentKey string) string {
 // string means this agent has no task-timeout prompt (not worker/planner) — the
 // caller should then fall back to the per-run prompt.
 func resolveTaskTimeoutWrapup(agentKey string) string {
-	if WrapupTaskTimeoutOverride != nil {
-		if t, ok := WrapupTaskTimeoutOverride(agentKey); ok && strings.TrimSpace(t) != "" {
+	if override := WrapupTaskTimeoutOverride(); override != nil {
+		if t, ok := override(agentKey); ok && strings.TrimSpace(t) != "" {
 			return t
 		}
 	}
@@ -150,8 +212,8 @@ func resolveTaskTimeoutWrapup(agentKey string) string {
 }
 
 func resolveTaskTimeoutTurns(agentKey string) int {
-	if WrapupTaskTimeoutTurnsOverride != nil {
-		if v, ok := WrapupTaskTimeoutTurnsOverride(agentKey); ok && v > 0 {
+	if override := WrapupTaskTimeoutTurnsOverride(); override != nil {
+		if v, ok := override(agentKey); ok && v > 0 {
 			return v
 		}
 	}

build.sh

@@ -8,7 +8,7 @@
 #   ARTEX_TARGET_OS=linux             One target OS in single-target mode.
 #   ARTEX_TARGET_ARCH=amd64           One target arch in single-target mode.
 #   ARTEX_TARGETS=linux/amd64,...     Comma-separated targets for multi-target mode.
-#   ARTEX_BUILD_VERSION=v0.3.3        Version embedded in the binary and archive name.
+#   ARTEX_BUILD_VERSION=vX.Y.Z        Version embedded in the binary and archive name.
 #   ARTEX_OUTPUT=/path/to/artex       Explicit binary path in single-target mode.
 #   ARTEX_OUTPUT_DIR=dist             Directory for default binary paths.
 #   ARTEX_PACKAGE=1                   Create a zip archive for each target.
@@ -97,7 +97,7 @@ if [ -z "${ARTEX_BUILD_VERSION:-}" ]; then
     ARTEX_BUILD_VERSION="dev"
   fi
 fi
-# Release tags are commonly passed as v0.3.3; keep the binary version consistent.
+# Release tags are commonly passed with a v prefix; keep the binary version consistent.
 ARTEX_BUILD_VERSION="${ARTEX_BUILD_VERSION#v}"
 ARTEX_OUTPUT_DIR="${ARTEX_OUTPUT_DIR:-dist}"
 ARTEX_PACKAGE_DIR="${ARTEX_PACKAGE_DIR:-$ARTEX_OUTPUT_DIR}"

cmd/artex/main.go

@@ -1,4 +1,4 @@
-// Command artex runs the ARTEX backend: the dual SQLite graph stores,
+// Command artex runs the ARTEX backend: the dual PostgreSQL graph stores,
 // the event-driven exploration engine, and the JSON HTTP API consumed by the
 // shadcn/ui frontend.
 package main
@@ -50,7 +50,7 @@ func main() {
 func run() int {
 	var (
 		addr    = flag.String("addr", "127.0.0.1:8787", "HTTP listen address")
-		dataDir = flag.String("data", filepath.Join(config.BaseDir(), "data"), "data directory for SQLite stores (default: data/ next to the executable)")
+		dataDir = flag.String("data", filepath.Join(config.BaseDir(), "data"), "runtime data directory: traffic index, task files, transcripts (default: data/ next to the executable)")
 		proxy   = flag.String("proxy", "127.0.0.1:8788", "traffic recording proxy address (empty to disable)")
 	)
 	flag.Parse()

db/coverage_graph_large_test.go

@@ -0,0 +1,198 @@
+package db
+
+import (
+	"fmt"
+	"strings"
+	"testing"
+)
+
+// largeCoverageFixture is a task scoped by 800 subdomains spread over 200 root
+// domains and 20 companies, with 1,000 services, 1,200 endpoints and 2,000
+// anchored facts. Every tenth root has no asset row, so the graph needs both
+// real and synthetic ("r:<domain>") connector roots.
+type largeCoverageFixture struct {
+	taskID, expID int64
+	suffix        string
+}
+
+const (
+	lcRoots     = 200
+	lcCompanies = 20
+	lcSubs      = 800
+	lcServices  = 1000
+	lcEndpoints = 1200
+	lcFacts     = 2000
+)
+
+func seedLargeCoverageFixture(tb testing.TB, d *DB) largeCoverageFixture {
+	tb.Helper()
+	task, err := d.CreateTask("large coverage graph", "large coverage graph", nil, 0, 0)
+	if err != nil {
+		tb.Fatal(err)
+	}
+	f := largeCoverageFixture{taskID: task.ID, expID: task.ExplorationID, suffix: fmt.Sprintf("lc%d", task.ID)}
+	tb.Cleanup(func() {
+		_, _ = d.Exec(`DELETE FROM explorations WHERE id=$1`, f.expID)
+		_ = d.DeleteTask(f.taskID)
+		_, _ = d.Exec(`DELETE FROM assets WHERE root_domain LIKE '%-'||$1||'.cov.test'`, f.suffix)
+		_, _ = d.Exec(`DELETE FROM companies WHERE nkey LIKE 'lcco-'||$1||'-%'`, f.suffix)
+	})
+	exec := func(q string, args ...any) {
+		tb.Helper()
+		if _, err := d.Exec(q, args...); err != nil {
+			tb.Fatalf("%v\n%s", err, q)
+		}
+	}
+	// root g: r<g>-<suffix>.cov.test, company 1+(g-1)%lcCompanies.
+	// subdomain i: s<i>.<root 1+(i-1)%lcRoots>.
+	exec(`INSERT INTO companies(name,nkey)
+SELECT 'large co '||g||' '||$1, 'lcco-'||$1||'-'||g FROM generate_series(1,$2) g`, f.suffix, lcCompanies)
+	exec(`INSERT INTO assets(type,domain,root_domain,company_id)
+SELECT 'root_domain', 'r'||g||'-'||$1||'.cov.test', 'r'||g||'-'||$1||'.cov.test',
+       (SELECT id FROM companies WHERE nkey='lcco-'||$1||'-'||(1+(g-1)%$3))
+FROM generate_series(1,$2) g WHERE g%10<>0`, f.suffix, lcRoots, lcCompanies)
+	exec(`INSERT INTO assets(type,domain,root_domain,company_id)
+SELECT 'subdomain', 's'||i||'.r'||r||'-'||$1||'.cov.test', 'r'||r||'-'||$1||'.cov.test',
+       (SELECT id FROM companies WHERE nkey='lcco-'||$1||'-'||(1+(r-1)%$4))
+FROM generate_series(1,$3) i, LATERAL (SELECT 1+(i-1)%$2 AS r) x`, f.suffix, lcRoots, lcSubs, lcCompanies)
+	// service j hangs off subdomain 1+(j-1)%lcSubs: port 443 for the first
+	// lcSubs services, 8443 for the rest.
+	exec(`INSERT INTO assets(type,service_type,url,domain,root_domain,port,company_id)
+SELECT 'service','http', 'https://'||s.domain||':'||p||'/', s.domain, s.root_domain, p, s.company_id
+FROM generate_series(1,$2) j
+CROSS JOIN LATERAL (SELECT CASE WHEN j<=$3 THEN 443 ELSE 8443 END AS p) port
+JOIN assets s ON s.type='subdomain' AND s.root_domain LIKE '%-'||$1||'.cov.test'
+ AND s.domain LIKE 's'||(1+(j-1)%$3)||'.%'`, f.suffix, lcServices, lcSubs)
+	exec(`INSERT INTO assets(type,url,method,domain,root_domain,port,company_id)
+SELECT 'endpoint', 'https://'||s.domain||'/p/'||k, 'GET', s.domain, s.root_domain, 443, s.company_id
+FROM generate_series(1,$2) k
+JOIN assets s ON s.type='subdomain' AND s.root_domain LIKE '%-'||$1||'.cov.test'
+ AND s.domain LIKE 's'||(1+(k-1)%$3)||'.%'`, f.suffix, lcEndpoints, lcSubs)
+	exec(`INSERT INTO task_scope(task_id,kind,domain,source)
+SELECT $1,'subdomain',domain,'manual' FROM assets
+WHERE type='subdomain' AND root_domain LIKE '%-'||$2||'.cov.test'`, f.taskID, f.suffix)
+	exec(`INSERT INTO exploration_nodes(exploration_id,kind,state,payload)
+SELECT $1,'fact','confirmed',jsonb_build_object('summary','large coverage fact '||g) FROM generate_series(1,$2) g`, f.expID, lcFacts)
+	exec(`WITH fn AS (
+  SELECT id, row_number() OVER (ORDER BY id) rn FROM exploration_nodes
+  WHERE exploration_id=$1 AND kind='fact' AND payload->>'summary' LIKE 'large coverage fact %'),
+an AS (
+  SELECT id, row_number() OVER (ORDER BY id) rn FROM assets
+  WHERE type<>'root_domain' AND root_domain LIKE '%-'||$2||'.cov.test')
+INSERT INTO exploration_anchors(node_id,asset_id) SELECT fn.id, an.id FROM fn JOIN an USING (rn)`, f.expID, f.suffix)
+	exec(`ANALYZE assets, task_scope, exploration_nodes, exploration_anchors, companies`)
+	return f
+}
+
+func TestBuildCoverageGraphLargeInvariants(t *testing.T) {
+	d, err := Open(testDSN(t))
+	if err != nil {
+		t.Skipf("postgres unavailable (%v) - skipping", err)
+	}
+	t.Cleanup(func() { d.Close() })
+	f := seedLargeCoverageFixture(t, d)
+
+	g, err := d.Assets().BuildCoverageGraph(f.taskID, f.expID)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	const (
+		syntheticRoots = lcRoots / 10
+		realRoots      = lcRoots - syntheticRoots
+		inScope        = lcSubs + lcServices + lcEndpoints
+		wantNodes      = inScope + lcRoots + lcCompanies
+		// subdomain→root, service→subdomain, endpoint→service (port 443), and
+		// real root→company; a synthetic root has no company.
+		wantEdges = lcSubs + lcServices + lcEndpoints + realRoots
+	)
+	if len(g.Nodes) != wantNodes || len(g.Edges) != wantEdges {
+		t.Fatalf("graph size: nodes=%d edges=%d, want %d/%d", len(g.Nodes), len(g.Edges), wantNodes, wantEdges)
+	}
+
+	byKey := make(map[string]CoverageGraphNode, len(g.Nodes))
+	kinds := map[string]int{}
+	var tested, scoped, synthetic, realConnector int
+	for _, n := range g.Nodes {
+		if _, dup := byKey[n.Key]; dup {
+			t.Fatalf("duplicate node key %q", n.Key)
+		}
+		byKey[n.Key] = n
+		kinds[n.Kind]++
+		if n.Tested {
+			tested++
+		}
+		if n.InScope {
+			scoped++
+		}
+		switch {
+		case strings.HasPrefix(n.Key, "r:"):
+			synthetic++
+			if n.Kind != "root_domain" || n.InScope || n.AssetID != 0 || n.Key != "r:"+n.Domain {
+				t.Fatalf("synthetic root: %+v", n)
+			}
+		case n.Kind == "root_domain":
+			realConnector++
+			if n.InScope || n.AssetID == 0 || n.CompanyID == 0 {
+				t.Fatalf("connector root: %+v", n)
+			}
+		case n.Kind == "company":
+			if n.InScope || n.Label == "" || n.Key != companyKey(n.CompanyID) {
+				t.Fatalf("company node: %+v", n)
+			}
+		}
+	}
+	if kinds["subdomain"] != lcSubs || kinds["service"] != lcServices || kinds["endpoint"] != lcEndpoints ||
+		kinds["root_domain"] != lcRoots || kinds["company"] != lcCompanies {
+		t.Fatalf("node kinds: %v", kinds)
+	}
+	if synthetic != syntheticRoots || realConnector != realRoots {
+		t.Fatalf("connector roots: synthetic=%d real=%d, want %d/%d", synthetic, realConnector, syntheticRoots, realRoots)
+	}
+	if scoped != inScope || tested != lcFacts {
+		t.Fatalf("in_scope=%d tested=%d, want %d/%d", scoped, tested, inScope, lcFacts)
+	}
+
+	seenEdge := map[CoverageGraphEdge]bool{}
+	for _, e := range g.Edges {
+		src, okSrc := byKey[e.Src]
+		dst, okDst := byKey[e.Dst]
+		if !okSrc || !okDst || e.Src == e.Dst {
+			t.Fatalf("edge %+v points to a missing node", e)
+		}
+		if seenEdge[e] {
+			t.Fatalf("duplicate edge %+v", e)
+		}
+		seenEdge[e] = true
+		want := map[string]string{"subdomain": "root_domain", "service": "subdomain", "endpoint": "service", "root_domain": "company"}[src.Kind]
+		if dst.Kind != want {
+			t.Fatalf("edge %s(%s) -> %s(%s), want parent kind %s", e.Src, src.Kind, e.Dst, dst.Kind, want)
+		}
+	}
+}
+
+// BenchmarkBuildCoverageGraphLarge locks in the cost of the coverage graph on
+// the large fixture (statement count and query plan). No time assertion.
+func BenchmarkBuildCoverageGraphLarge(b *testing.B) {
+	dsn, _, err := DSN()
+	if err != nil {
+		b.Skipf("no database config (%v) - skipping", err)
+	}
+	d, err := Open(dsn)
+	if err != nil {
+		b.Skipf("postgres unavailable (%v) - skipping", err)
+	}
+	b.Cleanup(func() { d.Close() })
+	f := seedLargeCoverageFixture(b, d)
+	store := d.Assets()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		g, err := store.BuildCoverageGraph(f.taskID, f.expID)
+		if err != nil {
+			b.Fatal(err)
+		}
+		if len(g.Nodes) == 0 {
+			b.Fatal("empty graph")
+		}
+	}
+}

db/migrate_test.go

@@ -119,8 +119,8 @@ func readApplied(t *testing.T, d *DB) []appliedMigration {
 	return out
 }
 
-// assertEmbeddedApplied checks that both LLM tables exist and that 0001 and
-// 0002 are recorded with the SHA-256 of their embedded files.
+// assertEmbeddedApplied checks that both LLM tables exist and that every
+// embedded migration is recorded with the SHA-256 of its file.
 func assertEmbeddedApplied(t *testing.T, d *DB) []appliedMigration {
 	t.Helper()
 	for _, table := range []string{"llm_records", "llm_usage"} {
@@ -136,9 +136,9 @@ func assertEmbeddedApplied(t *testing.T, d *DB) []appliedMigration {
 	want := []struct {
 		version int
 		name    string
-	}{{1, llmRecordsMigration}, {2, llmUsageMigration}}
+	}{{1, llmRecordsMigration}, {2, llmUsageMigration}, {3, "0003_task_scope_icp_index.sql"}}
 	if len(applied) != len(want) {
-		t.Fatalf("schema_migrations = %+v, want versions 1 and 2", applied)
+		t.Fatalf("schema_migrations = %+v, want versions 1 to 3", applied)
 	}
 	for i, w := range want {
 		content, err := fs.ReadFile(migrationsFS(), w.name)
@@ -301,7 +301,7 @@ func TestMigrationsFailClosed(t *testing.T) {
 	}{
 		{"checksum changed", withEmbedded(t, fstest.MapFS{"0003_probe.sql": {Data: append([]byte("-- edited\n"), probeMigration.Data...)}}),
 			[]string{"0003", "0003_probe.sql", "checksum"}},
-		{"version missing from binary", migrationsFS(),
+		{"version missing from binary", withEmbedded(t, fstest.MapFS{}),
 			[]string{"0003", "0003_probe.sql", "missing from this binary"}},
 		{"name changed", withEmbedded(t, fstest.MapFS{"0003_renamed.sql": probeMigration}),
 			[]string{"0003", "0003_probe.sql", "0003_renamed.sql"}},

db/migrations/0003_task_scope_icp_index.sql

@@ -0,0 +1,9 @@
+-- The coverage target CTE (contextCoverageCTE / covTargetCTE / scopeTargetCTE)
+-- joins assets to task_scope on an OR of per-kind predicates. PostgreSQL plans it
+-- as one BitmapOr probe of task_scope per asset. Every branch had an index except
+-- kind='icp', which fell back to uq_task_scope_v2 with only "kind = 'icp'" as the
+-- index condition (task_id is the leading column), so each probe walked the
+-- whole unique index: about 70% of the buffer hits of the coverage-graph query on
+-- a 3,000-asset task scoped by 800 subdomains. This partial index makes the icp
+-- probe an equality lookup on value.
+CREATE INDEX IF NOT EXISTS idx_ts_icp ON task_scope(value) WHERE kind = 'icp';

db/task_scope.go

@@ -4,6 +4,7 @@ import (
 	"database/sql"
 	"fmt"
 	"net"
+	"sort"
 	"strconv"
 	"strings"
 )
@@ -534,16 +535,44 @@ ORDER BY a.id`, taskID)
 			}
 		}
 	}
+	// One query for every missing root instead of one per root.
+	roots := make([]string, 0, len(missingRoots))
 	for root := range missingRoots {
-		var id, companyID int64
-		err := s.db.QueryRow(`SELECT id, COALESCE(company_id,0) FROM assets
-WHERE type='root_domain' AND domain=$1 LIMIT 1`, root).Scan(&id, &companyID)
+		roots = append(roots, root)
+	}
+	sort.Strings(roots)
+	type rootRow struct{ id, companyID int64 }
+	rootRows := map[string]rootRow{}
+	if len(roots) > 0 {
+		rrows, err := s.db.Query(`SELECT domain, id, COALESCE(company_id,0) FROM assets
+WHERE type='root_domain' AND domain=ANY($1::text[]) ORDER BY id`, roots)
+		if err != nil {
+			return nil, err
+		}
+		for rrows.Next() {
+			var domain string
+			var r rootRow
+			if err := rrows.Scan(&domain, &r.id, &r.companyID); err != nil {
+				rrows.Close()
+				return nil, err
+			}
+			if _, ok := rootRows[domain]; !ok {
+				rootRows[domain] = r
+			}
+		}
+		err = rrows.Err()
+		rrows.Close()
+		if err != nil {
+			return nil, err
+		}
+	}
+	for _, root := range roots {
 		var node CoverageGraphNode
-		if err == nil && id > 0 {
-			node = CoverageGraphNode{Key: assetKey(id), Kind: "root_domain", AssetID: id,
-				CompanyID: companyID, Domain: root, Label: root}
-			if companyID > 0 {
-				companyIDs[companyID] = true
+		if r, ok := rootRows[root]; ok && r.id > 0 {
+			node = CoverageGraphNode{Key: assetKey(r.id), Kind: "root_domain", AssetID: r.id,
+				CompanyID: r.companyID, Domain: root, Label: root}
+			if r.companyID > 0 {
+				companyIDs[r.companyID] = true
 			}
 		} else {
 			node = CoverageGraphNode{Key: "r:" + root, Kind: "root_domain", Domain: root, Label: root}
@@ -552,18 +581,34 @@ WHERE type='root_domain' AND domain=$1 LIMIT 1`, root).Scan(&id, &companyID)
 		rootByDomain[root] = node.Key
 	}
 
-	// Company nodes for every referenced company id — always gray context.
+	// Company nodes for every referenced company id — always gray context. One
+	// query for all of them; an id with no company row gets no node.
+	ids := make([]int64, 0, len(companyIDs))
 	for id := range companyIDs {
-		key := companyKey(id)
-		if _, ok := byKey[key]; ok {
-			continue
+		if _, ok := byKey[companyKey(id)]; !ok {
+			ids = append(ids, id)
 		}
-		var name string
-		if err := s.db.QueryRow(`SELECT name FROM companies WHERE id=$1`, id).Scan(&name); err != nil {
-			continue
+	}
+	if len(ids) > 0 {
+		crows, err := s.db.Query(`SELECT id, name FROM companies WHERE id=ANY($1::bigint[]) ORDER BY id`, ids)
+		if err != nil {
+			return nil, err
+		}
+		for crows.Next() {
+			var id int64
+			var name string
+			if err := crows.Scan(&id, &name); err != nil {
+				crows.Close()
+				return nil, err
+			}
+			add(CoverageGraphNode{Key: companyKey(id), Kind: "company", CompanyID: id,
+				Label: name, AssetID: 0})
+		}
+		err = crows.Err()
+		crows.Close()
+		if err != nil {
+			return nil, err
 		}
-		add(CoverageGraphNode{Key: key, Kind: "company", CompanyID: id,
-			Label: name, AssetID: 0})
 	}
 
 	// Derived containment edges (only when the parent node exists).

docker-compose.yml

@@ -54,10 +54,10 @@ services:
       - "${ARTEX_BIND_ADDR:-127.0.0.1}:8787:8787"
       - "127.0.0.1:8788:8788"
     volumes:
-      # Bind the data directory (SQLite, task files, etc.) to data/ in the project root,
+      # Bind the runtime data directory (traffic index, task files, transcripts, etc.) to data/ in the project root,
       # so it is easy to inspect/back up on the host and survives container rebuilds.
       - ./data:/app/data
-      # JWT signing key (jwt.key), kept out of data/, which the file manager browses.
+      # JWT signing key and secret key (jwt.key, secret.key), kept out of data/, which the file manager browses.
       # Persisting it keeps users signed in across container rebuilds.
       - ./keys:/app/keys
       # Mount skills/ from the project root into the container (overriding the image's built-in /app/skills);

server/assembly.go

@@ -29,7 +29,7 @@ const mcpUntrustedNote = "\nOutput of this tool may contain attacker-controlled
 // capture is on) to add to EVERY agent's base list — the DB tools table then
 // filters them per-agent binding. Empty/nil → no host tools this run (capture off).
 func wireAgentAugment(pg *db.DB, skillDir string, hostTools func() ([]actool.CoreTool, map[string][]string)) {
-	agent.ToolAugment = func(ctx context.Context, agentKey string) ([]actool.CoreTool, agent.DeferredInfo, func()) {
+	agent.SetToolAugment(func(ctx context.Context, agentKey string) ([]actool.CoreTool, agent.DeferredInfo, func()) {
 		a, err := pg.GetAgentByKey(agentKey)
 		if err != nil || a == nil {
 			return nil, agent.DeferredInfo{}, nil
@@ -188,7 +188,7 @@ func wireAgentAugment(pg *db.DB, skillDir string, hostTools func() ([]actool.Cor
 			UnlockSkill: unlockSkill,
 		}
 		return extra, def, cleanup
-	}
+	})
 }
 
 func idSet(ids []int64) map[int64]bool {
@@ -222,7 +222,7 @@ func seedPrompts(pg *db.DB) {
 // flag and, if kept, wrapped so the model sees the DB-overridden description/schema
 // and default params get injected. MCP/skill/host tools have no row and pass through.
 func wireTools(pg *db.DB, domainReg map[string]actool.CoreTool) {
-	agent.FindingTrafficBindingEnabled = func() bool { return pg.GetBool(settingAgentTrafficBinding, false) }
+	agent.SetFindingTrafficBindingEnabled(func() bool { return pg.GetBool(settingAgentTrafficBinding, false) })
 	// Seed the built-in domain tools (first-insert only; DO NOTHING preserves edits).
 	// No startup prune: rows we didn't seed are left alone so future user-defined
 	// custom tools (system=false, added via the UI) survive restarts.
@@ -248,7 +248,7 @@ func wireTools(pg *db.DB, domainReg map[string]actool.CoreTool) {
 	// interactive_shell is on, so Bash points at shell_open for interactive programs
 	// without ever referencing a tool that isn't injected (§14.1/§14.2).
 	const bashInteractiveShellNote = "\n\nPrograms that need [interactive input] (msfconsole / interactive ssh login / REPLs like mysql, psql, python / password or yes/no prompts / nc reverse shells) must not use Bash (it has no stdin and would hang); open an interactive session with shell_open instead (and shell_close when done). One-shot, non-interactive commands still use Bash."
-	agent.ToolResolve = func(ctx context.Context, agentKey string, tools []actool.CoreTool) []actool.CoreTool {
+	agent.SetToolResolve(func(ctx context.Context, agentKey string, tools []actool.CoreTool) []actool.CoreTool {
 		rows, err := pg.ListTools()
 		if err != nil {
 			log.Printf("[tools] failed to read tools table, passing through with code defaults: %v", err)
@@ -333,7 +333,7 @@ func wireTools(pg *db.DB, domainReg map[string]actool.CoreTool) {
 			}
 		}
 		return out
-	}
+	})
 }
 
 func contains(ss []string, v string) bool {

server/assembly_test.go

@@ -49,7 +49,7 @@ func TestAssembleVisibleSkill(t *testing.T) {
 	}
 
 	wireAgentAugment(pg, skillDir, nil)
-	t.Cleanup(func() { agent.ToolAugment = nil })
+	t.Cleanup(func() { agent.SetToolAugment(nil) })
 
 	ag, _ := pg.GetAgentByKey("planner")
 	if ag == nil {
@@ -65,7 +65,7 @@ func TestAssembleVisibleSkill(t *testing.T) {
 	t.Cleanup(func() { _ = pg.SetAgentSkillVisibility(ag.ID, orig) })
 
 	// before: skill not visible → no Skill meta-tool
-	extra, _, cleanup := agent.ToolAugment(context.Background(), "planner")
+	extra, _, cleanup := agent.ToolAugment()(context.Background(), "planner")
 	cleanup()
 	if hasSkillTool(extra) {
 		t.Fatalf("expected no Skill meta-tool before the skill is made visible")
@@ -78,7 +78,7 @@ func TestAssembleVisibleSkill(t *testing.T) {
 	t.Cleanup(func() { _ = pg.ToggleSkillVisibility(ag.ID, skillName, false) })
 
 	// after: the Skill meta-tool is packed in
-	extra, _, cleanup = agent.ToolAugment(context.Background(), "planner")
+	extra, _, cleanup = agent.ToolAugment()(context.Background(), "planner")
 	defer cleanup()
 	if !hasSkillTool(extra) {
 		t.Fatalf("expected the Skill meta-tool after making the skill visible")

server/chat_llm_resolve_test.go

@@ -18,7 +18,9 @@ func TestChatUnavailableReasonDistinguishesStates(t *testing.T) {
 	}
 	defer m.Close()
 	td := t.TempDir()
-	s := New(context.Background(), m, td, td, td)
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, td, td, td)
+	defer stopTestServer(t, s, cancel)
 
 	// Start from a clean profile table; other tests in the shared DB may have left rows.
 	existing, _ := m.pg.ListProfiles()
@@ -68,7 +70,9 @@ func TestResolveChatAgentHonoursConversationProfile(t *testing.T) {
 	}
 	defer m.Close()
 	td := t.TempDir()
-	s := New(context.Background(), m, td, td, td)
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, td, td, td)
+	defer stopTestServer(t, s, cancel)
 
 	// Force the global fallback to nil so a non-nil result can ONLY come from the
 	// conversation's own profile — this is exactly the situation the user hit

server/core_test.go

@@ -24,7 +24,9 @@ func TestCoreTaskLifecyclePG(t *testing.T) {
 	}
 	defer m.Close()
 	td := t.TempDir()
-	s := New(context.Background(), m, td, td, td)
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, td, td, td)
+	defer stopTestServer(t, s, cancel)
 	h := s.Handler()
 	tok, err := signJWT(s.jwtKey)
 	if err != nil {

server/fact_source_schema_test.go

@@ -24,7 +24,7 @@ func TestRecordFactSourceSchemaUpgrade(t *testing.T) {
 	ctx, cancel := context.WithCancel(context.Background())
 	cancel()
 	s := New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir())
-	t.Cleanup(func() { agent.ToolResolve = nil })
+	t.Cleanup(func() { agent.SetToolResolve(nil) })
 	pg := m.pg
 
 	old, err := pg.GetTool("record_fact")
@@ -96,7 +96,7 @@ func TestRecordFactSourceSchemaUpgrade(t *testing.T) {
 // serves it to the worker.
 func resolvedRecordFactProps(t *testing.T) map[string]any {
 	t.Helper()
-	tools := agent.ToolResolve(context.Background(), "worker", agent.NewToolSet(nil, "").WorkerTools())
+	tools := agent.ToolResolve()(context.Background(), "worker", agent.NewToolSet(nil, "").WorkerTools())
 	for _, tl := range tools {
 		if tl.Name() == "record_fact" {
 			props, _ := tl.InputSchema()["properties"].(map[string]any)

server/finding_retests_test.go

@@ -55,16 +55,18 @@ func newRetestServer(t *testing.T) (*Server, int64) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	oldAugment, oldResolve, oldPrompt := agent.ToolAugment, agent.ToolResolve, agent.PromptOverride
-	agent.ToolAugment = func(context.Context, string) ([]actool.CoreTool, agent.DeferredInfo, func()) {
+	oldAugment, oldResolve, oldPrompt := agent.ToolAugment(), agent.ToolResolve(), agent.PromptOverride()
+	agent.SetToolAugment(func(context.Context, string) ([]actool.CoreTool, agent.DeferredInfo, func()) {
 		return s.findingRetestTools(), agent.DeferredInfo{}, func() {}
-	}
-	agent.ToolResolve = nil
-	agent.PromptOverride = func(string) (string, bool) { return agent.RetesterDefaultPrompt, true }
+	})
+	agent.SetToolResolve(nil)
+	agent.SetPromptOverride(func(string) (string, bool) { return agent.RetesterDefaultPrompt, true })
 	t.Cleanup(func() {
 		cancel()
 		waitRetestIdle(t, s)
-		agent.ToolAugment, agent.ToolResolve, agent.PromptOverride = oldAugment, oldResolve, oldPrompt
+		agent.SetToolAugment(oldAugment)
+		agent.SetToolResolve(oldResolve)
+		agent.SetPromptOverride(oldPrompt)
 		_, _ = pg.Exec(`DELETE FROM conversations WHERE id IN (SELECT conversation_id FROM finding_retests WHERE finding_id=$1)`, fid)
 		_, _ = pg.DeleteFinding(fid)
 		pg.Close()

server/inheritance_api_test.go

@@ -67,7 +67,9 @@ func TestInheritedActivityDetailAndRelationDeletion(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	s := New(context.Background(), m, t.TempDir(), t.TempDir(), t.TempDir())
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir())
+	defer stopTestServer(t, s, cancel)
 	token, err := signJWT(s.jwtKey)
 	if err != nil {
 		t.Fatal(err)

server/lessons_test.go

@@ -50,7 +50,9 @@ SELECT id,'completed','fixed','{}'::jsonb FROM findings WHERE task_id=$1 AND nam
 		t.Fatal(err)
 	}
 
-	s := New(context.Background(), m, t.TempDir(), t.TempDir(), t.TempDir())
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir())
+	defer stopTestServer(t, s, cancel)
 	token, err := signJWT(s.jwtKey)
 	if err != nil {
 		t.Fatal(err)
@@ -144,7 +146,9 @@ VALUES ($1,'xss','Reflected XSS','reflected in search','high','confirmed')`, tas
 		t.Fatal(err)
 	}
 
-	s := New(context.Background(), m, t.TempDir(), t.TempDir(), t.TempDir())
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir())
+	defer stopTestServer(t, s, cancel)
 	token, err := signJWT(s.jwtKey)
 	if err != nil {
 		t.Fatal(err)

server/mgmt_test.go

@@ -18,8 +18,14 @@ func TestMgmtAPI(t *testing.T) {
 	if m.pg == nil {
 		t.Skip("postgres unavailable — skipping management API test")
 	}
+	// New starts the notifier and task-archive workers on context.Background();
+	// closing the pool stops them from claiming later tests' digest batches
+	// and archive jobs.
+	defer m.Close()
 	td := t.TempDir()
-	s := New(context.Background(), m, td, td, td)
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, td, td, td)
+	defer stopTestServer(t, s, cancel)
 	h := s.Handler()
 	tok, err := signJWT(s.jwtKey)
 	if err != nil {

server/server.go

@@ -192,7 +192,7 @@ func New(ctx context.Context, m *Manager, skillDir string, dataDir string, keyDi
 	// Wire DB-stored prompt templates into the agents (new design plan §3.3 / §5a). With no
 	// override row, agents keep their built-in defaults — behavior is unchanged.
 	if m.pg != nil {
-		agent.PromptOverride = func(key string) (string, bool) {
+		agent.SetPromptOverride(func(key string) (string, bool) {
 			a, err := m.pg.GetAgentByKey(key)
 			if err != nil || a == nil {
 				return "", false
@@ -202,38 +202,38 @@ func New(ctx context.Context, m *Manager, skillDir string, dataDir string, keyDi
 				return "", false
 			}
 			return t, true
-		}
+		})
 		// Wire DB-stored wrap-up (settlement) prompts. Empty column → built-in default.
-		agent.WrapupOverride = func(key string) (string, bool) {
+		agent.SetWrapupOverride(func(key string) (string, bool) {
 			a, err := m.pg.GetAgentByKey(key)
 			if err != nil || a == nil || a.WrapupPrompt == "" {
 				return "", false
 			}
 			return a.WrapupPrompt, true
-		}
+		})
 		// Wire DB-stored wrap-up turn budgets. 0 / missing → built-in per-agent default.
-		agent.WrapupMaxTurnsOverride = func(key string) (int, bool) {
+		agent.SetWrapupMaxTurnsOverride(func(key string) (int, bool) {
 			a, err := m.pg.GetAgentByKey(key)
 			if err != nil || a == nil || a.WrapupMaxTurns <= 0 {
 				return 0, false
 			}
 			return a.WrapupMaxTurns, true
-		}
+		})
 		// Wire DB-stored TASK-TIMEOUT wrap-up prompt/turns (worker/planner). Empty/0 → default.
-		agent.WrapupTaskTimeoutOverride = func(key string) (string, bool) {
+		agent.SetWrapupTaskTimeoutOverride(func(key string) (string, bool) {
 			a, err := m.pg.GetAgentByKey(key)
 			if err != nil || a == nil || a.TaskTimeoutWrapupPrompt == "" {
 				return "", false
 			}
 			return a.TaskTimeoutWrapupPrompt, true
-		}
-		agent.WrapupTaskTimeoutTurnsOverride = func(key string) (int, bool) {
+		})
+		agent.SetWrapupTaskTimeoutTurnsOverride(func(key string) (int, bool) {
 			a, err := m.pg.GetAgentByKey(key)
 			if err != nil || a == nil || a.TaskTimeoutWrapupMaxTurns <= 0 {
 				return 0, false
 			}
 			return a.TaskTimeoutWrapupMaxTurns, true
-		}
+		})
 		wireAgentAugment(m.pg, s.skillDir, s.hostTools) // wire visible skills/MCP + traffic/orchestration host tools into the agent toolset
 		domainReg := buildDomainReg(m.Assets())
 		wireTools(m.pg, domainReg)   // built-in tools table: filter per agent + override description/schema + inject defaults

server/skill_gaps_test.go

@@ -33,7 +33,9 @@ INSERT INTO skill_usage(skill,agent_key,task_id,found) VALUES
 		t.Fatal(err)
 	}
 
-	s := New(context.Background(), m, t.TempDir(), t.TempDir(), t.TempDir())
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir())
+	defer stopTestServer(t, s, cancel)
 	token, err := signJWT(s.jwtKey)
 	if err != nil {
 		t.Fatal(err)

server/task_categories_test.go

@@ -21,7 +21,9 @@ func TestTaskCategoryBatchRoute(t *testing.T) {
 	defer m.Close()
 
 	td := t.TempDir()
-	s := New(context.Background(), m, td, td, td)
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, td, td, td)
+	defer stopTestServer(t, s, cancel)
 	h := s.Handler()
 	token, err := signJWT(s.jwtKey)
 	if err != nil {

server/task_control_routes_test.go

@@ -16,7 +16,9 @@ func TestWorkerControlRoutes(t *testing.T) {
 	defer m.Close()
 
 	td := t.TempDir()
-	s := New(context.Background(), m, td, td, td)
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, td, td, td)
+	defer stopTestServer(t, s, cancel)
 	h := s.Handler()
 	token, err := signJWT(s.jwtKey)
 	if err != nil {

server/task_detail_metrics_test.go

@@ -38,7 +38,9 @@ VALUES ($1,'goal','{}','met'), ($1,'goal','{}','open')`, task.ExpID); err != nil
 		t.Fatal(err)
 	}
 
-	s := New(context.Background(), m, t.TempDir(), t.TempDir(), t.TempDir())
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir())
+	defer stopTestServer(t, s, cancel)
 	token, err := signJWT(s.jwtKey)
 	if err != nil {
 		t.Fatal(err)

server/task_metadata_test.go

@@ -24,7 +24,9 @@ func TestTaskMetadataPatchReturnsRenameAndPin(t *testing.T) {
 	}
 	taskID, _ := strconv.ParseInt(task.ID, 10, 64)
 	defer func() { _ = m.pg.DeleteTask(taskID) }()
-	s := New(context.Background(), m, t.TempDir(), t.TempDir(), t.TempDir())
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir())
+	defer stopTestServer(t, s, cancel)
 	token, err := signJWT(s.jwtKey)
 	if err != nil {
 		t.Fatal(err)
@@ -66,7 +68,9 @@ func TestConversationBatchDeleteReportsMissing(t *testing.T) {
 		t.Skipf("postgres unavailable (%v) — skipping", err)
 	}
 	defer m.Close()
-	s := New(context.Background(), m, t.TempDir(), t.TempDir(), t.TempDir())
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir())
+	defer stopTestServer(t, s, cancel)
 	first, err := m.pg.CreateConversation("mainagent", "batch-http-first", nil)
 	if err != nil {
 		t.Fatal(err)

server/task_outcome_test.go

@@ -23,6 +23,9 @@ func TestTaskOutcomeCard(t *testing.T) {
 	}
 	taskID, _ := strconv.ParseInt(task.ID, 10, 64)
 	defer func() { _ = m.pg.DeleteTask(taskID) }()
+	// skill_usage has no foreign keys, so DeleteTask leaves these rows behind,
+	// and their misses would outrank TestSkillGapsReport's fixture in later runs.
+	defer func() { _, _ = m.pg.Exec(`DELETE FROM skill_usage WHERE task_id=$1`, taskID) }()
 
 	if _, err := m.pg.Exec(`
 INSERT INTO findings(task_id,vulnclass,name,severity,status) VALUES
@@ -57,7 +60,9 @@ INSERT INTO skill_usage(skill,task_id,found) VALUES ('api-recon',$1,true),('grap
 		t.Fatal(err)
 	}
 
-	s := New(context.Background(), m, t.TempDir(), t.TempDir(), t.TempDir())
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir())
+	defer stopTestServer(t, s, cancel)
 	token, err := signJWT(s.jwtKey)
 	if err != nil {
 		t.Fatal(err)

server/task_scope_description_test.go

@@ -23,7 +23,7 @@ func TestTaskScopeDescriptionUpgrade(t *testing.T) {
 	ctx, cancel := context.WithCancel(context.Background())
 	cancel()
 	s := New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir())
-	t.Cleanup(func() { agent.ToolResolve = nil })
+	t.Cleanup(func() { agent.SetToolResolve(nil) })
 	pg := m.pg
 
 	var want string
@@ -84,7 +84,7 @@ func TestTaskScopeDescriptionUpgrade(t *testing.T) {
 // ToolResolve serves it to the planner.
 func resolvedTaskScopeDescription(t *testing.T) string {
 	t.Helper()
-	tools := agent.ToolResolve(context.Background(), "planner", agent.NewToolSet(nil, "").PlannerTools())
+	tools := agent.ToolResolve()(context.Background(), "planner", agent.NewToolSet(nil, "").PlannerTools())
 	for _, tl := range tools {
 		if tl.Name() == "add_task_scope" {
 			return tl.Description()

server/task_templates_test.go

@@ -20,7 +20,9 @@ func TestTaskTemplateHTTPCRUD(t *testing.T) {
 		t.Skipf("postgres unavailable (%v) — skipping", err)
 	}
 	defer m.Close()
-	s := New(context.Background(), m, t.TempDir(), t.TempDir(), t.TempDir())
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir())
+	defer stopTestServer(t, s, cancel)
 	h := s.Handler()
 	token, err := signJWT(s.jwtKey)
 	if err != nil {
@@ -90,7 +92,9 @@ func TestConversationPatchReturnsPinState(t *testing.T) {
 		t.Skipf("postgres unavailable (%v) — skipping", err)
 	}
 	defer m.Close()
-	s := New(context.Background(), m, t.TempDir(), t.TempDir(), t.TempDir())
+	ctx, cancel := context.WithCancel(context.Background())
+	s := New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir())
+	defer stopTestServer(t, s, cancel)
 	conversation, err := m.pg.CreateConversation("mainagent", "pin through http", nil)
 	if err != nil {
 		t.Fatal(err)

server/testserver_test.go

@@ -0,0 +1,27 @@
+package server
+
+import (
+	"context"
+	"testing"
+	"time"
+)
+
+// stopTestServer cancels a test server's context and joins what New started.
+// New restores every unfinished task in the shared database and runs its
+// planner, worker and deadline loops, which write under m.dir. Call it with
+// defer right after New, so it runs before m.Close and the TempDir cleanups.
+func stopTestServer(t *testing.T, s *Server, cancel context.CancelFunc) {
+	t.Helper()
+	cancel()
+	for _, task := range s.m.List() {
+		s.engine.BeginDelete(task.ID)
+		waitCtx, waitCancel := context.WithTimeout(context.Background(), 30*time.Second)
+		if err := s.waitTaskQuiescent(waitCtx, task.ID); err != nil {
+			t.Errorf("task %s still running at teardown: %v", task.ID, err)
+		}
+		waitCancel()
+		s.engine.StopTask(task.ID)
+	}
+	s.archiveWG.Wait()
+	<-s.side.done
+}

server/tools_wire_test.go

@@ -33,7 +33,7 @@ func TestWireTools(t *testing.T) {
 	defer pg.Close()
 
 	wireTools(pg, nil) // nil domainReg: test only covers filter/decoration, not injection
-	t.Cleanup(func() { agent.ToolResolve = nil })
+	t.Cleanup(func() { agent.SetToolResolve(nil) })
 	// Prevent interactive-shell Bash decoration: if the worker agent has
 	// interactive_shell=true in the DB, ToolResolve would append a note to
 	// Bash's description. Disable that for this test so the undecorated
@@ -52,7 +52,7 @@ func TestWireTools(t *testing.T) {
 	base := append(ts.WorkerTools(), actool.DefaultTools()...)
 	ctx := context.Background()
 
-	worker := names(agent.ToolResolve(ctx, "worker", base))
+	worker := names(agent.ToolResolve()(ctx, "worker", base))
 	if _, ok := worker["record_fact"]; !ok {
 		t.Error("worker lost record_fact")
 	}
@@ -65,7 +65,7 @@ func TestWireTools(t *testing.T) {
 		t.Error("Bash should pass through undecorated, but description changed")
 	}
 	// planner is not bound to record_fact → resolving a base that contains it drops it.
-	planner := names(agent.ToolResolve(ctx, "planner", base))
+	planner := names(agent.ToolResolve()(ctx, "planner", base))
 	if _, ok := planner["record_fact"]; ok {
 		t.Error("planner should not get record_fact (not bound)")
 	}
@@ -85,7 +85,7 @@ func TestWireTools(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	worker2 := names(agent.ToolResolve(ctx, "worker", base))
+	worker2 := names(agent.ToolResolve()(ctx, "worker", base))
 	got := worker2["record_fact"]
 	if got == nil {
 		t.Fatal("record_fact missing after edit")