chore: release v1.5.3

Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>

.github/workflows/build-release.yml

@@ -70,7 +70,7 @@ jobs:
             TUI_NAME="strix-tui"
             dist/strix --version
           fi
-          uv run pyi-archive_viewer -l "$PYI_BINARY" | grep "strix/bin/$TUI_NAME" >/dev/null
+          uv run pyi-archive_viewer -l "$PYI_BINARY" | grep -E "strix[/\\]+bin[/\\]+$TUI_NAME" >/dev/null
 
           if [[ "${{ matrix.target }}" == "linux-arm64" ]]; then
             file dist/strix
@@ -118,4 +118,4 @@ jobs:
         with:
           prerelease: ${{ !startsWith(github.ref, 'refs/tags/') }}
           generate_release_notes: true
-          files: release/*
+          files: release/**

AGENTS.md

@@ -0,0 +1,49 @@
+# Strix — Agent Guide
+
+Strix is an open-source autonomous AI pentesting tool. This file is for AI coding agents that want to **use** Strix (run security scans) or **contribute** to it.
+
+## Using Strix from an agent
+
+Install the agent skills for step-by-step workflows:
+
+```bash
+npx skills add usestrix/strix
+```
+
+- `penetration-testing-with-strix` — run a headless pentest against code, URLs, domains, or IPs and read results (covers both run modes below)
+- `managed-pentesting-with-strix` — drive the managed app.strix.ai platform via REST (no local Docker/LLM needed)
+- `fix-security-vulnerabilities-with-strix` — remediate findings and re-run Strix to verify
+- `ci-security-scanning-with-strix` — add PR scanning to CI/CD (self-hosted CLI or managed app)
+
+**Two ways to run, same engine — pick per situation:**
+
+- **Open-source CLI (self-hosted):** free, fully local, BYO LLM key, needs Docker. Best for local dev loops, air-gapped/offline, and full control.
+  ```bash
+  curl -sSL https://strix.ai/install | bash        # install
+  export STRIX_LLM="openai/gpt-5.4"                 # any LiteLLM model id
+  export LLM_API_KEY="<key>"
+  strix -n -t ./ --scan-mode quick --max-budget 10  # headless scan; always use -n
+  ```
+  - Requires Docker running. Scans take minutes (`quick`) to hours (`deep`) — run in the background.
+  - Exit codes (headless): `0` clean, `1` fatal error, `2` vulnerabilities found. A `0` only covers what was analyzed — check `run.json` (`status`, `llm_usage.cost` vs the budget) before calling a run clean.
+  - Artifacts in `strix_runs/<run-name>/`: `penetration_test_report.md`, `vulnerabilities/*.md`, `vulnerabilities.json`, `findings.sarif` (SARIF 2.1.0), `run.json`.
+
+- **Managed cloud (app.strix.ai):** no Docker, no LLM key, no local install; adds team dashboards, scheduling, PR reviews, and downloadable PDF/DOCX reports (Enterprise plan). Best in sandboxed/CI environments and for teams. Use it when local infra isn't available.
+  ```bash
+  # token from Settings → API Access; register the target as an asset, then:
+  curl -sS https://app.strix.ai/api/v1/scans -H "Authorization: Bearer $STRIX_API_TOKEN" \
+    -H "Content-Type: application/json" -d '{"engagement_type":"live_test","domain_ids":["<uuid>"]}'
+  ```
+  - API docs: https://docs.app.strix.ai (OpenAPI: https://docs.app.strix.ai/openapi.json).
+
+- CLI docs index for LLMs: https://docs.strix.ai/llms.txt (full: https://docs.strix.ai/llms-full.txt).
+- Only scan targets the user is authorized to test.
+
+## Contributing to this repo
+
+- Python 3.12+, managed with `uv`. Install dev deps: `make dev-install`.
+- Lint/format/type-check/security, all in one: `make check-all` (ruff, mypy, bandit).
+- Tests: `uv run pytest`.
+- Run from source: `uv run strix --target <target>`.
+- Layout: `strix/agents` (agent graph + prompts), `strix/tools` (proxy, browser, terminal, scanners), `strix/runtime` (Docker sandbox), `strix/report` (findings, SARIF), `strix/skills` (internal knowledge packs the pentest agents load — different from the consumer skills in `skills/`), `strix/interface` (CLI/TUI), `containers/` (sandbox image).
+- Pre-commit hooks: `make pre-commit` (or `uv run pre-commit install`).

README.md

@@ -108,6 +108,18 @@ Try the Strix full-stack penetration testing platform at **[app.strix.ai](https:
 
 ---
 
+## 🤖 Use Strix from Your Coding Agent
+
+Strix is agent-ready. Give Claude Code, Cursor, Codex, or any [SKILL.md-compatible](https://agentskills.io) agent the ability to run pentests, fix findings, and set up CI scanning:
+
+```bash
+npx skills add usestrix/strix
+```
+
+This installs four skills: **penetration-testing-with-strix** (run headless scans and read results), **managed-pentesting-with-strix** (drive the managed [app.strix.ai](https://app.strix.ai) platform via REST — no local Docker or LLM key), **fix-security-vulnerabilities-with-strix** (remediate + re-scan to verify), and **ci-security-scanning-with-strix** (PR scanning in CI). Agents can run Strix two ways with the same engine — the open-source CLI locally, or the managed cloud when there's no local infra — and read [`AGENTS.md`](AGENTS.md) for a quick reference, [docs.strix.ai/llms.txt](https://docs.strix.ai/llms.txt) for the CLI docs, and [docs.app.strix.ai](https://docs.app.strix.ai) for the API.
+
+---
+
 ## ✨ Features
 
 ### Agentic Pentesting Tools
@@ -337,6 +349,7 @@ Strix builds on the incredible work of open-source projects like [LiteLLM](https
 
 
 > [!WARNING]
-> Only test apps you own or have permission to test. You are responsible for using Strix ethically and legally.
+> **Authorized use only.** Strix actively tests the targets you point it at, so only run it against systems you own or have **explicit, written permission** to test, and stay within the agreed scope. Unauthorized testing is illegal in most jurisdictions.
+> You alone are responsible for obtaining authorization and complying with the law. Strix is provided "as is" with no warranty or liability for misuse.
 
 </div>

containers/Dockerfile

@@ -16,7 +16,8 @@ RUN mkdir -p /out/bin && \
     go install -v github.com/projectdiscovery/katana/cmd/katana@latest && \
     go install -v github.com/projectdiscovery/cvemap/cmd/vulnx@latest && \
     go install -v github.com/jaeles-project/gospider@latest && \
-    go install -v github.com/projectdiscovery/interactsh/cmd/interactsh-client@latest
+    go install -v github.com/projectdiscovery/interactsh/cmd/interactsh-client@latest && \
+    go install -v golang.org/x/vuln/cmd/govulncheck@latest
 
 # ---------------------------------------------------------------------------
 # Runtime stage
@@ -53,6 +54,7 @@ RUN apt-get update && \
     nmap ncat ndiff \
     sqlmap nuclei subfinder naabu ffuf \
     nodejs npm pipx \
+    golang-go \
     libcap2-bin \
     gdb \
     libnss3-tools \
@@ -115,6 +117,21 @@ ENV AGENT_BROWSER_EXECUTABLE_PATH=/usr/bin/chromium
 ENV AGENT_BROWSER_USER_AGENT="Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
 ENV AGENT_BROWSER_ARGS="--disable-blink-features=AutomationControlled,--no-first-run,--no-default-browser-check,--lang=en-US"
 ENV AGENT_BROWSER_SCREENSHOT_DIR=/workspace/.agent-browser-screenshots
+ENV AGENT_BROWSER_IDLE_TIMEOUT_MS=180000
+USER root
+RUN set -eu; \
+    { \
+        for var in AGENT_BROWSER_EXECUTABLE_PATH AGENT_BROWSER_USER_AGENT \
+                   AGENT_BROWSER_ARGS AGENT_BROWSER_SCREENSHOT_DIR \
+                   AGENT_BROWSER_IDLE_TIMEOUT_MS; do \
+            eval "value=\${$var}"; \
+            printf 'export %s="${%s:-%s}"\n' "$var" "$var" "$value"; \
+        done; \
+    } > /tmp/agent-browser.sh; \
+    install -m 0644 /tmp/agent-browser.sh /etc/profile.d/agent-browser.sh; \
+    rm /tmp/agent-browser.sh; \
+    env -i bash -lc 'test "${AGENT_BROWSER_IDLE_TIMEOUT_MS}" = "180000"'
+USER pentester
 RUN /home/pentester/.npm-global/bin/agent-browser doctor --offline --quick
 
 RUN set -eux; \

docs/advanced/configuration.mdx

@@ -110,7 +110,7 @@ When remote vars are set, Strix dual-writes telemetry to both local JSONL and th
 
 ## Docker Configuration
 
-<ParamField path="STRIX_IMAGE" default="ghcr.io/usestrix/strix-sandbox:1.2.0" type="string">
+<ParamField path="STRIX_IMAGE" default="ghcr.io/usestrix/strix-sandbox:1.3.0" type="string">
   Docker image to use for the sandbox container.
 </ParamField>
 

docs/advanced/skills.mdx

@@ -68,10 +68,10 @@ Framework-specific testing patterns.
 
 Third-party service and platform security.
 
-| Skill                | Coverage                           |
-| -------------------- | ---------------------------------- |
-| `supabase`           | Supabase RLS bypasses, auth issues |
-| `firebase_firestore` | Firestore rules, Firebase auth     |
+| Skill      | Coverage                                               |
+| ---------- | ------------------------------------------------------ |
+| `supabase` | Supabase RLS bypasses, auth issues                     |
+| `firebase` | Firebase Firestore, Storage rules, Auth, and Functions |
 
 ### Protocols
 

docs/docs.json

@@ -46,7 +46,8 @@
             "group": "Integrations",
             "pages": [
               "integrations/github-actions",
-              "integrations/ci-cd"
+              "integrations/ci-cd",
+              "integrations/coding-agents"
             ]
           },
           {

docs/integrations/coding-agents.mdx

@@ -0,0 +1,61 @@
+---
+title: "Coding Agents"
+description: "Use Strix from Claude Code, Cursor, Codex, and other AI agents"
+---
+
+Strix is built to be driven by AI coding agents. Install the official agent skills and your agent knows how to run pentests, remediate findings, and wire Strix into CI.
+
+## Install the Skills
+
+Works with any agent that supports the open [SKILL.md standard](https://agentskills.io) — Claude Code, Cursor, Codex, Gemini CLI, OpenCode, and dozens more:
+
+```bash
+npx skills add usestrix/strix
+```
+
+| Skill | What your agent learns |
+|-------|------------------------|
+| `penetration-testing-with-strix` | Run headless scans against code, URLs, domains, or IPs — self-hosted CLI or managed cloud — with budget caps, and read the results |
+| `managed-pentesting-with-strix` | Drive the managed [app.strix.ai](https://app.strix.ai) platform over REST — no local Docker or LLM key needed |
+| `fix-security-vulnerabilities-with-strix` | Triage findings, fix root causes, and re-run Strix to verify each fix |
+| `ci-security-scanning-with-strix` | Add PR security scanning to GitHub Actions or any CI (self-hosted CLI or managed app) |
+
+Install a single skill with `npx skills add usestrix/strix --skill penetration-testing-with-strix`, or use one without installing:
+
+```bash
+npx skills use usestrix/strix@penetration-testing-with-strix | claude
+```
+
+## Two ways to run — self-hosted or managed
+
+Both use the same engine and produce the same validated findings and SARIF, so agents can pick per situation or combine them:
+
+- **Open-source CLI (self-hosted)** — runs locally in a Docker sandbox with your own LLM key. Free, fully local, air-gap capable. Best for local dev loops and full control.
+- **Managed cloud** — runs on Strix's infrastructure via the [app.strix.ai REST API](https://docs.app.strix.ai). No Docker, no LLM key, no local install; adds team dashboards, scheduling, PR reviews, and downloadable PDF/DOCX reports (Enterprise plan). Best in sandboxed/CI environments and for teams. Create an API token under **Settings → API Access**; the `managed-pentesting-with-strix` skill has the full flow.
+
+## Agent-Friendly Interfaces
+
+Everything an agent needs is machine-readable:
+
+- **Headless CLI** — `strix -n` runs without the TUI and exits with `0` (clean), `1` (error), or `2` (vulnerabilities found).
+- **REST API** — the managed platform exposes a documented [OpenAPI](https://docs.app.strix.ai/openapi.json) at `https://app.strix.ai/api/v1` (scans, vulnerabilities, assets, PR reviews, schedules, webhooks) with bearer tokens and scopes.
+- **Structured results** — every run writes `vulnerabilities.json`, `vulnerabilities.csv`, `findings.sarif` (SARIF 2.1.0), and per-finding Markdown under `strix_runs/<run-name>/`; the cloud exposes the same as JSON plus SARIF export.
+- **Budget controls** — `--max-budget` and `--max-turns` give agents hard cost/time caps.
+- **`AGENTS.md`** — the [repository's agent guide](https://github.com/usestrix/strix/blob/main/AGENTS.md) with a quick reference.
+- **`llms.txt`** — this documentation is indexed at [docs.strix.ai/llms.txt](https://docs.strix.ai/llms.txt) and fully exported at [docs.strix.ai/llms-full.txt](https://docs.strix.ai/llms-full.txt); every page is also available as Markdown by appending `.md` to its URL.
+
+## Example Prompts
+
+Once the skills are installed, prompts like these just work:
+
+```text
+Pentest this repo with Strix (quick mode, $10 budget) and summarize the findings.
+```
+
+```text
+Fix all critical and high findings from the last Strix run, then re-scan to verify.
+```
+
+```text
+Add Strix security scanning to our GitHub Actions so every PR gets tested.
+```

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "strix-agent"
-version = "1.4.1"
+version = "1.5.3"
 description = "Open-source AI Hackers for your apps"
 readme = "README.md"
 license = "Apache-2.0"
@@ -236,6 +236,9 @@ ignore = [
 "strix/interface/auth_cli.py" = ["N802"]
 "tests/test_codex_streaming.py" = ["N802"]
 "tests/test_disable_streaming.py" = ["N802"]
+"tests/test_tool_call_ids.py" = ["N802"]
+"tests/test_tool_call_limits.py" = ["N802", "SLF001"]
+"tests/test_stream_idle_timeout.py" = ["N802", "SLF001"]
 "tests/test_unknown_tool_recovery.py" = ["N802"]
 "tests/test_report_pdf.py" = ["S105", "S106"]
 # Stdlib HTTP handler overrides (do_GET/do_POST) and lazy imports that avoid a

scripts/install.sh

@@ -4,7 +4,7 @@ set -euo pipefail
 
 APP=strix
 REPO="usestrix/strix"
-STRIX_IMAGE="ghcr.io/usestrix/strix-sandbox:1.2.0"
+STRIX_IMAGE="ghcr.io/usestrix/strix-sandbox:1.3.0"
 
 MUTED='\033[0;2m'
 RED='\033[0;31m'

skills/ci-security-scanning-with-strix/SKILL.md

@@ -0,0 +1,136 @@
+---
+name: ci-security-scanning-with-strix
+description: Add security scanning to CI/CD with Strix — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code before it merges, with results as PR comments and SARIF uploaded to code scanning. Covers both the self-hosted open-source CLI (runs in your runner) and the managed app.strix.ai platform (GitHub/GitLab app or API, no runner infra). Use when the user asks to add security scanning, SAST/DAST, pentesting, vulnerability checks, or automated security review to their CI pipeline, pre-merge gate, or PR workflow.
+license: Apache-2.0
+metadata:
+  author: usestrix
+  homepage: https://docs.strix.ai
+---
+
+# Set up Strix in CI/CD
+
+You can gate PRs two ways — pick based on the environment, or combine them:
+
+- **Managed platform (recommended for most teams)** — connect the GitHub/GitLab/Bitbucket app once and Strix reviews every PR with **no workflow file, no runner, no Docker, and no LLM key**. Results post as PR comments and land in the team dashboard. Best when you want zero CI maintenance, central tracking, or your runners lack Docker. See "Managed platform" below and the **managed-pentesting-with-strix** skill.
+- **Self-hosted OSS CLI in your runner** — run a diff-scoped scan as a pipeline step. Fully in your infra, free (BYO LLM key), no external account. Requires Docker on the runner. Best for air-gapped/self-hosted CI or when you don't want scans leaving your environment.
+
+Both fail the build on validated findings and both emit SARIF 2.1.0, so you can start with one and add the other later.
+
+---
+
+# Option A — Self-hosted OSS CLI in the runner
+
+Run a diff-scoped Strix scan on every PR: only changed files are tested, `quick` mode keeps it fast, and exit code `2` fails the build when validated vulnerabilities are found.
+
+## GitHub Actions
+
+Create `.github/workflows/security.yml`:
+
+```yaml
+name: Security Scan
+
+on:
+  pull_request:
+
+jobs:
+  strix-scan:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0   # required for diff-scope resolution
+
+      - name: Install Strix
+        run: curl -sSL https://strix.ai/install | bash
+
+      - name: Run Security Scan
+        env:
+          STRIX_LLM: ${{ secrets.STRIX_LLM }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+        run: strix -n -t ./ --scan-mode quick --max-budget 10
+
+      # Don't fail open: a run that hits the hard budget stop exits 0 but leaves
+      # run.json status "stopped", not "completed". Enforce completion explicitly.
+      # This does not catch an agent that wrapped up early on a budget *warning*
+      # (it still calls finish_scan and records "completed"), so size the budget.
+      - name: Fail unless the scan completed
+        run: |
+          run_json=$(ls -t strix_runs/*/run.json | head -1)
+          status=$(jq -r .status "$run_json")
+          if [ "$status" != "completed" ]; then
+            echo "Strix run status is '$status' — the scan did not complete (likely budget exhausted). Raise --max-budget." >&2
+            exit 1
+          fi
+```
+
+Then tell the user to add two repository secrets: `STRIX_LLM` (model id, e.g. `openai/gpt-5.4`) and `LLM_API_KEY` (the provider key). Do not create these values yourself.
+
+Notes:
+- In CI/headless runs Strix automatically scopes to the PR's changed files (`--scope-mode auto`). If diff resolution fails, keep `fetch-depth: 0` or set `--diff-base` to the PR's actual base branch — use `origin/${{ github.base_ref }}` in GitHub Actions rather than a hard-coded `origin/main`, since repos use different default branches.
+- Exit codes: `0` pass, `2` vulnerabilities found (fails the job), `1` setup error.
+- The runner needs Docker (default GitHub-hosted Ubuntu runners have it).
+- **Size the budget so the scan completes — don't let it fail open.** A `0` exit means "no validated vulnerabilities in what was analyzed"; if `--max-budget` is hit before the diff is fully covered, the scan wraps up early and can still exit `0`. The "Fail unless the scan completed" step above narrows the gap: `strix_runs/<run>/run.json` is `"stopped"` when the scan was cut off at the hard budget limit without a final report. It is not a complete guard — the agents get graduated wrap-up warnings before that limit, and a run that wraps up on a warning still calls `finish_scan` and records `"completed"` with partial coverage. So keep that step in any pipeline that gates merges **and** give the scan real headroom (compare `run.json`'s `llm_usage.cost` against `--max-budget`; if it ran right up to the cap, raise it). For a `quick` diff-scoped PR scan `--max-budget 10` is usually ample, raise it for large diffs.
+
+### Optional: upload findings to GitHub code scanning
+
+Strix writes SARIF 2.1.0 to `strix_runs/<run>/findings.sarif`:
+
+```yaml
+      - name: Upload SARIF
+        if: always()
+        uses: github/codeql-action/upload-sarif@v3
+        with:
+          sarif_file: strix_runs
+```
+
+## Other CI systems
+
+Any pipeline works the same way — install, set the two env vars, run headless:
+
+```bash
+curl -sSL https://strix.ai/install | bash
+# Resolve the PR's base branch robustly (use your CI's base-branch variable if it
+# has one, e.g. GitHub Actions: origin/${{ github.base_ref }}). Avoid piping the
+# git lookup into another command — a failed lookup would otherwise be masked.
+BASE_BRANCH="${CI_MERGE_REQUEST_TARGET_BRANCH_NAME:-}"   # GitLab MR target
+if [ -z "$BASE_BRANCH" ]; then
+  BASE_BRANCH=$(git symbolic-ref --quiet --short refs/remotes/origin/HEAD 2>/dev/null)
+  BASE_BRANCH="${BASE_BRANCH#origin/}"
+fi
+DIFF_BASE="origin/${BASE_BRANCH:-main}"
+# Fail loudly rather than silently narrowing scope (e.g. to HEAD~1, which on a
+# multi-commit branch would scan only the last commit and let earlier ones pass).
+if ! git rev-parse --verify --quiet "$DIFF_BASE" >/dev/null; then
+  echo "Cannot resolve diff base '$DIFF_BASE'. Fetch the base branch (git fetch origin <base>) or set --diff-base explicitly." >&2
+  exit 1
+fi
+strix -n -t ./ --scan-mode quick --scope-mode diff --diff-base "$DIFF_BASE" --max-budget 10
+```
+
+Gate the pipeline on the exit code (see the budget/fail-open caveat above — give the scan enough budget to finish). Schedule `standard` scans nightly and `deep` scans for release candidates.
+
+---
+
+# Option B — Managed platform (no runner infra)
+
+No workflow file, no Docker, no LLM key. Two ways to use it:
+
+1. **PR-review app (zero code):** the user installs the Strix GitHub/GitLab/Bitbucket app and enables PR reviews for the repo in the app.strix.ai dashboard. Every PR is then reviewed automatically, with findings posted as PR comments. Nothing to add to the repo. This is the lowest-effort path — recommend it first when the user just wants PR gating.
+
+2. **API-triggered from any pipeline:** if you want to trigger from an existing pipeline (or a system without the SCM app), call the API with a token that has `pr_reviews:write` (or `scans:write`). Store the token as a CI secret; ask the user to create it at **Settings → API Access**. Example GitHub Actions step:
+
+   ```yaml
+   - name: Strix PR review (managed)
+     if: github.event_name == 'pull_request'
+     env:
+       STRIX_API_TOKEN: ${{ secrets.STRIX_API_TOKEN }}
+     run: |
+       curl -sS --fail https://app.strix.ai/api/v1/pr-reviews/start \
+         -H "Authorization: Bearer $STRIX_API_TOKEN" \
+         -H "Content-Type: application/json" \
+         -d "{\"repository_full_name\":\"${{ github.repository }}\",\"pr_number\":${{ github.event.pull_request.number }}}"
+   ```
+
+   To gate the build on results, poll the PR review / scan status and fail on unresolved criticals/highs. Full endpoints (PR reviews, scans, SARIF export, schedules for scheduled deep scans) are in the **managed-pentesting-with-strix** skill.
+
+Recommend Option B for most teams (no maintenance, central dashboard); use Option A when scans must stay entirely within your own infrastructure.

skills/fix-security-vulnerabilities-with-strix/SKILL.md

@@ -0,0 +1,77 @@
+---
+name: fix-security-vulnerabilities-with-strix
+description: Fix security vulnerabilities found by a Strix pentest (open-source CLI or app.strix.ai cloud) — triage by severity, patch the root cause rather than the symptom, and re-run Strix to prove each fix actually closes the exploit. Handles injection, XSS, SSRF, broken access control, IDOR, and other validated findings. Use after a Strix scan reports findings, or when the user asks to remediate, patch, or fix security issues from a strix_runs report, vulnerabilities.json, findings.sarif, or a cloud scan.
+license: Apache-2.0
+metadata:
+  author: usestrix
+  homepage: https://docs.strix.ai
+---
+
+# Fix Strix findings and verify
+
+Turn validated Strix findings into minimal, correct fixes — and prove they work by re-scanning.
+
+## 1. Triage
+
+Get the findings from wherever the scan ran:
+
+- **OSS CLI** — artifacts in `strix_runs/<run-name>/`:
+  - `vulnerabilities/*.md` — one finding per file: description, severity, PoC steps or script, affected code locations, remediation guidance.
+  - `vulnerabilities.json` — the same findings as JSON (ids, severity, CWE/CVE, `code_locations` with `fix_before`/`fix_after` suggestions when available).
+- **Cloud (app.strix.ai)** — fetch the scan's `vulnerabilities[]` via `GET /api/v1/scans/{scanId}` (or `GET /api/v1/vulnerabilities` org-wide). Each carries `severity, cwe, endpoint, method, impact, technical_analysis, poc_description, poc_script_code` and, for code findings, `code_file`/`code_diff`/`code_before`/`code_after`. See the **managed-pentesting-with-strix** skill for auth.
+
+Order work by severity: critical → high → medium → low. Every Strix finding was validated with a working proof-of-concept, so do not dismiss findings as false positives without re-testing the PoC yourself.
+
+## 2. Fix
+
+For each finding:
+
+1. Reproduce it with the PoC from the finding file when feasible.
+2. Fix the root cause, not the specific payload (e.g. parameterize all queries, don't blocklist one string; enforce authorization in the handler, don't hide the endpoint).
+3. Prefer the framework's built-in defense (ORM parameterization, template auto-escaping, CSRF middleware, centralized authz) over ad-hoc sanitization.
+4. Keep the diff minimal and apply the repo's existing patterns. Finding files often include `fix_before`/`fix_after` snippets — use them as a starting point, not verbatim.
+
+Common finding classes and expected fixes: injection → parameterization/escaping at the sink; IDOR/broken access control → object-level authorization checks; SSRF → allowlist + block internal ranges; XSS → context-aware output encoding + CSP; secrets exposure → rotate the secret AND remove it from code/history; auth issues → fix the server-side check (never client-side).
+
+## 3. Verify by re-running Strix
+
+After fixing, re-scan scoped to the fixed area and confirm the finding is gone. Verify in whichever environment you scanned (or both):
+
+**OSS CLI:**
+```bash
+# Re-test just the changed files (fast). Resolve the repo's real default
+# branch instead of assuming origin/main (many repos use master/develop).
+# Avoid the current branch's own upstream as the base — its merge base with
+# HEAD would be HEAD, giving an empty diff and a falsely clean result.
+DIFF_BASE=$(git symbolic-ref --quiet --short refs/remotes/origin/HEAD 2>/dev/null)
+# origin/HEAD can be a dangling symbolic ref — keep it only if its target exists.
+git rev-parse --verify --quiet "$DIFF_BASE" >/dev/null 2>&1 || DIFF_BASE=""
+if [ -z "$DIFF_BASE" ]; then
+  for b in origin/main origin/master origin/develop; do
+    git rev-parse --verify --quiet "$b" >/dev/null && DIFF_BASE="$b" && break
+  done
+fi
+# No silent fallback: a guess like HEAD~1 would cover only the last commit of a
+# multi-commit fix branch. If no base resolves, ask the user for the base branch
+# (or use the focused --instruction verification below, which needs no diff base).
+[ -n "$DIFF_BASE" ] || { echo "Set DIFF_BASE to the branch your fix will merge into." >&2; exit 1; }
+strix -n -t ./ --scan-mode quick --scope-mode diff --diff-base "$DIFF_BASE" --max-budget 5
+
+# Or re-test with the original finding as focus (no diff base needed)
+strix -n -t ./ --instruction "Verify the SQL injection in app/api/search.py is fixed. Original PoC: <poc>" --max-budget 5
+```
+Exit codes: `2` = findings remain (read the new `strix_runs/<run>/vulnerabilities/` and iterate); `0` = clean **for what was analyzed**. Before trusting a `0`, confirm the run wasn't cut short — check `run.json` for a completed status and compare its `llm_usage.cost` with `--max-budget`: a hard budget stop leaves `status: "stopped"`, but a run that wrapped up on a budget warning records `"completed"` with partial coverage. Give verification enough budget to finish, and prefer re-running the specific PoC as the ground-truth signal.
+
+**Cloud:** rerun with the same config and re-poll, then confirm the finding no longer appears:
+```bash
+new_id=$(curl -sS "$BASE/scans/$scan_id/rerun" "${auth[@]}" -X POST | jq -r .scan_id)
+# poll GET /scans/$new_id until completed, then check its vulnerabilities[]
+```
+Or, if the cloud scan came from a repo/PR, trigger a fresh PR review on the fix branch (`POST /pr-reviews/start`). The platform also retests a single finding directly: `POST /api/v1/vulnerabilities/{vulnerabilityId}/retest`.
+
+- Also re-run the PoC manually when it is a simple request/script — fastest signal.
+- Run the project's own test suite to make sure the fix doesn't break behavior.
+
+## 4. Report
+
+Summarize per finding: severity, root cause, fix applied (file:line), verification result (re-scan clean / PoC no longer reproduces). Never include live secrets in the report; if a secret leaked, state that rotation is required.

skills/managed-pentesting-with-strix/SKILL.md

@@ -0,0 +1,152 @@
+---
+name: managed-pentesting-with-strix
+description: Run a managed pentest of a web app or API through the app.strix.ai REST API — no local Docker, LLM key, or install needed. Create an API token, register domain/repository assets, launch and poll scans, triage vulnerabilities, export SARIF, download PDF/DOCX pentest reports for SOC 2 and other compliance evidence (Enterprise plan), start PR reviews, and set up schedules and webhooks. Use when the user wants continuous or scheduled pentesting-as-a-service, an auditor-ready pentest report, scans tracked in a team dashboard, or security testing from a sandboxed agent/CI environment with no infrastructure.
+license: Apache-2.0
+metadata:
+  author: usestrix
+  homepage: https://docs.app.strix.ai
+---
+
+# Strix Cloud API (managed, no local infra)
+
+Use this when you want Strix's autonomous pentesting **without running Docker or an LLM yourself** — the scan runs on Strix's infrastructure and results are tracked in a team dashboard. This is the right choice in sandboxed/hosted agent and CI environments, for teams, and for scheduled/continuous testing (downloadable PDF/DOCX reports are an Enterprise-plan feature). For fully local, free, air-gapped, or BYO-LLM runs, use the open-source CLI in the **penetration-testing-with-strix** skill instead — both share the same engine and SARIF output, so you can mix them.
+
+Full reference: **[docs.app.strix.ai](https://docs.app.strix.ai)** · OpenAPI: `https://docs.app.strix.ai/openapi.json`
+
+## Setup
+
+- **Base URL:** `https://app.strix.ai/api/v1`
+- **Auth:** every request sends `Authorization: Bearer <token>`. Tokens are **org-scoped**.
+- **Get a token:** the user creates one in the dashboard at **Settings → API Access** (app.strix.ai). Ask them for it; never hardcode, log, or commit it. Store it in an env var or the CI secret store.
+- **Scopes (least-privilege):** assign only what the integration needs and rotate regularly:
+
+  | Scope | Grants |
+  |---|---|
+  | `scans:read` / `scans:write` | list/read/report scans · create/rerun/cancel scans |
+  | `vulnerabilities:read` / `:write` | read findings · update status & notes |
+  | `assets:read` / `:write` | read domains/repos · register/update them |
+  | `schedules:read` / `:write` | read schedules · create/trigger recurring scans |
+  | `pr_reviews:write` | trigger PR security reviews |
+  | `webhooks:read` / `:write` | manage webhook subscriptions |
+  | `tokens:write` | create/revoke API tokens |
+
+```bash
+export STRIX_API_TOKEN="<token>"
+BASE=https://app.strix.ai/api/v1
+auth=(-H "Authorization: Bearer $STRIX_API_TOKEN")
+```
+
+All examples use `jq` to parse JSON. Handle HTTP errors: `401` bad/expired token, `402` out of credits, `403` scope/plan-tier limit, `422` validation error.
+
+## 1. Register the target as an asset
+
+Scans run against **registered assets**, not raw URLs. Register once, then reuse the returned UUID.
+
+```bash
+# Domain (black-box / live target). Requires domain verification before external scanning.
+# asset_type must be one of: web_app | api | attack_surface.
+curl -sS "$BASE/domains" "${auth[@]}" -H "Content-Type: application/json" \
+  -d '{"domain":"staging.example.com","asset_type":"web_app"}' | jq '{id:.domain.id, status, reachable, verification}'
+
+# Repository (white-box / code review). `full_name` is "owner/name".
+# Send one repository object, or a bare JSON array for several — not an object
+# wrapping a "repositories" key (that is rejected with 400).
+curl -sS "$BASE/repositories" "${auth[@]}" -H "Content-Type: application/json" \
+  -d '[{"full_name":"org/app","provider":"github"}]' | jq '.repositories[] | {id, full_name}'
+```
+
+Look up existing assets instead of re-adding: `GET /domains`, `GET /repositories` (both `assets:read`, paginated with `?page=&limit=`).
+
+## 2. Launch a scan
+
+`POST /scans` (`scans:write`). Provide at least one target via `domain_ids`, `repository_ids`, or `internal_targets` (internal infra needs a network connector — see docs).
+
+```bash
+scan_id=$(curl -sS "$BASE/scans" "${auth[@]}" -H "Content-Type: application/json" -d '{
+  "engagement_type": "live_test",
+  "domain_ids": ["<domain-uuid>"],
+  "focus": "IDOR, auth bypass, SSRF",
+  "context": "Staging. Test account creds are configured as a test user.",
+  "notify_on_completion": true
+}' | jq -r .scan_id)
+echo "$scan_id"
+```
+
+Useful `CreateScanRequest` fields:
+
+| Field | Purpose |
+|---|---|
+| `engagement_type` | `live_test` (default), `code_review`, `internal_infra`, `compliance_pentest` |
+| `domain_ids` / `repository_ids` / `internal_targets` | targets (at least one) |
+| `domain_paths` / `repository_branches` | narrow to specific paths / branches |
+| `credentials` | authenticated scanning, incl. `mfa_method` (`totp`/`email_otp`/…) + `totp_secret` |
+| `headers` | extra HTTP headers (e.g. API keys) for the target |
+| `focus` / `concerns` / `context` | steer the agents |
+| `upload_ids` | attach uploaded source/docs archives for white-box context |
+| `notify_on_completion` / `notification_emails` | email when done |
+
+Response is `{ scan_id, title, status }` with `status` = `pending`.
+
+## 3. Poll to completion
+
+`GET /scans/{scanId}` (`scans:read`). Status flow: `pending → running → completed` (or `failed` / `cancelled`). Poll on an interval — scans take minutes to hours; don't block.
+
+```bash
+while :; do
+  s=$(curl -sS "$BASE/scans/$scan_id" "${auth[@]}" | jq -r .status)
+  echo "status=$s"; [[ "$s" =~ ^(completed|failed|cancelled)$ ]] && break
+  sleep 60
+done
+```
+
+## 4. Read findings
+
+The scan-detail response includes `executive_summary`, `methodology`, `recommendations`, a `findings` severity roll-up, and a `vulnerabilities[]` array. Each vulnerability carries `title, severity, status, cvss, cwe, endpoint, method, impact, technical_analysis, poc_description, poc_script_code`, and (for code findings) `code_file`/`code_diff`/`code_before`/`code_after`.
+
+```bash
+curl -sS "$BASE/scans/$scan_id" "${auth[@]}" \
+  | jq '["critical","high","medium","low","info"] as $order
+       | .vulnerabilities
+       | sort_by(.severity as $s | $order | index($s))
+       | .[] | {title, severity, endpoint, cwe}'
+```
+
+Cloud severities are `critical | high | medium | low` and statuses are `open | in_progress | fixed | ignored`. Sort by an explicit severity order rather than `sort_by(.severity)`, which sorts alphabetically (critical, high, low, medium).
+
+Org-wide triage across scans: `GET /vulnerabilities` (`vulnerabilities:read`; filter by severity/status). Update triage state with the vulnerabilities `:write` endpoints. To remediate, hand off to the **fix-security-vulnerabilities-with-strix** skill.
+
+## 5. Export & report
+
+```bash
+# SARIF 2.1.0 for GitHub code scanning / ASPM ingestion
+curl -sS "$BASE/scans/$scan_id/sarif" "${auth[@]}" -o findings.sarif
+
+# Report. The format and file type are query params (`Accept` is ignored):
+#   format=technical (default) | retest | attestation | executive_summary
+#   type=pdf (default) | docx
+# Any report download requires the Enterprise plan; formats beyond `technical`,
+# DOCX, and white-label branding are Enterprise-only too. Scan must be completed.
+curl -sS "$BASE/scans/$scan_id/report?format=technical&type=pdf" "${auth[@]}" -o strix-report.pdf
+```
+
+## 6. PR reviews
+
+Trigger an automated security review of a pull request (`pr_reviews:write`); results appear as PR comments and in the dashboard:
+
+```bash
+curl -sS "$BASE/pr-reviews/start" "${auth[@]}" -H "Content-Type: application/json" \
+  -d '{"repository_full_name":"org/app","pr_number":123}'
+```
+
+List/inspect via `GET /pr-reviews` and `GET /pr-reviews/{id}`. Repo-level PR-review behavior is configured with the repository-settings endpoint.
+
+## 7. Continuous testing (schedules & webhooks)
+
+- **Schedules** (`schedules:write`, Pro plan): create recurring scans and trigger them on demand — the managed equivalent of a cron-driven CLI loop.
+- **Webhooks** (`webhooks:write`): subscribe to pentest/vulnerability lifecycle events (e.g. `scan.completed`, `vulnerability.created`) to push results into Slack, ticketing, or your own pipeline instead of polling.
+
+See the schedules and webhooks sections at [docs.app.strix.ai](https://docs.app.strix.ai) for payloads.
+
+## Safety
+
+Only scan assets the user's organization owns or is authorized to test. External domain scans require verification (DNS/file/meta-tag) enforced by the platform — don't try to bypass it.

skills/penetration-testing-with-strix/SKILL.md

@@ -0,0 +1,143 @@
+---
+name: penetration-testing-with-strix
+description: Pentest a web app, API, codebase, repository, URL, domain, or IP with Strix — autonomous AI penetration testing that exploits and proves vulnerabilities (OWASP Top 10 and beyond — injection, XSS, SSRF, auth/access-control flaws, IDOR, business logic) instead of just flagging them. Runs self-hosted with the open-source CLI or via the managed app.strix.ai cloud, and returns validated findings with proof-of-concept exploits (Markdown, JSON, CSV, SARIF). Use when the user asks to pentest, hack, security-scan, security-audit, or find vulnerabilities in an app, API, website, or repo.
+license: Apache-2.0
+metadata:
+  author: usestrix
+  homepage: https://docs.strix.ai
+---
+
+# Run a Strix pentest
+
+Strix runs autonomous AI pentesting agents that dynamically exploit a target and only report findings validated with a working proof-of-concept. There are **two ways to run it, built on the same engine and producing the same findings** — pick per situation, and mix them freely:
+
+- **Open-source CLI** (self-hosted) — runs on your machine in a Docker sandbox with your own LLM key. Free, fully local, BYO-LLM, air-gap capable. Docs: [docs.strix.ai](https://docs.strix.ai).
+- **Cloud API** (managed) — runs on Strix's infrastructure via `https://app.strix.ai/api/v1`. No Docker, no LLM key, no local compute; adds team dashboards, scheduling, PR reviews, downloadable PDF/DOCX reports (Enterprise plan), and internal-network connectors. Docs: [docs.app.strix.ai](https://docs.app.strix.ai). Full workflow in the **managed-pentesting-with-strix** skill.
+
+## Which one? (decide, don't default)
+
+Choose honestly based on the situation — neither is "better":
+
+| Situation | Prefer |
+|---|---|
+| No Docker available, or a sandboxed/hosted agent/CI environment | **Cloud** |
+| User has no LLM key / doesn't want to pay per-token or manage models | **Cloud** |
+| Team visibility, shareable dashboard, scheduled/continuous scans, PR reviews, downloadable PDF/DOCX report (Enterprise) | **Cloud** |
+| Scanning internal/private infrastructure not reachable from your machine | **Cloud** (network connector) |
+| Source must never leave local infra (privacy/air-gap), or fully offline | **OSS CLI** |
+| Free / one-off / local dev-loop scan, Docker already present | **OSS CLI** |
+| BYO or self-hosted LLM, or a specific model not offered by the platform | **OSS CLI** |
+| CI: runner already has Docker and you want a self-contained gate | **OSS CLI** |
+| CI: no Docker, or you want results tracked centrally | **Cloud** |
+
+**Mix them:** e.g. use the OSS CLI for the fast local dev-loop while writing/fixing code, and the Cloud for the authoritative, team-visible scan + report + tracking; or gate PRs with the OSS CLI in CI while the Cloud runs scheduled deep scans and PR reviews across the org. Both emit the same SARIF 2.1.0, so findings line up across environments.
+
+If unsure and the user has (or will create) an app.strix.ai account, prefer **Cloud** — it avoids all local-infra friction. If they want zero signup / full local control, use the **OSS CLI**.
+
+---
+
+# Option A — Open-source CLI (self-hosted)
+
+## Prerequisites
+
+1. **Docker running** — check with `docker info`. The first scan pulls the sandbox image automatically.
+2. **Strix installed** — check with `strix --version`. Install if missing:
+   ```bash
+   curl -sSL https://strix.ai/install | bash   # or: pipx install strix-agent
+   ```
+3. **LLM configured** — two environment variables:
+   ```bash
+   export STRIX_LLM="openai/gpt-5.4"      # any LiteLLM model id (openai/..., anthropic/..., openrouter/...)
+   export LLM_API_KEY="<provider api key>"
+   ```
+   Ask the user for these if unset. Never hardcode or commit keys.
+
+## Running a scan
+
+Always use `-n` (non-interactive/headless) — the default TUI blocks agents. Always set `--max-budget` unless the user says otherwise.
+
+```bash
+# Local code (white-box)
+strix -n -t ./ --scan-mode standard --max-budget 10
+
+# Deployed app / API (black-box)
+strix -n -t https://staging.example.com --max-budget 20
+
+# Repo + deployed app together (best coverage)
+strix -n -t https://github.com/org/app -t https://staging.example.com
+
+# Focused testing with credentials or scope hints
+strix -n -t https://app.example.com \
+  --instruction "Use credentials user@example.com:pass123. Focus on IDOR and auth bypass."
+
+# Large monorepo: bind-mount instead of copying
+strix -n --mount ./huge-monorepo
+```
+
+Key flags:
+
+| Flag | Meaning |
+|---|---|
+| `-t, --target` | URL, repo URL, local path, domain, or IP. Repeatable. |
+| `-n, --non-interactive` | Headless, exits on completion. Required for agents. |
+| `-m, --scan-mode` | `quick` (minutes) / `standard` (~30 min) / `deep` (hours, default). |
+| `--instruction` / `--instruction-file` | Credentials, focus areas, scope rules. |
+| `--max-budget USD` | Hard LLM spend cap; scan wraps up cleanly at the limit. |
+| `--max-turns N` | Per-agent turn cap (default 500). |
+| `--resume RUN_NAME` | Resume a prior run from `strix_runs/`. |
+
+Scans take minutes (`quick`) to hours (`deep`). Run them in the background and poll for completion rather than blocking.
+
+### Exit codes (headless)
+
+- `0` — finished with no validated vulnerabilities **in what was analyzed**
+- `1` — fatal error (missing env vars, Docker down, bad config)
+- `2` — vulnerabilities found
+
+A `0` is not proof of full coverage: if `--max-budget`/`--max-turns` is reached before the scan completes, it wraps up early and still exits `0`. When you need assurance the scan finished, give it enough budget and check `strix_runs/<run>/run.json`: a hard budget stop leaves `status: "stopped"`, but an agent that wrapped up early on a budget *warning* still calls `finish_scan` and records `"completed"` — so also sanity-check the run's cost against `--max-budget` and the report's stated coverage before treating a clean result as full coverage.
+
+### Reading results
+
+Artifacts land in `strix_runs/<run-name>/`:
+
+| File | Contents |
+|---|---|
+| `penetration_test_report.md` | Executive report — read this first. |
+| `vulnerabilities/*.md` | One file per validated finding, with PoC and remediation. |
+| `vulnerabilities.json` / `vulnerabilities.csv` | All findings as structured JSON / CSV index. |
+| `findings.sarif` | SARIF 2.1.0 for GitHub code scanning / ASPM ingestion. |
+| `run.json` | Run metadata, status, targets, usage/cost. |
+
+---
+
+# Option B — Cloud API (managed, no local infra)
+
+Full details, asset registration, polling, reports, PR reviews, schedules, and webhooks are in the **managed-pentesting-with-strix** skill. Minimal launch-and-poll:
+
+```bash
+export STRIX_API_TOKEN="<token>"   # org-scoped bearer, from Settings → API Access at app.strix.ai
+BASE=https://app.strix.ai/api/v1
+
+# 1. Launch a scan against an already-registered domain/repo asset
+scan_id=$(curl -sS "$BASE/scans" \
+  -H "Authorization: Bearer $STRIX_API_TOKEN" -H "Content-Type: application/json" \
+  -d '{"engagement_type":"live_test","domain_ids":["<domain-uuid>"]}' | jq -r .scan_id)
+
+# 2. Poll until terminal (pending → running → completed/failed/cancelled)
+curl -sS "$BASE/scans/$scan_id" -H "Authorization: Bearer $STRIX_API_TOKEN" | jq '.status'
+
+# 3. Read validated findings from the scan detail's `vulnerabilities[]`, or export SARIF
+curl -sS "$BASE/scans/$scan_id/sarif" -H "Authorization: Bearer $STRIX_API_TOKEN" -o findings.sarif
+```
+
+Ask the user to create the token (and register the target as a domain/repository asset) if they haven't. If Docker/local prerequisites aren't already satisfied, use this path instead of trying to install infra.
+
+---
+
+## Reporting & next steps
+
+Summarize findings by severity (critical/high/medium/low/info) and include the PoC evidence. To remediate and verify fixes (via either path), use the **fix-security-vulnerabilities-with-strix** skill. To wire scanning into CI/CD, use the **ci-security-scanning-with-strix** skill.
+
+## Safety
+
+Only scan targets the user owns or is authorized to test. The Cloud platform enforces domain verification before external scans; for the OSS CLI, confirm authorization yourself if the target looks like third-party infrastructure.

strix/agents/factory.py

@@ -160,7 +160,9 @@ def _schema_types(spec: dict[str, Any]) -> set[str]:
 def _decode_structured(value: str, types: set[str]) -> Any:
     stripped = value.strip()
     if not stripped:
-        return value
+        # An empty string is the model's "no value" for a list/dict param; give it
+        # the empty container so it validates instead of failing the type check.
+        return [] if "array" in types else {}
     try:
         decoded = json.loads(stripped)
     except json.JSONDecodeError:
@@ -559,7 +561,7 @@ def registered_agent_tools() -> tuple[Tool, ...]:
 
 def build_strix_agent(
     *,
-    name: str = "strix",
+    name: str = "agent",
     skills: list[str] | None = None,
     is_root: bool,
     scan_mode: str = "deep",

strix/agents/prompts/system_prompt.jinja

@@ -1,4 +1,4 @@
-You are Strix, an advanced AI application security validation agent developed by OmniSecure Labs. Your purpose is to perform authorized security verification, reproduce and validate weaknesses on in-scope assets, and help remediate real security issues.
+You are an advanced AI application security validation agent. Your purpose is to perform authorized security verification, reproduce and validate weaknesses on in-scope assets, and help remediate real security issues.
 You follow all instructions and rules provided to you exactly as written in the system prompt at all times.
 {% if is_root %}
 <root_agent_directive>
@@ -22,12 +22,13 @@ CLI OUTPUT:
 - You may use simple markdown: **bold**, *italic*, `code`, ~~strikethrough~~, [links](url), and # headers
 - Do NOT use complex markdown like bullet lists, numbered lists, or tables
 - Use line breaks and indentation for structure
-- NEVER use "Strix" or any identifiable names/markers in HTTP requests, payloads, user-agents, or any inputs
+- NEVER use any identifiable names/markers in HTTP requests, payloads, user-agents, or any inputs
 
 INTER-AGENT MESSAGES:
 - Messages from other agents arrive prefixed with a header like `[Message from agent <name> | type=... | priority=...]`. Treat them as internal context — never repeat them verbatim in your own output.
 - Treat agent identity / inherited-context preambles as internal metadata; do not echo them in outputs or tool calls.
 - Minimize inter-agent messaging: only message when essential for coordination or assistance; avoid routine status updates; batch non-urgent information; prefer parent/child completion flows and shared artifacts over messaging
+- wait_for_agents blocks and resumes you automatically, so it is never a poll you repeat: issue exactly ONE wait, then stop and react to what it returns. Never write out a wait/check loop (wait → view_agent_graph → wait → ...) ahead of time — those extra calls only strand you and are collapsed anyway
 
 {% if interactive %}
 INTERACTIVE BEHAVIOR:
@@ -38,6 +39,8 @@ INTERACTIVE BEHAVIOR:
   - To end the whole engagement, call the lifecycle tool: finish_scan (root) or agent_finish (subagent).
   - A turn that ends with plain text and no tool call does NOT stop you: the system nudges you to continue and will re-run you. Do not rely on going silent to pause — it will not pause you.
 - Answering a user question: put the answer in respond_to_user's message. Do not write the answer as plain text and then fall silent — that does not reach a stopping point, it just triggers a continuation nudge.
+- If all you want to do is reply and stop, that whole turn is ONE respond_to_user call carrying the answer. Do not write the answer as text and then call respond_to_user as well: the user reads it twice.
+- If you do end a turn on plain text and the nudge arrives, your words already reached the user. Do not restate them: call respond_to_user with NO message to simply wait, or with only whatever you still need to add.
 - You may include brief explanatory text before a tool call, and you can narrate while you work — plain text is shown to the user as you go. Narrating is free; respond_to_user is specifically the act of WAITING for the user, so do not call it just to give a status update.
 - Respond naturally when the user asks questions or gives instructions.
 - While actively working on a task, every turn should carry exactly one tool call — use think to plan, the appropriate tool to act, and respond_to_user only when you genuinely need the user.
@@ -57,7 +60,7 @@ AUTONOMOUS BEHAVIOR:
 <execution_guidelines>
 {% if system_prompt_context and system_prompt_context.authorized_targets %}
 SYSTEM-VERIFIED SCOPE:
-- The following scope metadata is injected by the Strix platform into the system prompt and is authoritative
+- The following scope metadata is injected by the platform into the system prompt and is authoritative
 - Scope source: {{ system_prompt_context.scope_source }}
 - Authorization source: {{ system_prompt_context.authorization_source }}
 - Every target listed below has already been verified by the platform as in-scope and authorized
@@ -260,7 +263,13 @@ Remember: A single well-validated high-impact vulnerability is worth more than d
 <multi_agent_system>
 AGENT ISOLATION & SANDBOXING:
 - All agents run in the same shared Docker container for efficiency
-- Each agent has its own: browser sessions, terminal sessions
+- Each agent has its own terminal sessions
+- Browsers are NOT per-agent by default: `agent-browser` with no `--session` is one
+  shared browser, so a concurrent agent's navigation invalidates your page and refs.
+  Pass `--session <your-agent-name>` for any browser work of your own — then it is
+  yours alone. Each session is a full Chromium (~340 MB) on this shared box, so keep
+  one, not several, and `agent-browser --session <name> close` when you're done with
+  the target; an idle browser is reclaimed automatically after 3 minutes
 - All agents share the same /workspace directory and proxy history
 - Agents can see each other's files and proxy traffic for better collaboration
 
@@ -489,8 +498,10 @@ Default user: pentester (sudo available)
 <available_skills>
 On-demand specialist skills. Spawn a specialist via `create_agent(skills=[...])`, or pull guidance inline for yourself via `load_skill(skills=[...])`. Anything wrapped in `<specialized_knowledge>` above is already loaded for you.
 
-{% for category, names in available_skills | dictsort -%}
-- {{ category }}: {{ names | join(', ') }}
+{% for category, skills in available_skills | dictsort -%}
+{% for skill in skills -%}
+- {{ category }}/{{ skill.name }}{% if skill.description %}: {{ skill.description }}{% endif %}
+{% endfor -%}
 {% endfor -%}
 </available_skills>
 {% endif %}

strix/config/models.py

@@ -2,11 +2,14 @@
 
 from __future__ import annotations
 
+import asyncio
 import contextlib
 import inspect
+import logging
 import os
 import time
-from typing import TYPE_CHECKING, Any
+from collections.abc import AsyncGenerator
+from typing import TYPE_CHECKING, Any, cast
 
 from agents import (
     set_default_openai_api,
@@ -24,12 +27,19 @@ from agents.retry import (
     RetryPolicyContext,
     retry_policies,
 )
-from openai.types.responses import Response, ResponseCompletedEvent
+from openai.types.responses import (
+    Response,
+    ResponseCompletedEvent,
+    ResponseOutputItemAddedEvent,
+    ResponseOutputItemDoneEvent,
+)
 from openai.types.responses.response_usage import ResponseUsage
 from openai.types.shared import Reasoning
 
 from strix.config import codex
 from strix.config.loader import load_settings
+from strix.config.tool_call_ids import TurnCallIdRewriter, dedupe_input
+from strix.config.tool_call_limits import TurnToolCallLimiter
 
 
 if TYPE_CHECKING:
@@ -48,6 +58,9 @@ if TYPE_CHECKING:
     from strix.config.settings import LlmSettings, ReasoningEffort, Settings
 
 
+logger = logging.getLogger(__name__)
+
+
 def request_timeout_extra_args(timeout_s: float | None) -> dict[str, float] | None:
     """Per-request model timeout; a plain float so ``ModelSettings.to_json_dict()`` stays serializable."""  # noqa: E501
     if not timeout_s or timeout_s <= 0:
@@ -229,6 +242,170 @@ class _NonStreamingModel(Model):
         yield _completed_stream_event(response, getattr(self._inner, "model", None))
 
 
+class _TurnGuardModel(Model):
+    """Keep one turn from corrupting the conversation or running away.
+
+    Tool-call ids: providers that number calls per turn (``exec_command:0``,
+    ...) restart the counter each turn, so the same id eventually appears twice
+    in one conversation and strict providers reject every subsequent request.
+    Ids that collide with the history are rewritten before the turn is
+    recorded, and already-corrupted histories are repaired on the way out.
+
+    Tool-call volume: a degenerate response can queue hundreds of calls that
+    the run loop then honours one by one. Only the first
+    ``LLM_MAX_TOOL_CALLS_PER_TURN`` calls of a response are kept.
+
+    Stalled streams: a turn that emits a few tokens and then goes silent is
+    not covered by the request timeout, which resets on any byte (keepalives
+    included). ``LLM_STREAM_IDLE_TIMEOUT`` bounds the gap between events so the
+    turn fails instead of hanging, and the existing retry path replays it.
+    """
+
+    def __init__(
+        self,
+        inner: Model,
+        *,
+        max_tool_calls_per_turn: int = 0,
+        stream_idle_timeout: float = 0.0,
+    ) -> None:
+        self._inner = inner
+        self._max_tool_calls_per_turn = max_tool_calls_per_turn
+        self._stream_idle_timeout = stream_idle_timeout
+
+    def _limiter(self) -> TurnToolCallLimiter:
+        return TurnToolCallLimiter(self._max_tool_calls_per_turn)
+
+    def _log_dropped(self, limiter: TurnToolCallLimiter) -> None:
+        if limiter.dropped:
+            logger.warning(
+                "dropped %d tool call(s) past the per-response limit of %d",
+                limiter.dropped,
+                self._max_tool_calls_per_turn,
+            )
+
+    async def close(self) -> None:
+        await self._inner.close()
+
+    def get_retry_advice(self, request: ModelRetryAdviceRequest) -> ModelRetryAdvice | None:
+        return self._inner.get_retry_advice(request)
+
+    async def get_response(
+        self,
+        system_instructions: str | None,
+        input: str | list[TResponseInputItem],  # noqa: A002
+        model_settings: ModelSettings,
+        tools: list[Tool],
+        output_schema: AgentOutputSchemaBase | None,
+        handoffs: list[Handoff],
+        tracing: ModelTracing,
+        *,
+        previous_response_id: str | None,
+        conversation_id: str | None,
+        prompt: ResponsePromptParam | None,
+    ) -> ModelResponse:
+        sanitized = dedupe_input(input)
+        rewriter = TurnCallIdRewriter(sanitized)
+        response = await self._inner.get_response(
+            system_instructions,
+            cast("str | list[TResponseInputItem]", sanitized),
+            model_settings,
+            tools,
+            output_schema,
+            handoffs,
+            tracing,
+            previous_response_id=previous_response_id,
+            conversation_id=conversation_id,
+            prompt=prompt,
+        )
+        limiter = self._limiter()
+        response.output = limiter.filter_items(rewriter.rewrite_items(list(response.output)))
+        self._log_dropped(limiter)
+        return response
+
+    async def stream_response(
+        self,
+        system_instructions: str | None,
+        input: str | list[TResponseInputItem],  # noqa: A002
+        model_settings: ModelSettings,
+        tools: list[Tool],
+        output_schema: AgentOutputSchemaBase | None,
+        handoffs: list[Handoff],
+        tracing: ModelTracing,
+        *,
+        previous_response_id: str | None,
+        conversation_id: str | None,
+        prompt: ResponsePromptParam | None,
+    ) -> AsyncIterator[TResponseStreamEvent]:
+        sanitized = dedupe_input(input)
+        rewriter = TurnCallIdRewriter(sanitized)
+        limiter = self._limiter()
+        stream = self._inner.stream_response(
+            system_instructions,
+            cast("str | list[TResponseInputItem]", sanitized),
+            model_settings,
+            tools,
+            output_schema,
+            handoffs,
+            tracing,
+            previous_response_id=previous_response_id,
+            conversation_id=conversation_id,
+            prompt=prompt,
+        )
+        async for event in _with_idle_timeout(stream, self._stream_idle_timeout):
+            guarded = _guard_event(event, rewriter, limiter)
+            if guarded is not None:
+                yield guarded
+        self._log_dropped(limiter)
+
+
+async def _aclose(stream: AsyncIterator[TResponseStreamEvent]) -> None:
+    if isinstance(stream, AsyncGenerator):
+        with contextlib.suppress(Exception):
+            await stream.aclose()
+
+
+async def _with_idle_timeout(
+    stream: AsyncIterator[TResponseStreamEvent], timeout: float
+) -> AsyncIterator[TResponseStreamEvent]:
+    if timeout <= 0:
+        async for event in stream:
+            yield event
+        return
+
+    iterator = stream.__aiter__()
+    while True:
+        try:
+            event = await asyncio.wait_for(iterator.__anext__(), timeout)
+        except StopAsyncIteration:
+            return
+        except TimeoutError:
+            await _aclose(stream)
+            message = f"model stream produced no event for {timeout:.0f}s"
+            logger.warning("%s; abandoning the turn", message)
+            raise TimeoutError(message) from None
+        yield event
+
+
+def _guard_event(
+    event: TResponseStreamEvent, rewriter: TurnCallIdRewriter, limiter: TurnToolCallLimiter
+) -> TResponseStreamEvent | None:
+    if isinstance(event, ResponseOutputItemAddedEvent | ResponseOutputItemDoneEvent):
+        rewritten = rewriter.rewrite_item(event.item)
+        if not limiter.allow(rewritten):
+            return None
+        if rewritten is not event.item:
+            return event.model_copy(update={"item": rewritten})
+        return event
+    if isinstance(event, ResponseCompletedEvent):
+        original = list(event.response.output)
+        output = limiter.filter_items(rewriter.rewrite_items(original))
+        if output != original:
+            return event.model_copy(
+                update={"response": event.response.model_copy(update={"output": output})}
+            )
+    return event
+
+
 def _completed_stream_event(
     model_response: ModelResponse, model_name: object | None
 ) -> TResponseStreamEvent:
@@ -294,19 +471,29 @@ class StrixProvider(MultiProvider):
     def get_model(self, model_name: str | None) -> Model:
         llm = load_settings().llm
         slug = codex.subscription_model(model_name)
+        idle_timeout = float(llm.stream_idle_timeout)
         if slug:
             # The ChatGPT subscription backend is always streamed; it has no
             # non-streaming mode to fall back to, so LLM_DISABLE_STREAMING
             # does not apply here.
-            return _CodexResponsesModel(
+            model: Model = _CodexResponsesModel(
                 slug,
                 codex.get_subscription_client(),
                 reasoning_effort=llm.reasoning_effort,
             )
-        model = super().get_model(model_name)
-        if llm.disable_streaming:
-            return _NonStreamingModel(model)
-        return model
+        else:
+            model = super().get_model(model_name)
+            if llm.disable_streaming:
+                model = _NonStreamingModel(model)
+                # The wrapper emits its single event only once the whole request
+                # is done, so an idle gap is meaningless here; the request
+                # timeout bounds it instead.
+                idle_timeout = 0.0
+        return _TurnGuardModel(
+            model,
+            max_tool_calls_per_turn=llm.max_tool_calls_per_turn,
+            stream_idle_timeout=idle_timeout,
+        )
 
 
 DEFAULT_MODEL_RETRY = ModelRetrySettings(
@@ -465,27 +652,31 @@ def _install_openrouter_stream_cost_capture() -> None:
     litellm.OpenrouterConfig = _StrixOpenrouterConfig  # type: ignore[misc]
 
 
-_OPENROUTER_ATTRIBUTION_HEADERS = {
+OPENROUTER_ATTRIBUTION_HEADERS = {
     "HTTP-Referer": "https://strix.ai",
     "X-Title": "Strix",
     "X-OpenRouter-Categories": "cli-agent",
 }
 
 
+def is_openrouter_model(model_name: str | None) -> bool:
+    return bool(model_name) and "openrouter/" in (model_name or "").strip().lower()
+
+
 def _configure_openrouter_attribution(model_name: str | None) -> None:
     import litellm
 
     current: object = litellm.headers
     existing: dict[str, str] = current if isinstance(current, dict) else {}
-    if not model_name or "openrouter/" not in model_name.strip().lower():
-        if any(key in existing for key in _OPENROUTER_ATTRIBUTION_HEADERS):
+    if not is_openrouter_model(model_name):
+        if any(key in existing for key in OPENROUTER_ATTRIBUTION_HEADERS):
             remaining = {
-                k: v for k, v in existing.items() if k not in _OPENROUTER_ATTRIBUTION_HEADERS
+                k: v for k, v in existing.items() if k not in OPENROUTER_ATTRIBUTION_HEADERS
             }
             litellm.headers = remaining or None  # type: ignore[assignment]
         return
 
-    litellm.headers = {**existing, **_OPENROUTER_ATTRIBUTION_HEADERS}  # type: ignore[assignment]
+    litellm.headers = {**existing, **OPENROUTER_ATTRIBUTION_HEADERS}  # type: ignore[assignment]
 
 
 def _configure_extra_headers(llm: LlmSettings) -> None:

strix/config/settings.py

@@ -57,6 +57,12 @@ class LlmSettings(BaseSettings):
         alias="LLM_DISABLE_STREAMING",
     )
     timeout: int = Field(default=300, alias="LLM_TIMEOUT")
+    stream_idle_timeout: int = Field(default=300, ge=0, alias="LLM_STREAM_IDLE_TIMEOUT")
+    max_tool_calls_per_turn: int = Field(
+        default=32,
+        ge=0,
+        alias="LLM_MAX_TOOL_CALLS_PER_TURN",
+    )
 
 
 class DedupeSettings(BaseSettings):
@@ -100,7 +106,7 @@ class RuntimeSettings(BaseSettings):
     model_config = _BASE_CONFIG
 
     image: str = Field(
-        default="ghcr.io/usestrix/strix-sandbox:1.2.0",
+        default="ghcr.io/usestrix/strix-sandbox:1.3.0",
         alias="STRIX_IMAGE",
     )
     backend: str = Field(default="docker", alias="STRIX_RUNTIME_BACKEND")

strix/config/tool_call_ids.py

@@ -0,0 +1,117 @@
+"""Keep tool-call ids unique within a conversation.
+
+Some providers return per-turn tool-call ids (``exec_command:0``,
+``exec_command:1``, ...) whose counter restarts on every turn. Once the same
+id appears twice in one conversation, the request payload has two assistant
+tool calls sharing an id and strict providers reject the whole turn, which
+permanently kills the agent because the malformed history is replayed on
+every retry. Rewriting duplicates to fresh unique ids keeps the history
+valid for any provider.
+"""
+
+from __future__ import annotations
+
+from collections import defaultdict, deque
+from typing import Any
+from uuid import uuid4
+
+from openai.types.responses import ResponseFunctionToolCall
+
+
+def new_call_id() -> str:
+    return f"call_{uuid4().hex}"
+
+
+def collect_call_ids(items: list[Any]) -> set[str]:
+    used: set[str] = set()
+    for item in items:
+        if isinstance(item, dict):
+            call_id = item.get("call_id")
+            if isinstance(call_id, str):
+                used.add(call_id)
+        elif isinstance(item, ResponseFunctionToolCall):
+            used.add(item.call_id)
+    return used
+
+
+def dedupe_history_call_ids(items: list[Any]) -> tuple[list[Any], bool]:
+    """Rewrite duplicate call ids in a conversation history.
+
+    Outputs are paired with their call by order, so parallel calls that share
+    an id keep answering the right call after the rewrite.
+    """
+    used: set[str] = set()
+    pending: dict[str, deque[str]] = defaultdict(deque)
+    rebuilt: list[Any] = []
+    changed = False
+
+    for item in items:
+        if not isinstance(item, dict):
+            rebuilt.append(item)
+            continue
+        call_id = item.get("call_id")
+        if not isinstance(call_id, str):
+            rebuilt.append(item)
+            continue
+
+        kind = item.get("type")
+        if kind == "function_call":
+            effective = call_id
+            if call_id in used:
+                effective = new_call_id()
+                item = {**item, "call_id": effective}  # noqa: PLW2901
+                changed = True
+            used.add(effective)
+            pending[call_id].append(effective)
+        elif kind == "function_call_output":
+            queue = pending.get(call_id)
+            if queue:
+                effective = queue.popleft()
+                if effective != call_id:
+                    item = {**item, "call_id": effective}  # noqa: PLW2901
+                    changed = True
+        rebuilt.append(item)
+
+    return rebuilt, changed
+
+
+def dedupe_input(model_input: str | list[Any]) -> str | list[Any]:
+    if isinstance(model_input, str):
+        return model_input
+    rebuilt, changed = dedupe_history_call_ids(model_input)
+    return rebuilt if changed else model_input
+
+
+class TurnCallIdRewriter:
+    """Rewrite a single turn's tool-call ids that collide with the history.
+
+    A turn's items surface several times (streamed item events, then the
+    completed response), so the same original id must always map to the same
+    replacement within the turn.
+    """
+
+    def __init__(self, model_input: str | list[Any]) -> None:
+        self._used = set() if isinstance(model_input, str) else collect_call_ids(model_input)
+        self._remap: dict[str, str] = {}
+        self._settled: set[str] = set()
+
+    def rewrite_item(self, item: Any) -> Any:
+        if not isinstance(item, ResponseFunctionToolCall):
+            return item
+        original = item.call_id
+        if original in self._settled:
+            return item
+        replacement = self._remap.get(original)
+        if replacement is None:
+            if original not in self._used:
+                self._used.add(original)
+                self._settled.add(original)
+                return item
+            replacement = new_call_id()
+            self._remap[original] = replacement
+            self._used.add(replacement)
+            self._settled.add(replacement)
+        return item.model_copy(update={"call_id": replacement})
+
+    def rewrite_items(self, items: list[Any]) -> list[Any]:
+        return [self.rewrite_item(item) for item in items]

strix/config/tool_call_limits.py

@@ -0,0 +1,46 @@
+"""Bound how many tool calls one assistant response may queue.
+
+A degenerate generation can emit hundreds or thousands of tool calls in a
+single response — typically a poll/wait loop the model writes out ahead of
+time instead of issuing one call and yielding. The run loop honours all of
+them, so the agent stops reacting to anything for hours. Keeping only the
+first ``limit`` calls of a response bounds that blast radius; the model sees
+their results on the next turn and can reconsider.
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+from openai.types.responses import ResponseFunctionToolCall
+
+
+class TurnToolCallLimiter:
+    """Decide, once per call, whether a turn's tool call is within the limit."""
+
+    def __init__(self, limit: int) -> None:
+        self._limit = limit
+        self._decisions: dict[str, bool] = {}
+        self._kept = 0
+        self.dropped = 0
+
+    @property
+    def enabled(self) -> bool:
+        return self._limit > 0
+
+    def allow(self, item: Any) -> bool:
+        if not self.enabled or not isinstance(item, ResponseFunctionToolCall):
+            return True
+        decided = self._decisions.get(item.call_id)
+        if decided is not None:
+            return decided
+        allowed = self._kept < self._limit
+        if allowed:
+            self._kept += 1
+        else:
+            self.dropped += 1
+        self._decisions[item.call_id] = allowed
+        return allowed
+
+    def filter_items(self, items: list[Any]) -> list[Any]:
+        return [item for item in items if self.allow(item)]

strix/core/execution.py

@@ -830,7 +830,7 @@ async def _append_tool_required_message(
             "execution and never hands control to the user: it is shown to the user, and the "
             "run continues. Continue immediately and call exactly one tool. "
             "If you have something to tell the user and nothing to do until they reply, "
-            "call respond_to_user. "
+            "call respond_to_user — with no message if you have already said it. "
             "If you are blocked waiting for another agent, call wait_for_agents. "
             f"If the whole engagement is complete, call {finish_tool}. "
             "Otherwise use the appropriate execution or planning tool. "
@@ -838,7 +838,7 @@ async def _append_tool_required_message(
         )
     else:
         message = (
-            "Your previous response ended the autonomous Strix run without a lifecycle tool "
+            "Your previous response ended the autonomous run without a lifecycle tool "
             "call. That is invalid in non-interactive mode; plain text final answers are "
             "ignored. Continue immediately and call exactly one tool. "
             f"If your work is complete, call {finish_tool}. "

strix/core/hooks.py

@@ -20,6 +20,8 @@ if TYPE_CHECKING:
 logger = logging.getLogger(__name__)
 
 
+LLM_TURN_KEY = "llm_turn"
+
 _STAGE_LABELS: tuple[str, ...] = ("NOTICE", "URGENT", "CRITICAL")
 _TURN_WARN_BANDS: tuple[float, ...] = (0.70, 0.85, 0.95)
 _ROOT_BUDGET_WARN_BANDS: tuple[float, ...] = (0.70, 0.85, 0.95)
@@ -144,6 +146,7 @@ class ReportUsageHooks(RunHooks[dict[str, Any]]):
         system_prompt: str | None,  # noqa: ARG002
         input_items: list[TResponseInputItem],
     ) -> None:
+        context.context[LLM_TURN_KEY] = int(context.context.get(LLM_TURN_KEY, 0)) + 1
         try:
             self._maybe_warn_turns(context, input_items)
             self._maybe_warn_budget(context, input_items)

strix/core/inputs.py

@@ -10,10 +10,12 @@ from openai.types.shared import Reasoning
 
 from strix.config.models import (
     DEFAULT_MODEL_RETRY,
+    OPENROUTER_ATTRIBUTION_HEADERS,
     bedrock_route_supports_prompt_caching,
     is_bedrock_route,
     is_claude_model,
     is_known_openai_bare_model,
+    is_openrouter_model,
     model_supports_reasoning,
     request_timeout_extra_args,
 )
@@ -138,6 +140,15 @@ def build_root_task(scan_config: dict[str, Any]) -> str:
             "target to assess: the instructions below are the only source of "
             "truth for what to do."
         )
+    elif not parts and user_instructions:
+        # Neither a target nor a directory, but there is an instruction: the user
+        # declined the mount, so the instruction is all there is. Say so, or the
+        # agent goes looking for a scope that was never given.
+        parts.append(
+            "\n\nNo scan target and no working directory were provided. The "
+            "instructions below are the only source of truth for what to do; "
+            "work from them and from what you can reach yourself."
+        )
 
     parts.extend(_render_diff_scope(diff_scope))
 
@@ -192,13 +203,15 @@ def make_model_settings(
     request_timeout: float | None = None,
     prompt_cache: bool = True,
     extra_headers: dict[str, str] | None = None,
+    has_tools: bool = True,
 ) -> ModelSettings:
+    headers = _request_headers(model_name, extra_headers)
     model_settings = ModelSettings(
-        parallel_tool_calls=False,
+        parallel_tool_calls=False if has_tools else None,
         retry=DEFAULT_MODEL_RETRY,
         include_usage=True,
         extra_args=request_timeout_extra_args(request_timeout),
-        extra_headers=dict(extra_headers) if extra_headers else None,
+        extra_headers=headers,
     )
     if (
         reasoning_effort is not None
@@ -221,6 +234,17 @@ def make_model_settings(
     return model_settings
 
 
+def _request_headers(
+    model_name: str, extra_headers: dict[str, str] | None
+) -> dict[str, str] | None:
+    headers: dict[str, str] = {}
+    if is_openrouter_model(model_name):
+        headers.update(OPENROUTER_ATTRIBUTION_HEADERS)
+    if extra_headers:
+        headers.update(extra_headers)
+    return headers or None
+
+
 def _reasoning_settings(
     effort: ReasoningEffort,
     extra_args: dict[str, Any] | None,

strix/core/runner.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import asyncio
 import contextlib
 import io
 import json
@@ -293,7 +294,7 @@ async def run_strix_scan(
         )
 
         root_agent = build_strix_agent(
-            name="Strix",
+            name="Root Agent",
             skills=skills,
             is_root=True,
             scan_mode=scan_mode,
@@ -307,7 +308,7 @@ async def run_strix_scan(
         if not is_resume:
             await coordinator.register(
                 root_id,
-                "Strix",
+                "Root Agent",
                 parent_id=None,
                 task=root_task,
                 skills=skills,
@@ -429,7 +430,6 @@ async def run_strix_scan(
     except BudgetExceededError as exc:
         logger.info("Scan %s stopped: %s", scan_id, exc)
         if root_id is not None:
-            await coordinator.cancel_descendants(root_id)
             with contextlib.suppress(Exception):
                 await coordinator.set_status(root_id, "stopped")
         return None
@@ -442,19 +442,28 @@ async def run_strix_scan(
             scan_id,
         )
         if root_id is not None:
-            await coordinator.cancel_descendants(root_id)
             with contextlib.suppress(Exception):
                 await coordinator.set_status(root_id, "stopped")
         return None
+    except (asyncio.CancelledError, KeyboardInterrupt):
+        logger.info("Scan %s interrupted by the user", scan_id)
+        if root_id is not None:
+            with contextlib.suppress(Exception):
+                await coordinator.set_status(root_id, "running")
+        raise
     except BaseException:
         logger.exception("Strix scan %s failed", scan_id)
         if root_id is not None:
-            await coordinator.cancel_descendants(root_id)
             with contextlib.suppress(Exception):
                 await coordinator.set_status(root_id, "failed")
         raise
     finally:
         configure_spill_writer(None)
+        # Settle descendants before closing sessions: on a clean finish a child
+        # can still be mid-turn, and closing its session underneath it crashes it.
+        if root_id is not None:
+            with contextlib.suppress(Exception):
+                await coordinator.cancel_descendants(root_id)
         for s in sessions_to_close:
             with contextlib.suppress(Exception):
                 s.close()

strix/core/sessions.py

@@ -4,6 +4,8 @@ from __future__ import annotations
 
 import asyncio
 import logging
+import sqlite3
+from contextlib import contextmanager
 from typing import TYPE_CHECKING, Any, cast
 from weakref import WeakKeyDictionary
 
@@ -12,7 +14,7 @@ from agents.memory import SQLiteSession
 
 
 if TYPE_CHECKING:
-    from collections.abc import Callable
+    from collections.abc import Callable, Iterator
     from pathlib import Path
 
     from agents.items import TResponseInputItem
@@ -22,9 +24,25 @@ if TYPE_CHECKING:
 logger = logging.getLogger(__name__)
 
 
+class _PooledConnectionSession(SQLiteSession):
+    @contextmanager
+    def _locked_connection(self) -> Iterator[sqlite3.Connection]:
+        with self._lock:
+            if self._closed:
+                raise RuntimeError("SQLiteSession is closed")
+            if self._is_memory_db:
+                yield self._shared_connection
+                return
+            connection = sqlite3.connect(str(self.db_path), check_same_thread=False)
+            try:
+                yield connection
+            finally:
+                connection.close()
+
+
 def open_agent_session(agent_id: str, path: Path) -> SQLiteSession:
     path.parent.mkdir(parents=True, exist_ok=True)
-    return SQLiteSession(session_id=agent_id, db_path=path)
+    return _PooledConnectionSession(session_id=agent_id, db_path=path)
 
 
 async def seed_initial_input(session: Session, initial_input: Any) -> bool:

strix/interface/cli_args.py

@@ -328,10 +328,11 @@ def _load_resume_state(args: argparse.Namespace, parser: argparse.ArgumentParser
         parser.error(f"--resume {args.resume}: run.json unreadable: {exc}")
 
     args.targets_info = state.get("targets_info") or []
-    # A target-less run has no targets_info at all: it works in a mounted
-    # directory, driven by its instruction.
+    # A target-less run has no targets_info at all. It is driven by its
+    # instruction, over a mounted working directory or over nothing when the
+    # mount was declined, so either of those is enough to resume it.
     workspace_mount = state.get("workspace_mount") or None
-    if not args.targets_info and not workspace_mount:
+    if not args.targets_info and not workspace_mount and not state.get("user_instruction"):
         parser.error(f"--resume {args.resume}: run.json has no targets_info")
 
     for target in args.targets_info:

strix/interface/main.py

@@ -224,6 +224,7 @@ async def warm_up_llm(show_model_warning: bool = True) -> None:
                 request_timeout=llm.timeout,
                 prompt_cache=False,
                 extra_headers=settings.dedupe.extra_headers,
+                has_tools=False,
             )
             if deduper_extra:
                 merged = {**(deduper_settings.extra_args or {}), **deduper_extra}

strix/interface/scan_setup.py

@@ -78,6 +78,7 @@ async def preflight_model_connection(
         request_timeout=resolved_settings.llm.timeout,
         prompt_cache=False,
         extra_headers=resolved_settings.llm.extra_headers,
+        has_tools=False,
     )
     await asyncio.wait_for(
         model.get_response(

strix/interface/tui/backend/controller.py

@@ -138,13 +138,6 @@ class TuiController:
         self.error = detail
         self.notify_changed()
 
-    def enter_setup(self) -> None:
-        """Return a session to the start screen, e.g. on a declined mount."""
-        self.setup_mode = True
-        self.scan_started = False
-        self.scan_state = "setup"
-        self.notify_changed()
-
     def add_message(self, text: str, level: str = "info") -> None:
         self._append_message(text, level)
         self.notify_changed()
@@ -356,14 +349,12 @@ class TuiController:
         if not isinstance(approved, bool):
             raise TypeError("approved must be a boolean")
         self.pending_workspace_mount = None
-        if not approved:
-            # Nothing was prepared, so return to the start screen untouched.
-            self.workspace_mount = None
-            self.enter_setup()
-            return {"approved": False}
-        self.workspace_mount = mount
+        # Declining skips the mount, it does not abandon the scan. The prompt is
+        # the whole of the input either way; the working directory is only an
+        # extra the agent may look at, so the run goes ahead without one.
+        self.workspace_mount = mount if approved else None
         await self._begin_scan(self._pending_verify)
-        return {"approved": True}
+        return {"approved": approved}
 
     async def _send_message(self, payload: dict[str, Any]) -> dict[str, Any]:
         agent_id = self._required_string(payload, "agent_id")

strix/interface/tui/internal/app/findings_test.go

@@ -0,0 +1,299 @@
+package app
+
+import (
+	"encoding/json"
+	"fmt"
+	"strings"
+	"testing"
+
+	tea "github.com/charmbracelet/bubbletea"
+	"github.com/charmbracelet/x/ansi"
+	"github.com/usestrix/strix/tui/internal/protocol"
+)
+
+func findingsModel(t *testing.T, titles ...string) Model {
+	t.Helper()
+	m := New(nil)
+	m.width, m.height = 130, 30
+	m.showSplash = false
+	m.handleEnvelope(stateEnvelope(t, 1, protocol.Snapshot{ScanState: "running"}))
+	items := make([]json.RawMessage, 0, len(titles))
+	for i, title := range titles {
+		items = append(items, rawJSON(t, map[string]any{
+			"id": string(rune('a' + i)), "title": title, "severity": "high",
+		}))
+	}
+	m.handleEnvelope(protocol.Envelope{Version: protocol.Version, Type: "collection_bootstrap",
+		Payload: rawJSON(t, protocol.CollectionBootstrap{
+			Collection: "vulnerabilities", Revision: 1, Cursor: 0,
+			NextCursor: len(items), Done: true, Items: items,
+		})})
+	m.resizeViewport()
+	return m
+}
+
+// The list scrolls by row, not by finding. Stepping a whole entry at a time is
+// what made a list of wrapped titles feel paginated.
+func TestFindingsScrollByRow(t *testing.T) {
+	long := "A deliberately long finding title that wraps across several rows in the sidebar"
+	m := findingsModel(t, long, long, long)
+
+	rows := m.vulnerabilityRows(m.vulnerabilityListWidth())
+	if len(rows) <= 3 {
+		t.Fatalf("titles did not wrap, so this proves nothing: %d rows", len(rows))
+	}
+	total, offset := m.vulnerabilityScrollRows()
+	if total != len(rows) || offset != 0 {
+		t.Fatalf("scroll metrics are not in rows: total=%d offset=%d rows=%d", total, offset, len(rows))
+	}
+
+	// One step of the offset moves one row, and the first visible line follows it.
+	first := strings.Split(ansi.Strip(m.vulnerabilitiesView(40, 4)), "\n")[0]
+	m.vulnOffset = 1
+	second := strings.Split(ansi.Strip(m.vulnerabilitiesView(40, 4)), "\n")[0]
+	if first == second {
+		t.Fatalf("advancing one row did not move the list: %q", first)
+	}
+	// That row still belongs to the first finding, which an item-stepping list
+	// would have skipped past entirely.
+	if got := m.vulnerabilityIndexAtRow(0); got != 0 {
+		t.Fatalf("one row in, the top line belongs to finding %d, want 0", got)
+	}
+}
+
+// Selecting a finding scrolls the least it can, and never past its own start.
+func TestSelectingAFindingBringsItIntoView(t *testing.T) {
+	long := "A deliberately long finding title that wraps across several rows in the sidebar"
+	m := findingsModel(t, long, long, long, long)
+
+	m.selectedVuln = 3
+	m.ensureVulnerabilityVisible()
+
+	rows := m.vulnerabilityRows(m.vulnerabilityListWidth())
+	height := m.vulnerabilityPageSize()
+	end := min(len(rows), m.vulnOffset+height)
+	found := false
+	for _, row := range rows[m.vulnOffset:end] {
+		if row.index == 3 {
+			found = true
+			break
+		}
+	}
+	if !found {
+		t.Fatalf("the selected finding is not on screen: offset=%d height=%d", m.vulnOffset, height)
+	}
+	if m.vulnOffset > len(rows)-height && len(rows) > height {
+		t.Fatalf("scrolled past the end: offset=%d rows=%d height=%d", m.vulnOffset, len(rows), height)
+	}
+}
+
+func reportModel(t *testing.T, count int) Model {
+	t.Helper()
+	titles := make([]string, 0, count)
+	for i := range count {
+		titles = append(titles, fmt.Sprintf("Finding number %d", i+1))
+	}
+	m := findingsModel(t, titles...)
+	m.openModal(modalVulnerability)
+	return m
+}
+
+// The open report can be stepped through the list without closing it.
+func TestReportStepsBetweenFindings(t *testing.T) {
+	m := reportModel(t, 3)
+
+	updated, _ := m.updateModal(tea.KeyMsg{Type: tea.KeyRight})
+	m = updated.(Model)
+	if m.selectedVuln != 1 {
+		t.Fatalf("right moved to %d, want 1", m.selectedVuln)
+	}
+	if m.modal != modalVulnerability {
+		t.Fatal("stepping closed the report")
+	}
+	updated, _ = m.updateModal(tea.KeyMsg{Type: tea.KeyLeft})
+	m = updated.(Model)
+	if m.selectedVuln != 0 {
+		t.Fatalf("left moved to %d, want 0", m.selectedVuln)
+	}
+}
+
+// The ends do not wrap: rolling from the last report to the first would hide
+// that you had reached the end.
+func TestReportStepsStopAtTheEnds(t *testing.T) {
+	m := reportModel(t, 3)
+
+	updated, _ := m.updateModal(tea.KeyMsg{Type: tea.KeyLeft})
+	m = updated.(Model)
+	if m.selectedVuln != 0 {
+		t.Fatalf("left from the first report moved to %d, want 0", m.selectedVuln)
+	}
+
+	m.selectedVuln = 2
+	updated, _ = m.updateModal(tea.KeyMsg{Type: tea.KeyRight})
+	m = updated.(Model)
+	if m.selectedVuln != 2 {
+		t.Fatalf("right from the last report moved to %d, want 2", m.selectedVuln)
+	}
+}
+
+// Each direction is offered only when there is a report that way, and a lone
+// finding is offered neither.
+func TestReportNavigationHintsFollowAvailability(t *testing.T) {
+	m := reportModel(t, 3)
+	for _, testCase := range []struct {
+		index              int
+		wantPrev, wantNext bool
+		position           string
+	}{
+		{index: 0, wantNext: true, position: "1/3"},
+		{index: 1, wantPrev: true, wantNext: true, position: "2/3"},
+		{index: 2, wantPrev: true, position: "3/3"},
+	} {
+		m.selectedVuln = testCase.index
+		view := ansi.Strip(m.modalView())
+		if !strings.Contains(view, testCase.position) {
+			t.Fatalf("report %d does not show %q", testCase.index, testCase.position)
+		}
+		if got := strings.Contains(view, reportPrev); got != testCase.wantPrev {
+			t.Fatalf("report %d prev hint = %v, want %v", testCase.index, got, testCase.wantPrev)
+		}
+		if got := strings.Contains(view, reportNext); got != testCase.wantNext {
+			t.Fatalf("report %d next hint = %v, want %v", testCase.index, got, testCase.wantNext)
+		}
+	}
+
+	lone := reportModel(t, 1)
+	view := ansi.Strip(lone.modalView())
+	if strings.Contains(view, reportPrev) || strings.Contains(view, reportNext) || strings.Contains(view, "1/1") {
+		t.Fatalf("a lone finding offered navigation:\n%s", view)
+	}
+}
+
+// A new report opens at its top, and the copy state does not carry over.
+func TestSteppingResetsTheReportView(t *testing.T) {
+	m := reportModel(t, 3)
+	m.vulnerabilityCopied = true
+	m.vulnViewport.SetYOffset(3)
+
+	m.showVulnerability(1)
+
+	if m.vulnViewport.YOffset != 0 {
+		t.Fatalf("the next report opened scrolled to %d", m.vulnViewport.YOffset)
+	}
+	if m.vulnerabilityCopied {
+		t.Fatal("the copy state carried over to another report")
+	}
+}
+
+// Prev and Next are buttons, not just key hints: they can be clicked.
+func TestReportStepButtonsAreClickable(t *testing.T) {
+	m := reportModel(t, 3)
+	m.selectedVuln = 1
+
+	click := func(label string) Model {
+		t.Helper()
+		view := m.modalView()
+		left, top, _, _ := m.centeredViewBounds(view)
+		for row, line := range strings.Split(view, "\n") {
+			plain := ansi.Strip(line)
+			index := strings.Index(plain, label)
+			if index < 0 {
+				continue
+			}
+			updated, _ := m.updateModalMouse(tea.MouseMsg{
+				X: left + ansi.StringWidth(plain[:index]) + 1, Y: top + row,
+				Button: tea.MouseButtonLeft, Action: tea.MouseActionPress,
+			})
+			return updated.(Model)
+		}
+		t.Fatalf("%q was not rendered", label)
+		return m
+	}
+
+	if got := click(reportNext).selectedVuln; got != 2 {
+		t.Fatalf("clicking Next selected %d, want 2", got)
+	}
+	if got := click(reportPrev).selectedVuln; got != 0 {
+		t.Fatalf("clicking Prev selected %d, want 0", got)
+	}
+	if got := click(reportNext).modal; got != modalVulnerability {
+		t.Fatalf("clicking Next closed the report: modal=%v", got)
+	}
+}
+
+// Tab walks the whole row, so the step buttons are reachable from the keyboard
+// as well, and Enter presses whichever one is focused.
+func TestTabReachesTheStepButtons(t *testing.T) {
+	m := reportModel(t, 3)
+	m.selectedVuln = 1
+
+	if got := m.focusedReportButton(); got != reportDone {
+		t.Fatalf("the report opened focused on %q, want %q", got, reportDone)
+	}
+	seen := map[string]bool{}
+	for range len(m.reportButtons()) {
+		updated, _ := m.updateModal(tea.KeyMsg{Type: tea.KeyTab})
+		m = updated.(Model)
+		seen[m.focusedReportButton()] = true
+	}
+	for _, want := range []string{reportPrev, reportNext, reportCopy, reportDone} {
+		if !seen[want] {
+			t.Fatalf("tab never reached %q: %v", want, seen)
+		}
+	}
+
+	// Enter on a focused step button steps.
+	m.reportFocus = reportNext
+	updated, _ := m.updateModal(tea.KeyMsg{Type: tea.KeyEnter})
+	if got := updated.(Model).selectedVuln; got != 2 {
+		t.Fatalf("enter on Next selected %d, want 2", got)
+	}
+}
+
+// Stepping to an end drops that button from the row; focus must not be stranded
+// on it.
+func TestFocusFallsBackWhenAStepButtonDisappears(t *testing.T) {
+	m := reportModel(t, 2)
+	m.selectedVuln = 0
+	m.reportFocus = reportNext
+
+	updated, _ := m.updateModal(tea.KeyMsg{Type: tea.KeyEnter})
+	m = updated.(Model)
+
+	if m.selectedVuln != 1 {
+		t.Fatalf("enter on Next selected %d, want 1", m.selectedVuln)
+	}
+	// Next is gone at the last report, so the focus cannot still be on it.
+	if got := m.focusedReportButton(); got == reportNext {
+		t.Fatalf("focus stayed on a button that is no longer shown: %q", got)
+	}
+	if got := m.focusedReportButton(); got != reportDone {
+		t.Fatalf("focus fell back to %q, want %q", got, reportDone)
+	}
+}
+
+// The list must be laid out at one width. Rendering at one and hit-testing at
+// another gives two different row counts for the same title, and then a click
+// resolves to the wrong finding and the scrollbar reports the wrong length.
+func TestFindingsUseOneWidthForRenderAndInteraction(t *testing.T) {
+	// This title wraps to one row at 21 columns and two at 20, which is exactly
+	// the pair of widths the two paths used to disagree on.
+	m := findingsModel(t, "ffffff dddd a a a a", "eeeee eeeee a a a a", "header dddd a a a a")
+
+	width := m.vulnerabilityListWidth()
+	rows := m.vulnerabilityRows(width)
+	rendered := strings.Split(ansi.Strip(m.vulnerabilitiesView(width, len(rows))), "\n")
+
+	if len(rendered) != len(rows) {
+		t.Fatalf("rendered %d rows, interaction counts %d", len(rendered), len(rows))
+	}
+	for row := range rendered {
+		if got := m.vulnerabilityIndexAtRow(row); got != rows[row].index {
+			t.Fatalf("row %d shows finding %d but a click resolves to %d",
+				row, rows[row].index, got)
+		}
+	}
+	if total, _ := m.vulnerabilityScrollRows(); total != len(rendered) {
+		t.Fatalf("the scrollbar reports %d rows, %d are rendered", total, len(rendered))
+	}
+}

strix/interface/tui/internal/app/model.go

@@ -110,6 +110,7 @@ type Model struct {
 	agentOffset            int
 	vulnOffset             int
 	modalChoice            int
+	reportFocus            string
 	ready                  bool
 	quitting               bool
 	showSplash             bool
@@ -157,12 +158,16 @@ const (
 	treeCursorBg = lipgloss.Color("#0178d4")
 )
 
-// Scrollbar thumbs. Each panel keeps its own, and the track stays blank so a
-// scrollable panel does not gain a visible rule down its edge.
+// Scrollbar thumbs. The track stays blank so a scrollable panel does not gain a
+// visible rule down its edge, and the thumb brightens while it is dragged, which
+// is the feedback Textual gave through scrollbar-color-active.
+//
+// One resting color for every panel, rather than the three the stylesheet named.
+// The chat pane's was #1a1a1a on black, which is invisible - the bar could not be
+// found, let alone grabbed (#1005).
 const (
-	thumbTrace    = lipgloss.Color("#1a1a1a")
-	thumbAgents   = lipgloss.Color("#404040")
-	thumbFindings = lipgloss.Color("#333333")
+	thumbResting = lipgloss.Color("#3f3f46")
+	thumbActive  = lipgloss.Color("#9ca3af")
 )
 
 // Composer placeholders. The launch screen falls back to the short prompt when

strix/interface/tui/internal/app/model_test.go

@@ -527,7 +527,8 @@ func TestVulnerabilityCopySupportsKeyboardAndMouse(t *testing.T) {
 	}
 
 	model := newModel()
-	updated, _ := model.updateModal(tea.KeyMsg{Type: tea.KeyLeft})
+	// Tab moves between the buttons; the arrows step between reports.
+	updated, _ := model.updateModal(tea.KeyMsg{Type: tea.KeyTab})
 	model = updated.(Model)
 	updated, cmd := model.updateModal(tea.KeyMsg{Type: tea.KeyEnter})
 	model = updated.(Model)
@@ -560,8 +561,8 @@ func TestVulnerabilityCopySupportsKeyboardAndMouse(t *testing.T) {
 		X: copyX, Y: copyY, Button: tea.MouseButtonLeft, Action: tea.MouseActionPress,
 	})
 	model = updated.(Model)
-	if cmd == nil || model.modalChoice != 0 {
-		t.Fatalf("mouse Copy was not activated: choice=%d cmd=%v", model.modalChoice, cmd)
+	if cmd == nil || model.reportFocus != reportCopy {
+		t.Fatalf("mouse Copy was not activated: focus=%q cmd=%v", model.reportFocus, cmd)
 	}
 	cmd()
 	if len(copied) != 2 {
@@ -820,8 +821,8 @@ func TestRunningViewerShowsCompleteWrappedURL(t *testing.T) {
 }
 
 func TestVerticalScrollbarThumbTracksScrollOffset(t *testing.T) {
-	top := strings.Split(ansi.Strip(verticalScrollbar(6, 24, 6, 0, thumbAgents)), "\n")
-	bottom := strings.Split(ansi.Strip(verticalScrollbar(6, 24, 6, 18, thumbAgents)), "\n")
+	top := strings.Split(ansi.Strip(verticalScrollbar(6, 24, 6, 0, thumbResting)), "\n")
+	bottom := strings.Split(ansi.Strip(verticalScrollbar(6, 24, 6, 18, thumbResting)), "\n")
 
 	// The track is blank, so only the thumb is drawn.
 	if top[0] != "█" || top[5] != " " {
@@ -830,10 +831,10 @@ func TestVerticalScrollbarThumbTracksScrollOffset(t *testing.T) {
 	if bottom[0] != " " || bottom[5] != "█" {
 		t.Fatalf("bottom scrollbar is incorrect: %#v", bottom)
 	}
-	if full := verticalScrollbar(4, 4, 4, 0, thumbAgents); full != "" {
+	if full := verticalScrollbar(4, 4, 4, 0, thumbResting); full != "" {
 		t.Fatalf("non-overflowing scrollbar should be hidden: %q", full)
 	}
-	withoutBar := ansi.Strip(withVerticalScrollbar("content", 12, 2, 2, 2, 0, thumbAgents))
+	withoutBar := ansi.Strip(withVerticalScrollbar("content", 12, 2, 2, 2, 0, thumbResting))
 	if strings.ContainsAny(withoutBar, "█") {
 		t.Fatalf("non-overflowing panel rendered a scrollbar: %q", withoutBar)
 	}
@@ -841,7 +842,7 @@ func TestVerticalScrollbarThumbTracksScrollOffset(t *testing.T) {
 
 // The bar takes exactly one column, so a scrolling panel keeps the rest.
 func TestVerticalScrollbarOccupiesOneColumn(t *testing.T) {
-	rows := strings.Split(withVerticalScrollbar("content", 12, 2, 24, 2, 0, thumbTrace), "\n")
+	rows := strings.Split(withVerticalScrollbar("content", 12, 2, 24, 2, 0, thumbResting), "\n")
 	for _, row := range rows {
 		if width := ansi.StringWidth(row); width != 12 {
 			t.Fatalf("scrolling panel row width = %d, want 12", width)
@@ -1169,3 +1170,120 @@ func TestChatContentRerendersOnWidthAndExpansionChange(t *testing.T) {
 		}
 	}
 }
+
+// A model or backend failure can be a wrapped exception hundreds of columns
+// wide and several lines long. The status row is one line of the chat column, so
+// an oversized one widens the whole column - JoinHorizontal pads every row to the
+// widest - which pushed the sidebar off screen and wrapped the frame.
+func TestLongErrorDoesNotBreakTheFrame(t *testing.T) {
+	model := New(nil)
+	model.width, model.height = 120, 24
+	model.showSplash = false
+	model.handleEnvelope(stateEnvelope(t, 1, protocol.Snapshot{ScanState: "running"}))
+	bootstrap := protocol.CollectionBootstrap{
+		Collection: "agents", Revision: 1, Cursor: 0, NextCursor: 1, Done: true,
+		Items: []json.RawMessage{rawJSON(t, protocol.Agent{ID: "a0", Name: "Strix", Status: "running"})},
+	}
+	model.handleEnvelope(protocol.Envelope{
+		Version: protocol.Version, Type: "collection_bootstrap", Payload: rawJSON(t, bootstrap),
+	})
+	model.errorText = "litellm.APIConnectionError: OpenrouterException - Connection error " +
+		"while calling https://openrouter.ai/api/v1/chat/completions: HTTPSConnectionPool" +
+		"(host='openrouter.ai', port=443): Max retries exceeded\nTraceback (most recent " +
+		"call last):\n  File \"/x/y.py\", line 42, in send\n    raise err"
+	model.resizeViewport()
+
+	lines := strings.Split(model.View(), "\n")
+	if len(lines) > model.height {
+		t.Fatalf("frame is %d rows in a %d-row terminal", len(lines), model.height)
+	}
+	for i, line := range lines {
+		if width := ansi.StringWidth(line); width > model.width {
+			t.Fatalf("row %d is %d columns in a %d-column terminal", i, width, model.width)
+		}
+	}
+	// The sidebar has to survive: its panels are the right edge of the frame.
+	if !strings.Contains(ansi.Strip(model.View()), "Strix") {
+		t.Fatal("the agent tree was pushed out of the frame")
+	}
+}
+
+func TestStatusMessageFlattensAndKeepsItsHint(t *testing.T) {
+	row := ansi.Strip(statusMessage("boom\nsecond line\twith tabs", red, " · Send message to resume", 60))
+
+	if strings.Contains(row, "\n") || strings.Contains(row, "\t") {
+		t.Fatalf("status row is not a single line: %q", row)
+	}
+	if !strings.HasSuffix(row, " · Send message to resume") {
+		t.Fatalf("the hint was lost: %q", row)
+	}
+	if !strings.Contains(row, "boom second line with tabs") {
+		t.Fatalf("the message was mangled: %q", row)
+	}
+	// A message far too long for the row keeps the hint readable.
+	long := ansi.Strip(statusMessage(strings.Repeat("x", 500), red, " · Send message to resume", 60))
+	if width := ansi.StringWidth(long); width > 60 {
+		t.Fatalf("status message is %d columns, want at most 60", width)
+	}
+	if !strings.HasSuffix(long, " · Send message to resume") {
+		t.Fatalf("the hint was clipped away: %q", long)
+	}
+}
+
+// The status row must be exactly as wide as the column it sits in, at every
+// terminal size. A narrow terminal cannot fit the quit hint alongside any status
+// text, and keeping it anyway made the row wider than the terminal.
+func TestStatusRowIsExactlyItsWidth(t *testing.T) {
+	quitHint := lipgloss.NewStyle().Foreground(white).Render("ctrl-q") +
+		lipgloss.NewStyle().Foreground(dim).Render(" quit")
+	longMessage := lipgloss.NewStyle().Foreground(red).Render(strings.Repeat("boom ", 40))
+
+	for width := 1; width <= 60; width++ {
+		for _, testCase := range []struct {
+			name        string
+			left, right string
+		}{
+			{"empty", "", ""},
+			{"hint only", "", quitHint},
+			{"long message and hint", longMessage, quitHint},
+			{"long message alone", longMessage, ""},
+		} {
+			row := composeStatusRow(testCase.left, testCase.right, width)
+			if got := ansi.StringWidth(row); got != width {
+				t.Fatalf("%s at width %d rendered %d columns: %q",
+					testCase.name, width, got, ansi.Strip(row))
+			}
+			if strings.Contains(row, "\n") {
+				t.Fatalf("%s at width %d spans rows", testCase.name, width)
+			}
+		}
+	}
+	if row := composeStatusRow("x", "y", 0); row != "" {
+		t.Fatalf("a zero-width row should be empty, got %q", row)
+	}
+}
+
+// A running scan in a narrow terminal must not wrap the frame.
+func TestNarrowTerminalKeepsTheFrameIntact(t *testing.T) {
+	for _, width := range []int{8, 10, 13, 14, 20, 40} {
+		model := New(nil)
+		model.width, model.height = width, 20
+		model.showSplash = false
+		model.handleEnvelope(stateEnvelope(t, 1, protocol.Snapshot{ScanState: "running"}))
+		bootstrap := protocol.CollectionBootstrap{
+			Collection: "agents", Revision: 1, Cursor: 0, NextCursor: 1, Done: true,
+			Items: []json.RawMessage{rawJSON(t, protocol.Agent{ID: "a0", Name: "Strix", Status: "running"})},
+		}
+		model.handleEnvelope(protocol.Envelope{
+			Version: protocol.Version, Type: "collection_bootstrap", Payload: rawJSON(t, bootstrap),
+		})
+		model.errorText = strings.Repeat("connection failed ", 20)
+		model.resizeViewport()
+
+		for i, line := range strings.Split(model.View(), "\n") {
+			if got := ansi.StringWidth(line); got > width {
+				t.Fatalf("at width %d row %d is %d columns", width, i, got)
+			}
+		}
+	}
+}

strix/interface/tui/internal/app/setup.go

@@ -66,13 +66,10 @@ func (m *Model) submitSetupPrompt(value string) (tea.Model, tea.Cmd) {
 }
 
 // answerMountConfirmation replies to the working-directory mount the backend is
-// waiting on. Declining returns to the start screen, so the prompt goes back in
-// the composer to be edited or given a target instead.
+// waiting on. Either answer starts the scan - declining only means it runs
+// without the directory - so the prompt stays with the run rather than coming
+// back to the composer.
 func (m *Model) answerMountConfirmation(approved bool) tea.Cmd {
-	if !approved && m.pendingPrompt != "" {
-		m.input.SetValue(m.pendingPrompt)
-		m.resizeViewport()
-	}
 	m.pendingPrompt = ""
 	return send(m.client, "setup.confirm_mount", map[string]any{"approved": approved})
 }
@@ -214,8 +211,11 @@ func (m *Model) setupLogAppend(line string) {
 }
 
 // setupMsg appends a styled feedback line (success green, error red, notice dim).
+// The log budgets rows by entry, so a message is flattened to one line first: a
+// wrapped exception would otherwise render as several rows and push the launch
+// column past the bottom of the terminal.
 func (m *Model) setupMsg(text string, style lipgloss.Style) {
-	m.setupLogAppend(style.Render(text))
+	m.setupLogAppend(style.Render(flattenStatus(text)))
 }
 
 // setupLogRows is how many feedback lines the launch column shows before the

strix/interface/tui/internal/app/setup_log_test.go

@@ -93,3 +93,25 @@ func TestFocusedPanelsCarryTheGreenBorder(t *testing.T) {
 		}
 	}
 }
+
+// A wrapped exception is several lines. The log budgets rows by entry, so it has
+// to become one row or the launch column grows past the terminal.
+func TestSetupLogKeepsMultiLineErrorsToOneRow(t *testing.T) {
+	model := New(nil)
+	model.width, model.height = 100, 26
+	model.showSplash = false
+	model.handleEnvelope(stateEnvelope(t, 1, protocol.Snapshot{SetupMode: true, ScanState: "setup"}))
+	model.setupMsg("boom\nTraceback (most recent call last):\n  File \"x.py\", line 1\n    raise", render.Col(red))
+	model.resizeViewport()
+
+	if entries := len(model.setupLog); entries != 1 {
+		t.Fatalf("one message became %d log entries", entries)
+	}
+	if strings.Contains(model.setupLog[0], "\n") {
+		t.Fatalf("log entry spans rows: %q", model.setupLog[0])
+	}
+	lines := strings.Split(model.View(), "\n")
+	if len(lines) > model.height {
+		t.Fatalf("start screen is %d rows in a %d-row terminal", len(lines), model.height)
+	}
+}

strix/interface/tui/internal/app/setup_prompt_test.go

@@ -247,13 +247,10 @@ func TestMountConfirmationAnswers(t *testing.T) {
 		if payload.Approved != tc.approved {
 			t.Fatalf("%s: approved=%v, want %v", tc.name, payload.Approved, tc.approved)
 		}
-		// Declining returns to the start screen, so the prompt comes back.
-		want := ""
-		if !tc.approved {
-			want = "find auth bugs in the login flow"
-		}
-		if got := model.input.Value(); got != want {
-			t.Fatalf("%s: composer = %q, want %q", tc.name, got, want)
+		// Either answer launches, so the prompt stays with the run rather than
+		// coming back to the composer.
+		if got := model.input.Value(); got != "" {
+			t.Fatalf("%s: composer = %q, want it cleared", tc.name, got)
 		}
 		if model.pendingPrompt != "" {
 			t.Fatalf("%s: held prompt was not cleared: %q", tc.name, model.pendingPrompt)
@@ -290,3 +287,101 @@ func TestSetupPromptWithTargetLaunches(t *testing.T) {
 		t.Fatalf("setup.start (%d) must come after setup.set_instruction (%d): %v", start, instr, types)
 	}
 }
+
+// The prompt's buttons are buttons: clicking Cancel has to answer the backend,
+// which it could not do while the mouse handler had no case for this modal.
+func TestMountPromptButtonsAreClickable(t *testing.T) {
+	for _, testCase := range []struct {
+		label    string
+		approved bool
+	}{
+		{mountConfirmLabel, true},
+		{mountCancelLabel, false},
+	} {
+		connection := &recordingConn{}
+		model := New(&Client{conn: connection})
+		model.width, model.height = 130, 40
+		model.snapshot = protocol.Snapshot{SetupMode: true, WorkingDir: "/Users/me/code/api"}
+		updated, _ := model.submit("find auth bugs in the login flow")
+		model = updated.(Model)
+		connection.Reset()
+		model.snapshot = protocol.Snapshot{
+			ScanStarted: true, ScanState: "preparing", PendingMount: "/Users/me/code/api",
+		}
+		model.syncMountPrompt()
+
+		left, top, panel := model.mountPromptBounds()
+		clicked := false
+		for row, line := range strings.Split(panel, "\n") {
+			plain := ansi.Strip(line)
+			index := strings.Index(plain, testCase.label)
+			if index < 0 {
+				continue
+			}
+			updated, cmd := model.updateModalMouse(tea.MouseMsg{
+				X: left + ansi.StringWidth(plain[:index]) + 1, Y: top + row,
+				Button: tea.MouseButtonLeft, Action: tea.MouseActionPress,
+			})
+			model = updated.(Model)
+			envelopes := drainCommands(t, cmd, connection)
+			if len(envelopes) != 1 || envelopes[0].Type != "setup.confirm_mount" {
+				t.Fatalf("clicking %s sent %v", testCase.label, commandTypes(envelopes))
+			}
+			var payload struct {
+				Approved bool `json:"approved"`
+			}
+			if err := json.Unmarshal(envelopes[0].Payload, &payload); err != nil {
+				t.Fatal(err)
+			}
+			if payload.Approved != testCase.approved {
+				t.Fatalf("clicking %s answered approved=%v", testCase.label, payload.Approved)
+			}
+			clicked = true
+			break
+		}
+		if !clicked {
+			t.Fatalf("%s was not found in the prompt", testCase.label)
+		}
+	}
+}
+
+// Skipping the mount runs the scan without a directory. It must not throw the
+// session back to the start screen, and it must not hand the prompt back: the
+// run has it.
+func TestSkippingTheMountKeepsTheScanRunning(t *testing.T) {
+	connection := &recordingConn{}
+	model := New(&Client{conn: connection})
+	model.width, model.height = 130, 40
+	model.snapshot = protocol.Snapshot{SetupMode: true, WorkingDir: "/Users/me/code/api"}
+	updated, _ := model.submit("find auth bugs in the login flow")
+	model = updated.(Model)
+	model.snapshot = protocol.Snapshot{
+		ScanStarted: true, ScanState: "preparing", PendingMount: "/Users/me/code/api",
+	}
+	model.syncMountPrompt()
+	if model.modal != modalConfirmMount {
+		t.Fatal("the prompt did not open")
+	}
+
+	model.modalChoice = 1
+	updated, _ = model.updateModal(tea.KeyMsg{Type: tea.KeyEnter})
+	model = updated.(Model)
+
+	// The backend answers by starting the scan with no mount.
+	model.handleEnvelope(stateEnvelope(t, 2, protocol.Snapshot{
+		ScanStarted: true, ScanState: "running",
+	}))
+
+	if model.modal != modalNone {
+		t.Fatalf("the prompt is still open: %v", model.modal)
+	}
+	if model.snapshot.SetupMode {
+		t.Fatal("skipping the mount fell back to the start screen")
+	}
+	if got := model.input.Value(); got != "" {
+		t.Fatalf("the prompt came back to the composer: %q", got)
+	}
+	if model.pendingPrompt != "" {
+		t.Fatalf("the held prompt was not released: %q", model.pendingPrompt)
+	}
+}

strix/interface/tui/internal/app/update.go

@@ -219,7 +219,8 @@ func (m Model) updateMouse(msg tea.MouseMsg) (tea.Model, tea.Cmd) {
 			case vulnHeight > 0 && y < viewerHeight+agentHeight+vulnHeight:
 				m.focus = focusVulnerabilities
 				m.input.Blur()
-				m.vulnOffset = min(max(0, len(m.snapshot.Vulnerabilities)-1), m.vulnOffset+3)
+				totalRows, _ := m.vulnerabilityScrollRows()
+				m.vulnOffset = min(max(0, totalRows-m.vulnerabilityPageSize()), m.vulnOffset+3)
 				m.keepVulnerabilitySelectionInWindow()
 			}
 			return m, nil
@@ -318,24 +319,7 @@ func (m *Model) updateMainScrollbarMouse(
 	if msg.Action != tea.MouseActionPress || msg.Button != tea.MouseButtonLeft {
 		return false
 	}
-
-	target := scrollbarNone
-	switch {
-	case msg.X == chatWidth-2 && msg.Y >= 1 && msg.Y < chatHeight-1 &&
-		m.viewport.TotalLineCount() > m.viewport.VisibleLineCount():
-		target = scrollbarTrace
-	case showSidebar && msg.X == m.width-3 && msg.Y >= viewerHeight+2 &&
-		msg.Y < viewerHeight+agentHeight-2 &&
-		len(agentTreeEntries(m.snapshot.Agents, m.collapsedAgents)) > m.agentPageSize():
-		target = scrollbarAgents
-	case showSidebar && vulnHeight > 0 && msg.X == m.width-3 &&
-		msg.Y >= viewerHeight+agentHeight+1 &&
-		msg.Y < viewerHeight+agentHeight+vulnHeight-1:
-		totalRows, _ := m.vulnerabilityScrollRows()
-		if totalRows > m.vulnerabilityPageSize() {
-			target = scrollbarFindings
-		}
-	}
+	target := m.scrollbarAt(msg, showSidebar, chatWidth, chatHeight, viewerHeight, agentHeight, vulnHeight)
 	if target == scrollbarNone {
 		return false
 	}
@@ -344,6 +328,40 @@ func (m *Model) updateMainScrollbarMouse(
 	return true
 }
 
+// scrollbarGrab is how far either side of the bar still counts as grabbing it. A
+// one column target is unreasonable to hit with a mouse, and nothing else lives
+// in the column beside it.
+const scrollbarGrab = 1
+
+func nearColumn(x, column int) bool {
+	return x >= column-scrollbarGrab && x <= column+scrollbarGrab
+}
+
+// scrollbarAt reports which scrollbar, if any, the pointer is over.
+func (m Model) scrollbarAt(
+	msg tea.MouseMsg,
+	showSidebar bool,
+	chatWidth, chatHeight, viewerHeight, agentHeight, vulnHeight int,
+) scrollbarTarget {
+	switch {
+	case nearColumn(msg.X, chatWidth-2) && msg.Y >= 1 && msg.Y < chatHeight-1 &&
+		m.viewport.TotalLineCount() > m.viewport.VisibleLineCount():
+		return scrollbarTrace
+	case showSidebar && nearColumn(msg.X, m.width-3) && msg.Y >= viewerHeight+2 &&
+		msg.Y < viewerHeight+agentHeight-2 &&
+		len(agentTreeEntries(m.snapshot.Agents, m.collapsedAgents)) > m.agentPageSize():
+		return scrollbarAgents
+	case showSidebar && vulnHeight > 0 && nearColumn(msg.X, m.width-3) &&
+		msg.Y >= viewerHeight+agentHeight+1 &&
+		msg.Y < viewerHeight+agentHeight+vulnHeight-1:
+		totalRows, _ := m.vulnerabilityScrollRows()
+		if totalRows > m.vulnerabilityPageSize() {
+			return scrollbarFindings
+		}
+	}
+	return scrollbarNone
+}
+
 func (m *Model) scrollFromMouse(
 	target scrollbarTarget,
 	y, chatHeight, viewerHeight, agentHeight int,
@@ -367,10 +385,10 @@ func (m *Model) scrollFromMouse(
 	case scrollbarFindings:
 		height := m.vulnerabilityPageSize()
 		totalRows, _ := m.vulnerabilityScrollRows()
-		rowOffset := scrollbarOffset(y-viewerHeight-agentHeight-1, height, totalRows, height)
 		m.focus = focusVulnerabilities
 		m.input.Blur()
-		m.vulnOffset = m.vulnerabilityOffsetAtRow(rowOffset)
+		// The offset is a row, so dragging moves the list continuously.
+		m.vulnOffset = scrollbarOffset(y-viewerHeight-agentHeight-1, height, totalRows, height)
 		m.keepVulnerabilitySelectionInWindow()
 	}
 }
@@ -405,6 +423,22 @@ func (m Model) updateSetupMouse(msg tea.MouseMsg) (tea.Model, tea.Cmd) {
 	return m, nil
 }
 
+// pressReportButton performs a button of the report row, however it was reached.
+func (m Model) pressReportButton(button string) (tea.Model, tea.Cmd) {
+	switch button {
+	case reportPrev:
+		m.showVulnerability(m.selectedVuln - 1)
+	case reportNext:
+		m.showVulnerability(m.selectedVuln + 1)
+	case reportCopy:
+		m.reportFocus = reportCopy
+		return m, m.startVulnerabilityCopy()
+	default:
+		m.closeModal()
+	}
+	return m, nil
+}
+
 func (m Model) updateModalMouse(msg tea.MouseMsg) (tea.Model, tea.Cmd) {
 	if m.modal == modalVulnerability {
 		view := m.modalView()
@@ -440,14 +474,35 @@ func (m Model) updateModalMouse(msg tea.MouseMsg) (tea.Model, tea.Cmd) {
 			m.modalChoice = 1
 			return m.updateModal(tea.KeyMsg{Type: tea.KeyEnter})
 		}
-	case modalVulnerability:
-		if m.centeredLabelHit(view, "Copy", msg.X, msg.Y) {
+	case modalConfirmMount:
+		left, top, panel := m.mountPromptBounds()
+		if labelHitAt(panel, mountConfirmLabel, left, top, msg.X, msg.Y) {
 			m.modalChoice = 0
+			cmd := m.answerMountConfirmation(true)
+			return m, cmd
+		}
+		if labelHitAt(panel, mountCancelLabel, left, top, msg.X, msg.Y) {
+			m.modalChoice = 1
+			cmd := m.answerMountConfirmation(false)
+			return m, cmd
+		}
+	case modalVulnerability:
+		for _, button := range m.reportButtons() {
+			if button == reportCopy || button == reportDone {
+				continue
+			}
+			if m.centeredLabelHit(view, button, msg.X, msg.Y) {
+				m.reportFocus = button
+				return m.pressReportButton(button)
+			}
+		}
+		if m.centeredLabelHit(view, "Copy", msg.X, msg.Y) {
+			m.reportFocus = reportCopy
 			cmd := m.startVulnerabilityCopy()
 			return m, cmd
 		}
 		if m.centeredLabelHit(view, "Done", msg.X, msg.Y) {
-			m.modalChoice = 1
+			m.reportFocus = reportDone
 			m.closeModal()
 		}
 	}
@@ -464,7 +519,14 @@ func (m Model) centeredViewBounds(view string) (left, top, width, height int) {
 
 func (m Model) centeredLabelHit(view, label string, x, y int) bool {
 	left, top, _, _ := m.centeredViewBounds(view)
-	for row, line := range strings.Split(view, "\n") {
+	return labelHitAt(view, label, left, top, x, y)
+}
+
+// labelHitAt reports whether a click landed on a label drawn in a panel whose
+// top-left corner is at (left, top). The mount prompt is docked in a corner
+// rather than centered, so it cannot use the centered bounds.
+func labelHitAt(panel, label string, left, top, x, y int) bool {
+	for row, line := range strings.Split(panel, "\n") {
 		plain := ansi.Strip(line)
 		index := strings.Index(plain, label)
 		if index < 0 || y != top+row {
@@ -516,16 +578,19 @@ func (m Model) updateModal(key tea.KeyMsg) (tea.Model, tea.Cmd) {
 		switch key.String() {
 		case "esc":
 			m.closeModal()
-		case "left", "right", "tab", "shift+tab":
-			m.modalChoice = 1 - m.modalChoice
+		// The arrows step between reports directly; tab walks the button row.
+		case "left":
+			m.showVulnerability(m.selectedVuln - 1)
+		case "right":
+			m.showVulnerability(m.selectedVuln + 1)
+		case "tab":
+			m.stepReportFocus(1)
+		case "shift+tab":
+			m.stepReportFocus(-1)
 		case "enter":
-			if m.modalChoice == 0 {
-				cmd := m.startVulnerabilityCopy()
-				return m, cmd
-			}
-			m.closeModal()
+			return m.pressReportButton(m.focusedReportButton())
 		case "c":
-			m.modalChoice = 0
+			m.reportFocus = reportCopy
 			cmd := m.startVulnerabilityCopy()
 			return m, cmd
 		case "up":
@@ -547,7 +612,8 @@ func (m Model) updateModal(key tea.KeyMsg) (tea.Model, tea.Cmd) {
 	case "esc":
 		if m.modal == modalConfirmMount {
 			// The backend is waiting on an answer; escape declines it.
-			return m, m.answerMountConfirmation(false)
+			cmd := m.answerMountConfirmation(false)
+			return m, cmd
 		}
 		m.closeModal()
 		return m, nil
@@ -558,7 +624,10 @@ func (m Model) updateModal(key tea.KeyMsg) (tea.Model, tea.Cmd) {
 		modal, choice := m.modal, m.modalChoice
 		if modal == modalConfirmMount {
 			// The snapshot closes this prompt once the backend has the answer.
-			return m, m.answerMountConfirmation(choice == 0)
+			// Bound to a variable first: the call restores the held prompt into
+			// the composer, and that has to be in the model being returned.
+			cmd := m.answerMountConfirmation(choice == 0)
+			return m, cmd
 		}
 		m.closeModal()
 		if choice == 1 {
@@ -584,6 +653,7 @@ func (m *Model) openModal(mode modalMode) {
 		m.modalChoice = 1
 	}
 	if mode == modalVulnerability {
+		m.reportFocus = reportDone
 		m.modalChoice = 1
 		m.vulnerabilityCopied = false
 		m.vulnerabilityCopyError = ""

strix/interface/tui/internal/app/view.go

@@ -164,6 +164,15 @@ func wrapBlock(value string, width int) string {
 	return strings.Join(out, "\n")
 }
 
+// scrollbarThumb brightens the bar being dragged so the grab reads as taking
+// hold of it.
+func (m Model) scrollbarThumb(target scrollbarTarget) lipgloss.Color {
+	if m.draggingScrollbar == target {
+		return thumbActive
+	}
+	return thumbResting
+}
+
 func verticalScrollbar(height, total, visible, offset int, thumb lipgloss.Color) string {
 	if height <= 0 || total <= visible {
 		return ""
@@ -262,6 +271,23 @@ func (m Model) viewInner() string {
 	return m.toastOverlay(main)
 }
 
+// mountPromptBounds is where the working-directory prompt is drawn. It is placed
+// by cornerOverlay rather than centered, so a click has to be tested against
+// these bounds and not the ones the other modals use.
+func (m Model) mountPromptBounds() (left, top int, panel string) {
+	panel = m.modalView()
+	if panel == "" {
+		return 0, 0, ""
+	}
+	_, _, chatWidth, _ := m.layout()
+	left = max(0, min(chatWidth, m.width)-lipgloss.Width(panel))
+	statusH := 0
+	if m.statusVisible() {
+		statusH = 1
+	}
+	return left, max(0, m.inputTop()-statusH-lipgloss.Height(panel)), panel
+}
+
 // cornerOverlay splices a panel in directly above the composer, right-aligned
 // with it, leaving the rest of the view visible behind it.
 func (m Model) cornerOverlay(view, panel string) string {
@@ -424,7 +450,7 @@ func (m Model) renderChatPane(width, height int, border lipgloss.Color) string {
 		m.viewport.TotalLineCount(),
 		m.viewport.VisibleLineCount(),
 		m.viewport.YOffset,
-		thumbTrace,
+		m.scrollbarThumb(scrollbarTrace),
 	)
 	out := lipgloss.NewStyle().Width(width).Height(height).
 		Border(lipgloss.RoundedBorder()).BorderForeground(border).Render(trace)
@@ -489,7 +515,7 @@ func (m Model) sidebarView(width, height int) string {
 		len(agentEntries),
 		agentRows,
 		m.agentOffset,
-		thumbAgents,
+		m.scrollbarThumb(scrollbarAgents),
 	)
 	parts := []string{
 		lipgloss.NewStyle().Width(width-2).Height(m.viewerHeight()-2).Border(lipgloss.RoundedBorder()).BorderForeground(dark).Padding(0, 1).Render(m.viewerView(width - 4)),
@@ -503,13 +529,13 @@ func (m Model) sidebarView(width, height int) string {
 		vulnRows := max(1, vulnHeight-2)
 		totalRows, offsetRows := m.vulnerabilityScrollRows()
 		findings := withVerticalScrollbar(
-			m.vulnerabilitiesView(max(1, width-5), vulnRows),
+			m.vulnerabilitiesView(m.vulnerabilityListWidth(), vulnRows),
 			width-4,
 			vulnRows,
 			totalRows,
 			vulnRows,
 			offsetRows,
-			thumbFindings,
+			m.scrollbarThumb(scrollbarFindings),
 		)
 		parts = append(parts, lipgloss.NewStyle().Width(width-2).Height(vulnRows).Border(lipgloss.RoundedBorder()).BorderForeground(vulnBorder).Padding(0, 1).Render(findings))
 	}
@@ -524,12 +550,7 @@ func (m Model) sidebarHeights() (statsHeight, vulnHeight, agentHeight int) {
 	statsRows := lipgloss.Height(lipgloss.NewStyle().Width(m.viewerContentWidth()).Render(m.statsView()))
 	statsHeight = min(15, statsRows+2)
 	if len(m.snapshot.Vulnerabilities) > 0 {
-		rows := 0
-		width := m.vulnerabilityListWidth()
-		for i := range m.snapshot.Vulnerabilities {
-			rows += len(m.vulnerabilityTitleLines(i, width))
-		}
-		vulnHeight = min(12, rows+2)
+		vulnHeight = min(12, len(m.vulnerabilityRows(m.vulnerabilityListWidth()))+2)
 	}
 	agentHeight = max(3, m.height-m.viewerHeight()-statsHeight-vulnHeight)
 	return
@@ -654,8 +675,7 @@ func (m Model) statusView(width int) string {
 		case "waiting":
 			left = lipgloss.NewStyle().Foreground(dim).Render("Send message to resume")
 			if msg := agent.ErrorMessage; msg != "" {
-				left = lipgloss.NewStyle().Foreground(red).Render(msg) +
-					lipgloss.NewStyle().Foreground(dim).Render(" · Send message to resume")
+				left = statusMessage(msg, red, " · Send message to resume", width)
 			}
 		case "budget_paused":
 			left = lipgloss.NewStyle().Foreground(amber).Render("Budget limit reached") +
@@ -670,15 +690,54 @@ func (m Model) statusView(width int) string {
 			if msg == "" {
 				msg = "Agent failed"
 			}
-			left = lipgloss.NewStyle().Foreground(red).Render(msg) +
-				lipgloss.NewStyle().Foreground(dim).Render(" · Send message to resume")
+			left = statusMessage(msg, red, " · Send message to resume", width)
 		}
 	}
 	if m.errorText != "" {
-		left = lipgloss.NewStyle().Foreground(red).Render(m.errorText)
+		left = statusMessage(m.errorText, red, "", width-lipgloss.Width(right))
 	}
-	gap := max(1, width-lipgloss.Width(left)-lipgloss.Width(right))
-	return " " + left + strings.Repeat(" ", max(1, gap-1)) + right
+	return composeStatusRow(left, right, width)
+}
+
+// composeStatusRow lays the status text and the corner hint on one row exactly
+// width columns wide. A wider row would widen the whole chat column, because
+// JoinHorizontal pads every row of a block to its widest, which pushes the
+// sidebar off screen and wraps the frame.
+func composeStatusRow(left, right string, width int) string {
+	if width <= 0 {
+		return ""
+	}
+	const leading = 1 // the row is indented one column, like the panels above it
+	// A terminal can be narrower than the hint itself. Drop the hint rather than
+	// keep it at the cost of the status, which is the part carrying information;
+	// ctrl-q works whether or not the row has room to say so.
+	if lipgloss.Width(right) > 0 && width < lipgloss.Width(right)+leading+2 {
+		right = ""
+	}
+	separator := 0
+	if lipgloss.Width(right) > 0 {
+		separator = 1
+	}
+	left = truncate(left, max(0, width-leading-lipgloss.Width(right)-separator))
+	padding := max(0, width-leading-lipgloss.Width(left)-lipgloss.Width(right))
+	return " " + left + strings.Repeat(" ", padding) + right
+}
+
+// statusMessage fits a message and its trailing hint on the one status row. A
+// model or backend error can be a wrapped exception several lines long, so it is
+// flattened to a single line and clipped, leaving the hint readable.
+func statusMessage(message string, color lipgloss.Color, hint string, width int) string {
+	styledHint := lipgloss.NewStyle().Foreground(dim).Render(hint)
+	room := max(1, width-2-lipgloss.Width(styledHint))
+	flat := truncate(flattenStatus(message), room)
+	return lipgloss.NewStyle().Foreground(color).Render(flat) + styledHint
+}
+
+// flattenStatus turns a multi-line message into one line, collapsing the runs of
+// whitespace that joining its lines leaves behind.
+func flattenStatus(message string) string {
+	message = strings.NewReplacer("\r\n", " ", "\r", " ", "\n", " ", "\t", " ").Replace(message)
+	return strings.Join(strings.Fields(message), " ")
 }
 
 func (m Model) sweepView() string {

strix/interface/tui/internal/app/vuln_report.go

@@ -74,6 +74,8 @@ func vulnerabilityMarkdownReport(v map[string]any) string {
 		field("Ecosystem", render.StringValue(dep["package_ecosystem"]))
 		field("Installed Version", render.StringValue(dep["installed_version"]))
 		field("Fixed Version", render.StringValue(dep["fixed_version"]))
+		field("Introduced By", render.StringValue(dep["introduced_by"]))
+		field("Dependency Chain", render.StringValue(dep["dependency_path"]))
 	}
 	field("Endpoint", render.StringValue(v["endpoint"]))
 	field("Method", render.StringValue(v["method"]))

strix/interface/tui/internal/app/vulnerabilities.go

@@ -1,6 +1,7 @@
 package app
 
 import (
+	"fmt"
 	"strings"
 
 	tea "github.com/charmbracelet/bubbletea"
@@ -13,115 +14,123 @@ var panelSeverityColors = map[string]lipgloss.Color{
 	"critical": render.SevCrit, "high": render.SevHigh, "medium": render.SevMed, "low": green, "info": blue,
 }
 
-func (m Model) vulnerabilitiesView(width, height int) string {
-	var lines []string
-	start := min(max(0, m.vulnOffset), max(0, len(m.snapshot.Vulnerabilities)-1))
-	for i := start; i < len(m.snapshot.Vulnerabilities) && len(lines) < height; i++ {
-		vuln := m.snapshot.Vulnerabilities[i]
-		severity := strings.ToLower(render.StringValue(vuln["severity"]))
-		color, ok := panelSeverityColors[severity]
-		if !ok {
-			color = blue // matches SEVERITY_COLORS.get(severity, "#3b82f6")
+// vulnerabilityRow is one rendered line of the findings list. The list scrolls by
+// row rather than by finding, so a long title does not make the panel jump a
+// whole entry at a time.
+type vulnerabilityRow struct {
+	index int    // the finding this line belongs to
+	text  string // one wrapped line of its title
+	first bool   // the line that carries the number and the severity dot
+}
+
+// vulnerabilityRows lays every finding out as the lines it will occupy.
+func (m Model) vulnerabilityRows(width int) []vulnerabilityRow {
+	// Wrapped lines sit under the title rather than under the severity dot.
+	body := max(1, width-2)
+	rows := make([]vulnerabilityRow, 0, len(m.snapshot.Vulnerabilities))
+	for i := range m.snapshot.Vulnerabilities {
+		for line, text := range strings.Split(wrapBlock(m.vulnerabilityTitle(i), body), "\n") {
+			rows = append(rows, vulnerabilityRow{index: i, text: text, first: line == 0})
 		}
-		marker := lipgloss.NewStyle().Foreground(color).Render("● ")
+	}
+	return rows
+}
+
+func (m Model) vulnerabilitiesView(width, height int) string {
+	rows := m.vulnerabilityRows(width)
+	start := min(max(0, m.vulnOffset), max(0, len(rows)-1))
+	end := min(len(rows), start+height)
+	lines := make([]string, 0, max(0, end-start))
+	for _, row := range rows[start:end] {
 		style := lipgloss.NewStyle().Foreground(textColor)
-		if i == m.selectedVuln {
+		if row.index == m.selectedVuln {
 			style = style.Bold(true).Foreground(white)
 		}
-		for row, titleLine := range m.vulnerabilityTitleLines(i, width) {
-			if len(lines) >= height {
-				break
+		prefix := "  "
+		if row.first {
+			severity := strings.ToLower(render.StringValue(m.snapshot.Vulnerabilities[row.index]["severity"]))
+			color, ok := panelSeverityColors[severity]
+			if !ok {
+				color = blue // matches SEVERITY_COLORS.get(severity, "#3b82f6")
 			}
-			prefix := "  "
-			if row == 0 {
-				prefix = marker
-			}
-			lines = append(lines, prefix+style.Render(titleLine))
+			prefix = lipgloss.NewStyle().Foreground(color).Render("● ")
 		}
+		lines = append(lines, prefix+style.Render(row.text))
 	}
 	return strings.Join(lines, "\n")
 }
 
+// vulnerabilityListWidth is the one width the findings list is laid out at, for
+// rendering and for every interaction alike. Wrapping a title at two widths a
+// column apart gives two different row counts, and then a click resolves to the
+// wrong finding and the scrollbar reports the wrong length.
+//
+// The panel is sidebarWidth-2 wide with a column of padding either side, and the
+// scrollbar takes one more. That last column is reserved whether or not the bar
+// is showing, so the layout does not shift as the list grows past the panel.
 func (m Model) vulnerabilityListWidth() int {
 	_, sidebarWidth, _, _ := m.layout()
-	return max(1, sidebarWidth-6)
+	return max(1, sidebarWidth-5)
 }
 
-func (m Model) vulnerabilityTitleLines(index, width int) []string {
+func (m Model) vulnerabilityTitle(index int) string {
 	title := render.StringValue(m.snapshot.Vulnerabilities[index]["title"])
 	if title == "" {
 		title = "Unknown Vulnerability"
 	}
-	return strings.Split(wrapBlock(title, max(1, width-2)), "\n")
+	return title
 }
 
+// vulnerabilityScrollRows reports the list length and position in rows, which is
+// what the scrollbar needs to move continuously.
 func (m Model) vulnerabilityScrollRows() (total, offset int) {
-	width := m.vulnerabilityListWidth()
-	for i := range m.snapshot.Vulnerabilities {
-		rows := len(m.vulnerabilityTitleLines(i, width))
-		total += rows
-		if i < m.vulnOffset {
-			offset += rows
-		}
-	}
-	return total, offset
-}
-
-func (m Model) vulnerabilityOffsetAtRow(targetRow int) int {
-	width := m.vulnerabilityListWidth()
-	row := 0
-	for i := range m.snapshot.Vulnerabilities {
-		row += len(m.vulnerabilityTitleLines(i, width))
-		if targetRow < row {
-			return i
-		}
-	}
-	return max(0, len(m.snapshot.Vulnerabilities)-1)
-}
-
-func (m Model) vulnerabilityVisibleEnd(start int) int {
-	height := m.vulnerabilityPageSize()
-	width := m.vulnerabilityListWidth()
-	rows := 0
-	end := min(max(0, start), len(m.snapshot.Vulnerabilities))
-	for end < len(m.snapshot.Vulnerabilities) {
-		itemRows := len(m.vulnerabilityTitleLines(end, width))
-		if rows > 0 && rows+itemRows > height {
-			break
-		}
-		rows += itemRows
-		end++
-		if rows >= height {
-			break
-		}
-	}
-	return end
+	return len(m.vulnerabilityRows(m.vulnerabilityListWidth())), m.vulnOffset
 }
 
+// vulnerabilityIndexAtRow maps a click on a visible row back to its finding.
 func (m Model) vulnerabilityIndexAtRow(row int) int {
-	width := m.vulnerabilityListWidth()
-	currentRow := 0
-	for i := m.vulnOffset; i < m.vulnerabilityVisibleEnd(m.vulnOffset); i++ {
-		currentRow += len(m.vulnerabilityTitleLines(i, width))
-		if row < currentRow {
-			return i
-		}
+	rows := m.vulnerabilityRows(m.vulnerabilityListWidth())
+	target := m.vulnOffset + row
+	if target < 0 || target >= len(rows) {
+		return -1
 	}
-	return -1
+	return rows[target].index
 }
 
+// ensureVulnerabilityVisible scrolls the least it can to bring the selected
+// finding into view, keeping the whole entry visible where it fits.
 func (m *Model) ensureVulnerabilityVisible() {
-	if len(m.snapshot.Vulnerabilities) == 0 {
+	rows := m.vulnerabilityRows(m.vulnerabilityListWidth())
+	if len(rows) == 0 {
 		m.vulnOffset = 0
 		return
 	}
-	if m.selectedVuln < m.vulnOffset {
-		m.vulnOffset = m.selectedVuln
+	height := m.vulnerabilityPageSize()
+	firstRow, lastRow := -1, -1
+	for row, entry := range rows {
+		if entry.index != m.selectedVuln {
+			continue
+		}
+		if firstRow < 0 {
+			firstRow = row
+		}
+		lastRow = row
 	}
-	for m.selectedVuln >= m.vulnerabilityVisibleEnd(m.vulnOffset) && m.vulnOffset < m.selectedVuln {
-		m.vulnOffset++
+	if firstRow < 0 {
+		m.vulnOffset = clampVulnerabilityOffset(m.vulnOffset, len(rows), height)
+		return
 	}
-	m.vulnOffset = min(m.vulnOffset, len(m.snapshot.Vulnerabilities)-1)
+	if firstRow < m.vulnOffset {
+		m.vulnOffset = firstRow
+	} else if lastRow >= m.vulnOffset+height {
+		// Prefer showing the whole entry, but never scroll its start out of view.
+		m.vulnOffset = min(firstRow, lastRow-height+1)
+	}
+	m.vulnOffset = clampVulnerabilityOffset(m.vulnOffset, len(rows), height)
+}
+
+func clampVulnerabilityOffset(offset, total, height int) int {
+	return min(max(0, offset), max(0, total-height))
 }
 
 func (m Model) vulnerabilityPageSize() int {
@@ -129,23 +138,52 @@ func (m Model) vulnerabilityPageSize() int {
 	return max(1, vulnHeight-2)
 }
 
+// vulnerabilityPageItems is how many findings a page step should move by: the
+// number of distinct entries currently on screen.
 func (m Model) vulnerabilityPageItems() int {
-	return max(1, m.vulnerabilityVisibleEnd(m.vulnOffset)-m.vulnOffset)
+	rows := m.vulnerabilityRows(m.vulnerabilityListWidth())
+	height := m.vulnerabilityPageSize()
+	start := min(max(0, m.vulnOffset), max(0, len(rows)))
+	end := min(len(rows), start+height)
+	seen := 0
+	previous := -1
+	for _, row := range rows[start:end] {
+		if row.index != previous {
+			seen++
+			previous = row.index
+		}
+	}
+	return max(1, seen)
 }
 
 func (m *Model) moveVulnerabilitySelection(delta int) {
 	m.selectedVuln = max(0, min(len(m.snapshot.Vulnerabilities)-1, m.selectedVuln+delta))
 }
 
+// keepVulnerabilitySelectionInWindow pulls the selection to the nearest finding
+// still on screen after the list has been scrolled directly.
 func (m *Model) keepVulnerabilitySelectionInWindow() {
-	if len(m.snapshot.Vulnerabilities) == 0 {
+	rows := m.vulnerabilityRows(m.vulnerabilityListWidth())
+	if len(rows) == 0 {
 		return
 	}
-	if m.selectedVuln < m.vulnOffset {
-		m.selectedVuln = m.vulnOffset
-	} else if end := m.vulnerabilityVisibleEnd(m.vulnOffset); m.selectedVuln >= end {
-		m.selectedVuln = max(m.vulnOffset, end-1)
+	height := m.vulnerabilityPageSize()
+	start := min(max(0, m.vulnOffset), max(0, len(rows)-1))
+	end := min(len(rows), start+height)
+	visible := rows[start:end]
+	if len(visible) == 0 {
+		return
 	}
+	for _, row := range visible {
+		if row.index == m.selectedVuln {
+			return
+		}
+	}
+	if m.selectedVuln < visible[0].index {
+		m.selectedVuln = visible[0].index
+		return
+	}
+	m.selectedVuln = visible[len(visible)-1].index
 }
 
 // statsView ports build_tui_stats_text + the version line appended in
@@ -182,6 +220,13 @@ func (m Model) confirmView(title string, width int, border, titleColor lipgloss.
 	return m.confirmDialog(title, "", width, border, titleColor, red, "Yes", "No")
 }
 
+// The mount prompt's buttons, named so the renderer and the click test cannot
+// drift apart.
+const (
+	mountConfirmLabel = "Mount"
+	mountCancelLabel  = "Skip"
+)
+
 // mountConfirmView asks before a target-less scan mounts the working directory.
 // It is a compact prompt docked in the corner of the live view: nothing is
 // prepared until it is answered, and the directory is a workspace rather than a
@@ -194,8 +239,8 @@ func (m Model) mountConfirmView() string {
 	}
 	title := render.Bold(amber).Render("△ Mount working directory?")
 	body := render.Col(white).Render(truncatePath(dir, width-4)) + "\n" +
-		render.Dim().Render("writable in the sandbox")
-	return m.cornerPrompt(title, body, width, "Confirm", "Cancel")
+		render.Dim().Render("writable in the sandbox · skip to run without it")
+	return m.cornerPrompt(title, body, width, mountConfirmLabel, mountCancelLabel)
 }
 
 // truncatePath keeps the tail of a path visible, which is the part that
@@ -298,6 +343,8 @@ func vulnerabilityBody(v map[string]any) string {
 		field("Ecosystem", render.StringValue(dep["package_ecosystem"]))
 		field("Installed Version", render.StringValue(dep["installed_version"]))
 		field("Fixed Version", render.StringValue(dep["fixed_version"]))
+		field("Introduced By", render.StringValue(dep["introduced_by"]))
+		field("Dependency Chain", render.StringValue(dep["dependency_path"]))
 	}
 	field("Endpoint", render.StringValue(v["endpoint"]))
 	field("Method", render.StringValue(v["method"]))
@@ -371,25 +418,116 @@ func (m Model) vulnerabilityDetail() string {
 	inner := max(1, width-8)
 	// Button row: right-aligned Copy / Done above a top rule (#vuln_detail_buttons).
 	rule := lipgloss.NewStyle().Foreground(lipgloss.Color("#1a1a1a")).Render(strings.Repeat("─", max(1, inner)))
-	copyLabel := "Copy"
-	if m.vulnerabilityCopied {
-		copyLabel = "Copied!"
-	} else if m.vulnerabilityCopyError != "" {
-		copyLabel = "Copy failed"
+	focused := m.focusedReportButton()
+	var stepping, acting []string
+	for _, button := range m.reportButtons() {
+		rendered := m.reportButton(button, button == focused)
+		if button == reportPrev || button == reportNext {
+			stepping = append(stepping, rendered)
+			continue
+		}
+		acting = append(acting, rendered)
 	}
-	copyButton := lipgloss.NewStyle().Foreground(lipgloss.Color("#525252"))
-	doneButton := lipgloss.NewStyle().Foreground(mid)
-	if m.modalChoice == 0 {
-		copyButton = copyButton.Background(lipgloss.Color("#363636")).Foreground(brightWhite).Bold(true).Padding(0, 1)
-	} else {
-		doneButton = doneButton.Background(lipgloss.Color("#363636")).Foreground(brightWhite).Bold(true).Padding(0, 1)
+	// Stepping sits on the left behind the position, acting on the right.
+	right := strings.Join(acting, "  ")
+	left := strings.Join(stepping, "  ")
+	if total := len(m.snapshot.Vulnerabilities); total > 1 {
+		left = render.Dim().Render(fmt.Sprintf("%d/%d", m.selectedVuln+1, total)) + "  " + left
 	}
-	buttons := copyButton.Render(copyLabel) + "  " + doneButton.Render("Done")
-	buttonRow := rule + "\n" + lipgloss.NewStyle().Width(inner).Align(lipgloss.Right).Render(buttons)
+	room := max(0, inner-lipgloss.Width(right))
+	buttonRow := rule + "\n" +
+		lipgloss.NewStyle().Width(room).Render(truncate(left, room)) + right
 	content := m.vulnerabilityScrollView() + "\n" + buttonRow
 	return lipgloss.NewStyle().Width(width-2).Height(height-2).Border(lipgloss.NormalBorder()).BorderForeground(lipgloss.Color("#262626")).Background(lipgloss.Color("#0a0a0a")).Padding(2, 3).Render(content)
 }
 
+// showVulnerability moves the open report to another finding, keeping the list
+// behind it in step and starting the new report at its top.
+func (m *Model) showVulnerability(index int) {
+	if index < 0 || index >= len(m.snapshot.Vulnerabilities) || index == m.selectedVuln {
+		return
+	}
+	m.selectedVuln = index
+	m.ensureVulnerabilityVisible()
+	// The copy state belongs to the report that was on screen, not this one.
+	m.vulnerabilityCopied = false
+	m.vulnerabilityCopyError = ""
+	m.resizeVulnerabilityViewport()
+	m.vulnViewport.GotoTop()
+}
+
+// The report's buttons. Prev and Next carry their arrows so a click test cannot
+// be fooled by the same word appearing in the body of a finding.
+const (
+	reportPrev = "‹ Prev"
+	reportNext = "Next ›"
+	reportCopy = "Copy"
+	reportDone = "Done"
+)
+
+// reportButtons is the row as it stands, left to right. Stepping is offered only
+// in the directions that have a report.
+func (m Model) reportButtons() []string {
+	previous, next := m.vulnerabilityNeighbors()
+	buttons := make([]string, 0, 4)
+	if previous {
+		buttons = append(buttons, reportPrev)
+	}
+	if next {
+		buttons = append(buttons, reportNext)
+	}
+	return append(buttons, reportCopy, reportDone)
+}
+
+// focusedReportButton is the button Enter would press. It falls back to Done when
+// the focused one has gone, which happens when stepping to either end drops a
+// direction from the row.
+func (m Model) focusedReportButton() string {
+	for _, button := range m.reportButtons() {
+		if button == m.reportFocus {
+			return button
+		}
+	}
+	return reportDone
+}
+
+// stepReportFocus moves along the row, wrapping at its ends.
+func (m *Model) stepReportFocus(delta int) {
+	buttons := m.reportButtons()
+	current := 0
+	for i, button := range buttons {
+		if button == m.focusedReportButton() {
+			current = i
+		}
+	}
+	m.reportFocus = buttons[clampCycle(current+delta, len(buttons))]
+}
+
+// vulnerabilityNeighbors reports which way the open report can be stepped. The
+// ends are not wrapped: a report is one of an ordered list, and rolling from the
+// last to the first hides that you reached the end.
+func (m Model) vulnerabilityNeighbors() (previous, next bool) {
+	return m.selectedVuln > 0, m.selectedVuln < len(m.snapshot.Vulnerabilities)-1
+}
+
+// reportButton renders one button of the report row. Copy reports the outcome of
+// the last attempt in its own label.
+func (m Model) reportButton(label string, focused bool) string {
+	if label == reportCopy {
+		switch {
+		case m.vulnerabilityCopied:
+			label = "Copied!"
+		case m.vulnerabilityCopyError != "":
+			label = "Copy failed"
+		}
+	}
+	if focused {
+		return lipgloss.NewStyle().Background(lipgloss.Color("#363636")).
+			Foreground(brightWhite).Bold(true).Padding(0, 1).Render(label)
+	}
+	return lipgloss.NewStyle().Foreground(lipgloss.Color("#525252")).Render(label)
+}
+
 func (m *Model) startVulnerabilityCopy() tea.Cmd {
 	m.vulnerabilityCopied = false
 	m.vulnerabilityCopyError = ""

strix/interface/tui/internal/render/dependency.go

@@ -57,6 +57,12 @@ func renderDependencyReport(args map[string]any, result any) string {
 	section("Description", StringValue(args["description"]))
 	section("Impact", StringValue(args["impact"]))
 	section("Technical Analysis", StringValue(args["technical_analysis"]))
+	if reach := StringValue(args["reachability"]); reach != "" && reach != "unknown" {
+		b.WriteString("\n\n" + Bold(Field).Render("Usage evidence: ") + reach)
+		if ev := StringValue(args["reachability_evidence"]); ev != "" {
+			b.WriteString("\n" + ev)
+		}
+	}
 	section("Assumptions", StringValue(args["assumptions"]))
 	section("Remediation", StringValue(args["remediation_steps"]))
 	if title == "" {

strix/interface/tui/live_view.py

@@ -431,7 +431,7 @@ _INTERNAL_TURN_PREFIXES = (
     "== Inherited context from parent",
     # strix.core.execution: the no-tool-call recovery nudge, both modes.
     "Your previous message ended a turn without a tool call.",
-    "Your previous response ended the autonomous Strix run without a lifecycle tool call.",
+    "Your previous response ended the autonomous run without a lifecycle tool call.",
     # strix.core.hooks: budget warnings, the only notices injected unwrapped.
     *(
         f"[{label}] {subject}"

strix/interface/utils.py

@@ -1102,7 +1102,7 @@ def resolve_diff_scope_context(
 def _is_http_git_repo(url: str) -> bool:
     check_url = f"{url.rstrip('/')}/info/refs?service=git-upload-pack"
     try:
-        with requests.get(check_url, headers={"User-Agent": "git/strix"}, timeout=10) as resp:
+        with requests.get(check_url, headers={"User-Agent": "git/2.43.0"}, timeout=10) as resp:
             if resp.status_code >= 400:
                 return resp.status_code == 401
             return "x-git-upload-pack-advertisement" in resp.headers.get("Content-Type", "")

strix/llm/compaction.py

@@ -294,6 +294,7 @@ async def _summarize(model: str, prompt: str, max_tokens: int) -> str | None:
         request_timeout=llm.timeout,
         prompt_cache=False,
         extra_headers=llm.extra_headers,
+        has_tools=False,
     ).resolve(ModelSettings(max_tokens=max_tokens))
     try:
         response = (

strix/report/dedupe.py

@@ -62,6 +62,7 @@ def _dedupe_model_settings(
         # must never receive the main endpoint's credentials. A dedicated model
         # gets its own DEDUPE_LLM_EXTRA_HEADERS instead.
         extra_headers=dedupe.extra_headers if dedupe.model else llm.extra_headers,
+        has_tools=False,
     )
     extra = _dedupe_extra_args(dedupe)
     if extra:
@@ -183,6 +184,24 @@ def _dependency_identity(report: dict[str, Any]) -> tuple[str, str, str] | None:
     return cve, ecosystem, package_name
 
 
+def _manifest_path(report: dict[str, Any]) -> str:
+    metadata = report.get("dependency_metadata")
+    if not isinstance(metadata, dict):
+        return ""
+    return str(metadata.get("manifest_path") or "").strip()
+
+
+def _distinct_manifest_paths(candidate: dict[str, Any], report: dict[str, Any]) -> bool:
+    """Same CVE/package observed in two different manifests is two findings.
+
+    Only applies when both sides carry a manifest_path; a missing path keeps
+    the legacy CVE/package/ecosystem identity.
+    """
+    candidate_path = _manifest_path(candidate)
+    report_path = _manifest_path(report)
+    return bool(candidate_path and report_path and candidate_path != report_path)
+
+
 def _report_cve(report: dict[str, Any]) -> str:
     return str(report.get("cve") or "").strip().upper()
 
@@ -228,6 +247,8 @@ def _check_dependency_duplicate(
             report_cve, report_ecosystem, report_package_name = report_identity
             if (report_cve, report_package_name) != (cve, package_name):
                 continue
+            if _distinct_manifest_paths(candidate, report):
+                continue
             if report_ecosystem == ecosystem:
                 return {
                     "is_duplicate": True,

strix/report/sarif.py

@@ -531,6 +531,10 @@ def _result_properties(
         if value not in (None, ""):
             strix[key] = value
 
+    dependency_metadata = report.get("dependency_metadata")
+    if isinstance(dependency_metadata, dict) and dependency_metadata:
+        strix["dependency_metadata"] = dependency_metadata
+
     # SARIF is written for external upload (code-scanning / ASPM), so it must
     # NOT carry the weaponized exploit payload — that stays a local run
     # artifact (vulnerabilities.json / the finding MD). We surface the PoC

strix/report/writer.py

@@ -205,6 +205,8 @@ def render_vulnerability_md(report: dict[str, Any]) -> str:  # noqa: PLR0912, PL
         ("Ecosystem", dep_meta.get("package_ecosystem")),
         ("Installed Version", dep_meta.get("installed_version")),
         ("Fixed Version", dep_meta.get("fixed_version")),
+        ("Introduced By", dep_meta.get("introduced_by")),
+        ("Dependency Chain", dep_meta.get("dependency_path")),
         ("Endpoint", report.get("endpoint")),
         ("Method", report.get("method")),
         ("CVE", report.get("cve")),

strix/skills/__init__.py

@@ -4,6 +4,9 @@ import threading
 from collections import Counter
 from collections.abc import Iterator
 from pathlib import Path
+from typing import TypeGuard
+
+import yaml
 
 from strix.telemetry import posthog, scarf
 from strix.utils.resource_paths import get_strix_resource_path
@@ -11,12 +14,17 @@ from strix.utils.resource_paths import get_strix_resource_path
 
 logger = logging.getLogger(__name__)
 
-_FRONTMATTER_PATTERN = re.compile(r"^---\s*\n.*?\n---\s*\n", re.DOTALL)
+_FRONTMATTER_PATTERN = re.compile(r"^---\s*\n(?P<body>.*?)\n---\s*\n", re.DOTALL)
 
 _INTERNAL_SKILL_CATEGORIES: frozenset[str] = frozenset({"scan_modes", "coordination"})
 _ROOT_SKILL_CATEGORY = "root"
 
 _EXTRA_SKILL_DIRS: list[Path] = []
+_SKILL_METADATA_CACHE: dict[tuple[Path, int, int], dict[str, str]] = {}
+
+
+def _is_frontmatter_mapping(value: object) -> TypeGuard[dict[object, object]]:
+    return isinstance(value, dict)
 
 
 def register_skill_dir(path: str | Path) -> None:
@@ -109,13 +117,18 @@ def _get_ambiguous_skill_names() -> set[str]:
     return {name for name, count in counts.items() if count > 1}
 
 
-def _qualified_skill_files(skill_name: str) -> list[Path]:
+def _qualified_skill_file_for_name(skill_name: str) -> Path | None:
     category, _, name = skill_name.partition("/")
     for skills_dir in skill_search_dirs():
         candidate = _qualified_skill_file(skills_dir, category, name)
         if candidate is not None:
-            return [candidate]
-    return []
+            return candidate
+    return None
+
+
+def _qualified_skill_files(skill_name: str) -> list[Path]:
+    candidate = _qualified_skill_file_for_name(skill_name)
+    return [candidate] if candidate is not None else []
 
 
 def _bare_skill_files(skill_name: str) -> list[Path]:
@@ -145,10 +158,59 @@ def _bare_skill_files(skill_name: str) -> list[Path]:
     return candidates
 
 
-def get_available_skills() -> dict[str, list[str]]:
-    grouped: dict[str, list[str]] = {}
+def _parse_skill_content(content: str, source: Path | None = None) -> tuple[dict[str, str], str]:
+    """Parse skill frontmatter once and return metadata plus markdown body."""
+    frontmatter = _FRONTMATTER_PATTERN.match(content)
+    if frontmatter is None:
+        return {}, content.lstrip()
+
+    try:
+        parsed: object = yaml.safe_load(frontmatter.group("body"))
+    except yaml.YAMLError as error:
+        logger.warning("Failed to parse skill frontmatter %s: %s", source or "<content>", error)
+        parsed = None
+    if not _is_frontmatter_mapping(parsed):
+        logger.warning("Skill frontmatter is not a mapping: %s", source or "<content>")
+        return {}, content[frontmatter.end() :].lstrip()
+
+    metadata = {str(key): "" if value is None else str(value) for key, value in parsed.items()}
+    return metadata, content[frontmatter.end() :].lstrip()
+
+
+def _read_skill_metadata(file_path: Path) -> dict[str, str]:
+    try:
+        stat = file_path.stat()
+    except OSError:
+        logger.warning("Skill file disappeared while reading metadata: %s", file_path)
+        return {}
+    cache_key = (file_path, stat.st_mtime_ns, stat.st_size)
+    cached = _SKILL_METADATA_CACHE.get(cache_key)
+    if cached is not None:
+        return cached
+    try:
+        content = file_path.read_text(encoding="utf-8")
+    except (OSError, ValueError):
+        logger.warning("Failed to read skill metadata: %s", file_path)
+        return {}
+    metadata, _ = _parse_skill_content(content, file_path)
+    _SKILL_METADATA_CACHE[cache_key] = metadata
+    return metadata
+
+
+def get_available_skills() -> dict[str, list[dict[str, str]]]:
+    grouped: dict[str, list[dict[str, str]]] = {}
     for category, name in _iter_user_skill_files():
-        grouped.setdefault(category, []).append(name)
+        file_path = _qualified_skill_file_for_name(f"{category}/{name}")
+        if file_path is None:
+            logger.warning(
+                "Skill disappeared while gathering available skills: %s/%s",
+                category,
+                name,
+            )
+            continue
+        metadata = _read_skill_metadata(file_path)
+        description = " ".join(metadata.get("description", "").split())
+        grouped.setdefault(category, []).append({"name": name, "description": description})
     return grouped
 
 
@@ -228,7 +290,8 @@ def load_skills(skill_names: list[str]) -> dict[str, str]:
             continue
 
         var_name = skill_name.split("/")[-1]
-        skill_content[var_name] = _FRONTMATTER_PATTERN.sub("", content).lstrip()
+        _, skill_body = _parse_skill_content(content, file_path)
+        skill_content[var_name] = skill_body
         logger.debug("Loaded skill: %s -> %s", skill_name, var_name)
         _track_skill_loaded(var_name, file_path)
 

strix/skills/cloud/gcp.md

@@ -16,7 +16,7 @@ GCP misconfigurations expose project data, service account keys, and lateral mov
 
 **Storage & Data**
 - Cloud Storage (GCS) buckets and objects
-- BigQuery datasets, Cloud SQL instances, Firestore (see `firebase_firestore` skill)
+- BigQuery datasets, Cloud SQL instances, Firestore (see `firebase` skill)
 - Secret Manager, Cloud KMS keys
 
 **Compute**

strix/skills/custom/dependency_cve_scanning.md

@@ -28,7 +28,7 @@ Run from the repo root and store output in the shared artifact directory used by
 the source-aware pass:
 
 ```bash
-ART=/workspace/.strix-source-aware
+ART=/workspace/.source-aware
 mkdir -p "$ART"
 
 # Record the vuln DB age so a stale DB is a visible signal, not a silent clean scan.
@@ -39,9 +39,11 @@ trivy version --format json 2>/dev/null | tee "$ART/trivy-version.json"
 # sandbox with egress gets the freshest CVEs; if the update fails, fall back to the
 # cached DB instead of failing the scan. --offline-scan keeps per-package advisory
 # lookups offline.
-trivy fs --scanners vuln --timeout 30m --offline-scan \
+# --list-all-pkgs includes the package graph (Relationship + DependsOn) needed
+# to attribute transitive CVEs to the direct dependency that introduces them.
+trivy fs --scanners vuln --timeout 30m --offline-scan --list-all-pkgs \
   --format json --output "$ART/trivy-sca.json" . \
-  || trivy fs --scanners vuln --timeout 30m --offline-scan --skip-db-update \
+  || trivy fs --scanners vuln --timeout 30m --offline-scan --skip-db-update --list-all-pkgs \
        --format json --output "$ART/trivy-sca.json" . \
   || true
 ```
@@ -75,18 +77,122 @@ For each entry under `.Results[].Vulnerabilities[]` in `trivy-sca.json`, collect
 - `CVSS` — the published advisory base score
 - `PrimaryURL` / references — to verify the advisory
 
-Deduplicate by `(CVE, PkgName, InstalledVersion)`. File one
-`create_dependency_report` per CVE — do not batch multiple CVEs into one report.
+Deduplicate by `(CVE, PkgName, Target)` — the same CVE/package observed in two
+different manifests (e.g. two workspaces of a monorepo) is two findings, one
+per manifest. File one `create_dependency_report` per CVE — do not batch
+multiple CVEs into one report.
+
+### Attribute transitive CVEs to the direct dependency
+
+With `--list-all-pkgs`, each `.Results[].Packages[]` entry carries `ID`
+(`name@version`), `Relationship` (`direct` / `indirect`) and `DependsOn` (the
+`ID`s it resolves to). For every vulnerable package that is **indirect**, walk
+the `DependsOn` graph backwards to find the `direct` package(s) whose closure
+contains it, then pass to `create_dependency_report`:
+
+- `introduced_by` — the direct dependency as `name@version` (e.g.
+  `express@4.18.1`). If several direct dependencies pull it in, pick the
+  primary one and name the rest in `technical_analysis`.
+- `dependency_path` — the shortest resolution chain from that direct
+  dependency to the vulnerable package, joined with ` > ` (e.g.
+  `express@4.18.1 > body-parser@1.20.0 > qs@6.10.2`).
+- Omit both when the vulnerable package is itself a direct dependency.
+
+If the ecosystem's lockfile gives trivy no graph (`DependsOn` absent), derive
+the chain from the package manager instead (`npm ls <pkg>`, `pnpm why <pkg>`,
+`yarn why <pkg>`, `pipdeptree --reverse -p <pkg>`, `go mod graph`,
+`mvn dependency:tree`, ...) — and if that also fails, leave the fields out
+rather than guessing.
+
+For transitive findings, `remediation_steps` must be actionable at the
+**direct-dependency level**: upgrading the vulnerable package directly is
+usually impossible from the app's own manifest. Say which direct dependency to
+bump (a version whose closure resolves the fixed version), or how to force the
+resolution (npm `overrides` / yarn `resolutions` / pnpm `pnpm.overrides` /
+Maven `dependencyManagement` / Gradle resolution strategy / `go mod edit`),
+not just "upgrade <vulnerable pkg> to <fixed>".
+
+### Usage / reachability analysis (required for every dependency CVE)
+
+For every CVE you are about to report, run a static usage analysis and record
+the result in the structured `reachability` + `reachability_evidence` fields.
+The level is an **evidence ladder, never an exploitability verdict** — claim
+only what you proved, and cite the proof. It never changes severity (that is
+`advisory_cvss` alone); it exists so the reader can prioritize.
+
+**Go — use govulncheck (real call-graph analysis):**
+
+```bash
+# Symbol-level: reports only vulnerabilities whose vulnerable functions are
+# actually reachable from application code. Needs the Go toolchain + module
+# deps; if either is missing, fall back to the checks below rather than
+# claiming a level.
+if command -v govulncheck >/dev/null && go version >/dev/null 2>&1; then
+  govulncheck -format json ./... > "$ART/govulncheck.json" || true
+fi
+```
+
+- A finding with a call stack ⇒ `reachability=reachable_call_path`, put the
+  call-path excerpt (entrypoint → vulnerable function) in
+  `reachability_evidence`.
+- Listed as affecting a required module but with no reachable symbol ⇒ fall
+  back to the import/symbol checks below (`imported` / `not_imported`).
+
+**All other ecosystems — import check, then symbol match:**
+
+1. **Import check.** Search application code (exclude lockfiles, vendored
+   deps, `node_modules`, build output) for imports of the vulnerable package:
+   `ast-grep`/`rg` for `import`/`require`/`from X import` of the package (and
+   its ecosystem import name, which may differ from the registry name, e.g.
+   `PyYAML` → `yaml`). No hits ⇒ `not_imported`, with the search scope stated
+   in `reachability_evidence`. For a **transitive** dependency, the check is
+   whether application code imports it directly; if not, it is reachable only
+   through the direct dependency — check whether the direct dep's usage can
+   hit it (if unclear, use `imported` when the direct dep is used at all).
+2. **Symbol match — per CVE, not per package.** Read each CVE's own advisory
+   (GHSA/NVD/OSV `affected[].ecosystem_specific.imports` or the advisory
+   text) for the affected functions/classes/APIs. Search application code for
+   those symbols (`ast-grep` pattern or `rg -n`). Hits ⇒
+   `vulnerable_symbol_used`, with repo-relative `file:line` of each hit (up
+   to a handful) in `reachability_evidence`. Imported but no affected-symbol
+   usage found (or the advisory names no symbols) ⇒ `imported`.
+   Different CVEs on the same package usually affect **different** symbols
+   (one hits a parser, another a header check) — never copy one CVE's
+   verdict/evidence onto its siblings; run the symbol search against each
+   CVE's own affected-symbol list. The import check (step 1) is the only
+   part shared across a package's CVEs.
+3. If the analysis was not performed or is inconclusive (obfuscated code,
+   dynamic loading, unparsable sources) ⇒ `unknown` and say why in
+   `assumptions`.
+
+Cheap-first budgeting: the import check is one search per package — always do
+it. Do the per-CVE symbol match for every CVE whose advisory names affected
+symbols (they can be batched into one multi-pattern search per package);
+prioritize `critical`/`high`/KEV when the budget is tight; a CVE whose symbol
+search was skipped may still be reported as `imported` (the import check is
+real evidence), but its `reachability_evidence` must state that the
+affected-symbol check was not performed, so a skipped search is never
+mistaken for a completed one with no hits. Never let this analysis stall
+reporting — `unknown` with a reason beats an unverified claim.
+
+Anti-overclaim rules:
+
+- `not_imported` still does NOT mean safe (dynamic `import()`/reflection/
+  framework wiring evade static search) — never phrase it as "not exploitable".
+- `reachable_call_path` is reserved for call-graph tools (govulncheck); a
+  symbol grep hit is `vulnerable_symbol_used`, no matter how convinced you are.
+- The tool rejects any level other than `unknown` without
+  `reachability_evidence`.
 
 ### Reachability is a confidence modifier, not a gate
 
 Do NOT suppress or downgrade a known CVE just because you could not prove the
 vulnerable code path is reachable. Report it, set `advisory_cvss` from the
-advisory, and use `assumptions` to note reachability (e.g. "the vulnerable
-`template()` API does not appear to be imported in application code, so practical
-exploitability is uncertain"). If you *can* show reachability or chain it into a
-dynamic exploit, do that and report it as a normal dynamic finding with
-`create_vulnerability_report` instead.
+advisory, record the usage analysis in `reachability`/`reachability_evidence`,
+and use `assumptions` for anything softer. If you *can* actually trigger the
+vulnerable path or chain it into a dynamic exploit, additionally report that
+as a normal dynamic finding with `create_vulnerability_report` (the standalone
+CVE stays in its own `create_dependency_report`).
 
 ## Reporting
 
@@ -107,6 +213,12 @@ findings and rejects empty PoC fields):
   - `package_ecosystem` — normalized ecosystem from `.Results[].Type` (lowercased,
     e.g. `npm`, `pypi`, `go`, `maven`, `rubygems`, `cargo`) (required).
   - `fixed_version` — `FixedVersion` (leave empty only if no fix is published).
+  - `manifest_path` — the repo-relative `Target` lockfile/manifest path
+    (required). Strip any scan-workspace or repo checkout directory prefix so
+    the path is relative to the repository root (e.g. `package-lock.json`,
+    `services/api/pom.xml`); the tool rejects absolute paths and `..` segments.
+    This binds the finding to the exact file so remediation can target the
+    right repository.
 - Reference the repo-relative `Target` lockfile path in `description` /
   `technical_analysis` (no leading slash) so the finding is traceable.
 - Put the concrete proof in `description` / `technical_analysis`: package name,
@@ -120,7 +232,8 @@ findings and rejects empty PoC fields):
 - Set `cwe` to the most specific `CWE-NNN` when the advisory names one.
 - Do NOT cap severity at LOW just because there is no dynamic reproduction — use
   the advisory score.
-- Use `assumptions` for reachability/exploitability caveats.
+- Set `reachability` + `reachability_evidence` from the usage analysis above;
+  use `assumptions` for anything softer (confidence, caveats, analysis limits).
 
 Verify the CVE with `web_search` when available before reporting. Never guess or
 hallucinate a CVE id.
@@ -136,3 +249,5 @@ hallucinate a CVE id.
 - Do not silently drop a known CVE because it lacks a dynamic PoC — that is the
   exact failure this skill prevents.
 - Do not downgrade advisory severity for lack of dynamic reproduction.
+- Do not claim a `reachability` level the evidence does not prove — `unknown`
+  with a reason is always acceptable; an overclaimed level never is.

strix/skills/custom/source_aware_sast.md

@@ -12,7 +12,7 @@ Use this skill for source-heavy analysis where static and structural signals sho
 Run tools from repo root and store outputs in a dedicated artifact directory:
 
 ```bash
-mkdir -p /workspace/.strix-source-aware
+mkdir -p /workspace/.source-aware
 ```
 
 ## Baseline Coverage Bundle (Recommended)
@@ -20,7 +20,7 @@ mkdir -p /workspace/.strix-source-aware
 Run this baseline once per repository before deep narrowing:
 
 ```bash
-ART=/workspace/.strix-source-aware
+ART=/workspace/.source-aware
 mkdir -p "$ART"
 
 semgrep scan --config p/default --config p/golang --config p/secrets \
@@ -30,7 +30,7 @@ python3 - <<'PY'
 import json
 from pathlib import Path
 
-art = Path("/workspace/.strix-source-aware")
+art = Path("/workspace/.source-aware")
 semgrep_json = art / "semgrep.json"
 targets_file = art / "sg-targets.txt"
 
@@ -70,10 +70,10 @@ Use Semgrep as the default static triage pass:
 ```bash
 # Preferred deterministic profile set (works with --metrics=off)
 semgrep scan --config p/default --config p/golang --config p/secrets \
-  --metrics=off --json --output /workspace/.strix-source-aware/semgrep.json .
+  --metrics=off --json --output /workspace/.source-aware/semgrep.json .
 
 # If you choose auto config, do not combine it with --metrics=off
-semgrep scan --config auto --json --output /workspace/.strix-source-aware/semgrep-auto.json .
+semgrep scan --config auto --json --output /workspace/.source-aware/semgrep-auto.json .
 ```
 
 If diff scope is active, restrict to changed files first, then expand only when needed.
@@ -85,8 +85,8 @@ Use `sg` for structure-aware code hunting:
 ```bash
 # Ruleless structural pass over deterministic target list (no sgconfig.yml required)
 xargs -r -n 200 sg run --pattern '$F($$$ARGS)' --json=stream \
-  < /workspace/.strix-source-aware/sg-targets.txt \
-  > /workspace/.strix-source-aware/ast-grep.json 2> /workspace/.strix-source-aware/ast-grep.log || true
+  < /workspace/.source-aware/sg-targets.txt \
+  > /workspace/.source-aware/ast-grep.json 2> /workspace/.source-aware/ast-grep.log || true
 ```
 
 Target high-value patterns such as:
@@ -110,15 +110,15 @@ Use outputs to improve route/symbol/sink maps for subsequent targeted scans.
 Detect hardcoded credentials:
 
 ```bash
-gitleaks detect --source . --report-format json --report-path /workspace/.strix-source-aware/gitleaks.json
-trufflehog filesystem --json . > /workspace/.strix-source-aware/trufflehog.json
+gitleaks detect --source . --report-format json --report-path /workspace/.source-aware/gitleaks.json
+trufflehog filesystem --json . > /workspace/.source-aware/trufflehog.json
 ```
 
 Run repository-wide dependency and config checks:
 
 ```bash
 trivy fs --scanners vuln,misconfig --timeout 30m --offline-scan \
-  --format json --output /workspace/.strix-source-aware/trivy-fs.json . || true
+  --format json --output /workspace/.source-aware/trivy-fs.json . || true
 ```
 
 Known-CVE dependency findings are the one exception to the "report only after
@@ -132,9 +132,9 @@ For frontends and Node services, layer these on top of the language-agnostic
 passes above:
 
 ```bash
-retire --path . --outputformat json --outputpath /workspace/.strix-source-aware/retire.json || true
+retire --path . --outputformat json --outputpath /workspace/.source-aware/retire.json || true
 eslint --no-config-lookup --rule '{"no-eval":2,"no-implied-eval":2}' \
-  -f json -o /workspace/.strix-source-aware/eslint.json . || true
+  -f json -o /workspace/.source-aware/eslint.json . || true
 ```
 
 When you hit a minified bundle, run `js-beautify <file>` for a readable

strix/skills/technologies/active_directory.md

@@ -202,7 +202,7 @@ Confirm with a version/patch check before firing — these are destructive.
 
 ## Tooling
 
-**None of the AD tools below ship in the Strix sandbox by default** (the image is Kali-rolling but installs only web-focused tooling). Install what the task needs — the sandbox has `pipx`, `pip`, `go`, `git`, and Kali's apt repos. AD testing also requires **network reachability to the target DC/subnet**, which the default web-target sandbox usually lacks; confirm connectivity first.
+**None of the AD tools below ship in the sandbox by default** (the image is Kali-rolling but installs only web-focused tooling). Install what the task needs — the sandbox has `pipx`, `pip`, `go`, `git`, and Kali's apt repos. AD testing also requires **network reachability to the target DC/subnet**, which the default web-target sandbox usually lacks; confirm connectivity first.
 
 ```
 # Python identity toolkit (impacket = GetUserSPNs/GetNPUsers/secretsdump/ntlmrelayx/getST/addcomputer/rbcd)

strix/skills/technologies/firebase.md

@@ -1,9 +1,9 @@
 ---
-name: firebase-firestore
-description: Firebase/Firestore security testing covering security rules, Cloud Functions, and client-side trust issues
+name: firebase
+description: Firebase security testing covering Firestore, Storage rules, Realtime Database, Auth, Functions, and client-side trust issues
 ---
 
-# Firebase / Firestore
+# Firebase
 
 Security testing for Firebase applications. Focus on Firestore/Realtime Database rules, Cloud Storage exposure, callable/onRequest Functions trusting client input, and incorrect ID token validation.
 
@@ -30,7 +30,17 @@ Security testing for Firebase applications. Focus on Firestore/Realtime Database
 **Endpoints**
 - Firestore REST: `https://firestore.googleapis.com/v1/projects/<project>/databases/(default)/documents/<path>`
 - Realtime DB: `https://<project>.firebaseio.com/.json`
-- Storage REST: `https://storage.googleapis.com/storage/v1/b/<bucket>`
+- GCS JSON API: `https://storage.googleapis.com/storage/v1/b/<bucket>`
+- Firebase Storage rules API: `https://firebasestorage.googleapis.com/v0/b/<bucket>/o`
+
+Cloud Storage has two front doors with different authorization engines:
+
+| Front door | Authorization engine |
+| --- | --- |
+| `storage.googleapis.com/<bucket>/<object>` and `/storage/v1/b/<bucket>` | GCS IAM and per-object ACLs |
+| `firebasestorage.googleapis.com/v0/b/<bucket>/o` | Firebase Storage Security Rules |
+
+A `403` from a GCS URL does not prove that Firebase Storage rules deny access. Always test both doors.
 
 **Auth**
 - Google-signed ID tokens (iss: `accounts.google.com` or `securetoken.google.com/<project>`)
@@ -117,9 +127,43 @@ exists(/databases/(default)/documents/orgs/$(org)/members/$(request.auth.uid))
 - Public reads on sensitive buckets/paths
 - Signed URLs with long TTL, no content-disposition controls, replayable across tenants
 - List operations exposed: `/o?prefix=` enumerates object keys
+- Firebase Storage rules allowing unauthenticated or overly broad reads and writes
+
+**Firebase Storage rules checks**
+
+Probe the rules door separately from GCS IAM and ACLs:
+
+1. Unauthenticated list: `GET https://firebasestorage.googleapis.com/v0/b/<bucket>/o?prefix=<known-prefix>`
+2. Unauthenticated read of a known object path
+3. Unauthenticated write/upload to a uniquely named test object
+4. Repeat list, read, and write as an anonymous-auth principal when anonymous sign-in is enabled
+5. Repeat the same matrix as a low-privilege authenticated user
+
+Write access is as important as read access and is routinely missed. Record status, response body, and object existence after each attempt; clean up only test objects that the test principal created.
+
+Review rules source when present and flag:
+
+- `allow read, write: if request.time < timestamp.date(...)` — the common console test-mode time gate
+- `{allPaths=**}` catch-alls
+- `request.auth != null` as the sole authorization gate
+- Claim-presence checks such as `request.auth.token.roles.size() > 0` without role or tenant validation
+
+Storage rules use OR-across-matches semantics: a later permissive match can reopen a path that an earlier match denied. Review every matching path, not only the most specific-looking deny.
+
+**Bucket discovery**
+
+- Extract `storageBucket` from `firebase.apps[0].options` and `NEXT_PUBLIC_FIREBASE_*` values in JavaScript bundles and source.
+- Check `<project>.appspot.com` and `<project>.firebasestorage.app` bucket conventions.
+
+**ACL and IAM checks are separate**
+
+- Sweep object ACLs for `allUsers` and `allAuthenticatedUsers`, including objects made public by Admin SDK `makePublic()` or writers using `public: true`. Per-object public ACLs persist after Firebase rules are tightened and can remain on older prefixes.
+- Check bucket IAM for `allUsers` and `allAuthenticatedUsers`.
+- Check whether Uniform Bucket-Level Access is disabled; legacy object ACLs matter when it is off.
+- Account for CDN caching of previously public objects; cache-bust when verifying a revocation.
 
 **Tests**
-- GET gs:// paths via HTTPS without auth; verify Content-Type and `Content-Disposition: attachment`
+- GET GCS object paths via HTTPS without auth; verify Content-Type and `Content-Disposition: attachment`
 - Generate and reuse signed URLs across accounts and paths; try case/URL-encoding variants
 - Upload HTML/SVG and verify `X-Content-Type-Options: nosniff`; check for script execution
 
@@ -189,12 +233,19 @@ Apps often implement multi-tenant data models (`orgs/<orgId>/...`). Bind tenant
 
 ## Testing Methodology
 
-1. **Extract config** - Get project config from client bundle
-2. **Obtain principals** - Collect tokens for unauth, anonymous, user A/B, admin
+1. **Extract config** - Get project and storage bucket config from client bundles and source
+2. **Obtain principals** - Collect tokens for unauth, anonymous, user A/B, and admin where authorized
 3. **Build matrix** - Resource × Action × Principal across Firestore/Realtime/Storage/Functions
-4. **SDK vs REST** - Exercise every action via both to detect parity gaps
-5. **Seed IDs** - Start from list/query paths to gather document IDs
-6. **Cross-principal** - Swap document paths, tenants, and user IDs across principals
+4. **Exercise both Storage doors** - Test Firebase Storage rules endpoints separately from GCS IAM/ACL URLs
+5. **SDK vs REST** - Exercise every action via both to detect parity gaps
+6. **Seed IDs** - Start from list/query paths to gather document and object paths
+7. **Cross-principal** - Swap document paths, tenants, and user IDs across principals
+
+## Whitebox Rules Review
+
+- Inspect `firebase.json`, `.firebaserc`, deployment scripts, CI configuration, and infrastructure code for `storage.rules` / `firestore.rules` declarations.
+- If `firebase.json` has no `storage` or `firestore` block, or the referenced rules file is absent from the tree, treat the live rules as unmanaged and force the live probe matrix. Absence of rules IaC is itself a finding; never conclude that there is nothing to review.
+- Correlate configured rule files with deployed project and bucket identifiers. A source rule file for a different project does not establish live protection.
 
 ## Tooling
 
@@ -206,6 +257,7 @@ Apps often implement multi-tenant data models (`orgs/<orgId>/...`). Bind tenant
 ## Validation Requirements
 
 - Owner vs non-owner Firestore queries showing unauthorized access or metadata leak
-- Cloud Storage read/write beyond intended scope (public object, signed URL reuse, list exposure)
+- Firebase Storage unauthenticated, anonymous, or low-privilege read/list/write beyond intended scope, with minimal reproducible requests and observed deltas
+- GCS object ACL or bucket IAM access beyond intended scope, including public object persistence after rules changes
 - Function accepting forged/foreign identity (wrong `aud`/`iss`) or trusting client `uid`/`orgId`
 - Minimal reproducible requests with roles/tokens used and observed deltas

strix/skills/tooling/agent_browser.md

@@ -58,6 +58,26 @@ agent-browser screenshot
 The browser stays running across commands so these feel like a single
 session. Use `agent-browser close` (or `close --all`) when you're done.
 
+The default session is **shared with every other agent in the sandbox** — if
+another agent navigates it, your page and your refs are gone from under you. So
+claim your own by passing `--session <your-agent-name>` on **every** command:
+
+```bash
+agent-browser --session recon-3 open https://example.com
+agent-browser --session recon-3 snapshot -i
+agent-browser --session recon-3 close        # when done with the target
+```
+
+The examples in the rest of this skill omit `--session` to keep them readable;
+keep passing yours. Each session is a separate Chromium (~340 MB) on a shared
+box, so hold one rather than several, and close it when you're finished.
+
+A browser left idle for 3 minutes is reclaimed automatically to free memory for
+the other agents; the next command relaunches it, but the page, tabs, refs and
+cookies are gone. If you're authenticated and about to go do something else for a
+while, save the state first (see
+[Persist session across runs](#persist-session-across-runs)).
+
 ## Reading a page
 
 ```bash
@@ -307,6 +327,16 @@ agent-browser --session b fill @e1 "bob@test.com"
 `AGENT_BROWSER_SESSION=myapp` sets the default session for the current
 shell.
 
+Use a session named after yourself for your own work — that's what keeps a
+concurrent agent from navigating the page out from under you. Every session is a
+separate Chromium though, so hold one at a time rather than a collection, and
+close each one when its flow is finished:
+
+```bash
+agent-browser --session a close
+agent-browser --session b close
+```
+
 ### Mock network requests
 
 ```bash
@@ -368,8 +398,11 @@ agent-browser dialog dismiss          # cancel
 ## Readiness & recovery
 
 The first `agent-browser open` in a session launches the headless-Chrome
-daemon; later commands reuse it. Distinguish the two failure modes and react
-differently — do **not** blindly re-run the same failing command in a loop:
+daemon; later commands reuse it. A daemon left idle for 3 minutes shuts itself
+down to free memory for the other agents, so an `open` after a long gap is a
+fresh browser rather than a resumed one — expect to re-navigate, and re-`state
+load` if you were logged in. Distinguish the failure modes and react differently
+— do **not** blindly re-run the same failing command in a loop:
 
 - **Daemon / connection failure** (`Failed to connect`, `connection refused`,
   socket missing, `browser not running`): the daemon isn't up or has died. Run

strix/skills/tooling/python.md

@@ -5,7 +5,7 @@ description: Run Python through exec_command in the SDK sandbox. Use the image-b
 
 # Python In The Sandbox
 
-Use `exec_command` for Python. There is no separate Strix Python executor.
+Use `exec_command` for Python. There is no separate Python executor.
 
 Prefer writing reusable scripts to a `.py` file and running them with
 `python3 <name>.py`. For short one-off transformations, `python3 -c` or a

strix/skills/vulnerabilities/prototype_pollution.md

@@ -80,7 +80,7 @@ Gadget availability depends on package versions — enumerate `node_modules` in
 1. **Identify merge points** — Search for extend/merge/defaults/deep copy on user-controlled objects
 2. **Baseline probe** — Inject benign pollution marker:
    ```json
-   {"__proto__": {"strixPolluted": "yes"}}
+   {"__proto__": {"pollutionCanary": "yes"}}
    ```
    Verify via response behavior, error messages, or follow-up request reading shared state
 3. **Shape variants** — Test `__proto__`, `constructor.prototype`, nested bracket notation
@@ -121,7 +121,7 @@ Gadget availability depends on package versions — enumerate `node_modules` in
 
 ## Pro Tips
 
-1. Always verify pollution with a unique canary key (`strixPolluted_<random>`) before attempting RCE gadgets
+1. Always verify pollution with a unique canary key (`pollutionCanary_<random>`) before attempting RCE gadgets
 2. In white-box scans, grep for `merge`, `extend`, `defaultsDeep`, `assign` with user input
 3. Check both request parsing and response template config merges (second-order)
 4. Node gadget chains are version-specific — confirm package version before claiming RCE

strix/tools/agents_graph/tools.py

@@ -14,6 +14,7 @@ from agents import RunContextWrapper, function_tool
 
 from strix.core.agents import Status, coordinator_from_context
 from strix.core.execution import notify_parent_on_terminal
+from strix.core.hooks import LLM_TURN_KEY
 from strix.skills import validate_requested_skills
 
 
@@ -224,6 +225,7 @@ _WAIT_DEFAULT_TIMEOUT_S = 300
 # ``timeout_seconds`` the model asks for. One second of headroom lets the
 # tool's own timeout fire first and return a clean result.
 _WAIT_HARD_CEILING_S = _WAIT_DEFAULT_TIMEOUT_S + 1
+_WAITED_TURN_KEY = "waited_llm_turn"
 
 
 @function_tool(timeout=_WAIT_HARD_CEILING_S)
@@ -239,6 +241,11 @@ async def wait_for_agents(  # noqa: PLR0911
     completion reports. You resume the instant any message arrives, so
     size ``timeout_seconds`` to the work you're awaiting.
 
+    **Issue exactly one wait, then stop and react to what it returns.**
+    This call blocks and resumes on its own; it is not a poll you repeat.
+    Do not write out a wait/check loop ahead of time — a second wait in
+    the same turn returns immediately without waiting.
+
     **This tool is only for waiting on other agents.** Two things it is
     NOT for:
 
@@ -290,6 +297,24 @@ async def wait_for_agents(  # noqa: PLR0911
             default=str,
         )
 
+    turn = inner.get(LLM_TURN_KEY)
+    if turn is not None and inner.get(_WAITED_TURN_KEY) == turn:
+        return json.dumps(
+            {
+                "success": True,
+                "wait_outcome": "already_waited",
+                "reason": reason,
+                "note": (
+                    "You already waited in this turn. A single wait_for_agents blocks and "
+                    "resumes on its own, so queueing more waits only strands you — issue one "
+                    "wait, then react to what it returns."
+                ),
+            },
+            ensure_ascii=False,
+            default=str,
+        )
+    inner[_WAITED_TURN_KEY] = turn
+
     async with coordinator._lock:
         stopped = coordinator.statuses.get(me) == "stopped"
     if stopped:

strix/tools/output_store.py

@@ -1,7 +1,7 @@
 """Bound oversized tool results before they enter agent history.
 
 Oversized results are spilled into the sandbox at
-``/workspace/.strix/tool-output/<id>.txt``; the agent sees a head + tail slice
+``/workspace/.tool-output/<id>.txt``; the agent sees a head + tail slice
 plus the path and reads the rest back with its own file tools. The spill writer
 is injected by the runner via :func:`configure_spill_writer`.
 """
@@ -25,7 +25,7 @@ _WORKSPACE_SPILL_NOTICE = (
     "in the sandbox; read it with exec_command (e.g. `sed -n`, `grep`, `cat`) ...]"
 )
 
-WORKSPACE_SPILL_DIR = "/workspace/.strix/tool-output"
+WORKSPACE_SPILL_DIR = "/workspace/.tool-output"
 
 # Longest possible workspace path, used only to reserve notice bytes.
 _SAMPLE_WORKSPACE_PATH = f"{WORKSPACE_SPILL_DIR}/{'0' * 32}.txt"

strix/tools/proxy/caido_api.py

@@ -189,7 +189,11 @@ def build_raw_request(
 
     final_headers = {**headers}
     final_headers.setdefault("Host", parsed.netloc)
-    final_headers.setdefault("User-Agent", "strix")
+    final_headers.setdefault(
+        "User-Agent",
+        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 "
+        "(KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36",
+    )
     # Framing headers inherited from the captured request describe the ORIGINAL
     # body; once the body is modified for replay they are stale. We always send a
     # plain (non-chunked) body with an explicit Content-Length, so drop any

strix/tools/reporting/tool.py

@@ -719,12 +719,47 @@ def _dependency_severity(advisory_cvss: float | None) -> tuple[float, str]:
     return score, "none"
 
 
+_VALID_REACHABILITY = frozenset(
+    {
+        "not_imported",
+        "imported",
+        "vulnerable_symbol_used",
+        "reachable_call_path",
+        "unknown",
+    }
+)
+
+
+def _validate_manifest_path(manifest_path: str | None) -> str | None:
+    """Return an error message when manifest_path is missing or unsafe."""
+    path = (manifest_path or "").strip()
+    if not path:
+        return (
+            "manifest_path is required: pass the repo-relative path of the "
+            "lockfile/manifest where the vulnerable version was observed "
+            "(trivy's Target, e.g. 'package-lock.json' or "
+            "'services/api/pom.xml'). It binds the finding to its exact file "
+            "so remediation can target the right repository."
+        )
+    if path.startswith("/") or "\\" in path or path.split("/")[0].endswith(":"):
+        return f"manifest_path must be a relative path within the repository, got {path!r}"
+    segments = path.split("/")
+    if any(segment in ("", ".", "..") for segment in segments):
+        return f"manifest_path must not contain empty, '.', or '..' segments, got {path!r}"
+    return None
+
+
 def _build_dependency_metadata(
     *,
     package_name: str,
     installed_version: str,
     package_ecosystem: str | None,
     fixed_version: str | None,
+    introduced_by: str | None,
+    dependency_path: str | None,
+    manifest_path: str | None = None,
+    reachability: str | None = None,
+    reachability_evidence: str | None = None,
 ) -> dict[str, str]:
     metadata = {
         "package_name": package_name.strip(),
@@ -732,17 +767,43 @@ def _build_dependency_metadata(
     }
     if package_ecosystem and package_ecosystem.strip():
         metadata["package_ecosystem"] = package_ecosystem.strip()
+    if manifest_path and manifest_path.strip():
+        metadata["manifest_path"] = manifest_path.strip()
     if fixed_version and fixed_version.strip():
         metadata["fixed_version"] = fixed_version.strip()
+    if introduced_by and introduced_by.strip():
+        metadata["introduced_by"] = introduced_by.strip()
+    if dependency_path and dependency_path.strip():
+        metadata["dependency_path"] = dependency_path.strip()
+    # "unknown" is the absent case — omitting it keeps the jsonb contract clean,
+    # and evidence without a level would have nothing to qualify.
+    if reachability and reachability.strip() and reachability.strip() != "unknown":
+        metadata["reachability"] = reachability.strip()
+        if reachability_evidence and reachability_evidence.strip():
+            metadata["reachability_evidence"] = reachability_evidence.strip()
     return metadata
 
 
+_REACHABILITY_EVIDENCE_LABELS = {
+    "not_imported": "not imported by application code",
+    "imported": "imported by application code; affected API usage unconfirmed",
+    "vulnerable_symbol_used": "the advisory's affected API is used in application code",
+    "reachable_call_path": (
+        "a call path from application code to the vulnerable function was proven"
+    ),
+}
+
+
 def _build_dependency_evidence(
     *,
     cve: str,
     package_name: str,
     installed_version: str,
     fixed_version: str | None,
+    introduced_by: str | None,
+    dependency_path: str | None,
+    reachability: str | None = None,
+    reachability_evidence: str | None = None,
 ) -> str:
     evidence = (
         f"**Advisory evidence:** `{cve}` applies to `{package_name}` "
@@ -750,6 +811,22 @@ def _build_dependency_evidence(
     )
     if fixed_version and fixed_version.strip():
         evidence += f" The advisory is fixed in `{fixed_version.strip()}`."
+    if introduced_by and introduced_by.strip():
+        evidence += (
+            f"\n\n**Transitive dependency:** introduced by the direct "
+            f"dependency `{introduced_by.strip()}`."
+        )
+    if dependency_path and dependency_path.strip():
+        evidence += f"\n\n**Dependency chain:** `{dependency_path.strip()}`"
+    label = _REACHABILITY_EVIDENCE_LABELS.get((reachability or "").strip().lower())
+    if label:
+        evidence += f"\n\n**Usage analysis:** {label}."
+        if reachability_evidence and reachability_evidence.strip():
+            evidence += f" {reachability_evidence.strip()}"
+        evidence += (
+            " This is a prioritization signal from static analysis, not a"
+            " proof of exploitability or of safety."
+        )
     return evidence
 
 
@@ -770,6 +847,11 @@ async def _do_create_dependency(  # noqa: PLR0912
     advisory_cvss: float | None,
     technical_analysis: str | None,
     fix_effort: str,
+    introduced_by: str | None = None,
+    dependency_path: str | None = None,
+    manifest_path: str | None = None,
+    reachability: str = "unknown",
+    reachability_evidence: str | None = None,
     agent_id: str | None = None,
     agent_name: str | None = None,
 ) -> dict[str, Any]:
@@ -806,6 +888,22 @@ async def _do_create_dependency(  # noqa: PLR0912
             f"Invalid fix_effort: {fix_effort!r}. Must be one of: {sorted(_VALID_FIX_EFFORT)}"
         )
 
+    manifest_err = _validate_manifest_path(manifest_path)
+    if manifest_err:
+        errors.append(manifest_err)
+
+    reachability = (reachability or "unknown").strip().lower()
+    if reachability not in _VALID_REACHABILITY:
+        errors.append(
+            f"Invalid reachability: {reachability!r}. Must be one of: {sorted(_VALID_REACHABILITY)}"
+        )
+    elif reachability != "unknown" and not (reachability_evidence or "").strip():
+        errors.append(
+            "reachability_evidence is required when reachability is not 'unknown': "
+            "cite the concrete proof (import file:line, matched symbol usage, or "
+            "govulncheck call path). Never claim a reachability level without evidence."
+        )
+
     if advisory_cvss is None:
         errors.append(
             "advisory_cvss is required: read the published advisory base score "
@@ -824,12 +922,21 @@ async def _do_create_dependency(  # noqa: PLR0912
         installed_version=installed_version,
         package_ecosystem=package_ecosystem,
         fixed_version=fixed_version,
+        introduced_by=introduced_by,
+        dependency_path=dependency_path,
+        manifest_path=manifest_path,
+        reachability=reachability,
+        reachability_evidence=reachability_evidence,
     )
     evidence = _build_dependency_evidence(
         cve=parsed_cve,
         package_name=package_name.strip(),
         installed_version=installed_version.strip(),
         fixed_version=fixed_version,
+        introduced_by=introduced_by,
+        dependency_path=dependency_path,
+        reachability=reachability,
+        reachability_evidence=reachability_evidence,
     )
 
     try:
@@ -922,10 +1029,15 @@ async def create_dependency_report(
     remediation_steps: str,
     assumptions: str,
     package_ecosystem: str,
+    manifest_path: str | None = None,
     fixed_version: str | None = None,
     cwe: str | None = None,
     technical_analysis: str | None = None,
     fix_effort: str = "low",
+    introduced_by: str | None = None,
+    dependency_path: str | None = None,
+    reachability: str = "unknown",
+    reachability_evidence: str | None = None,
 ) -> str:
     """File a known-CVE dependency (SCA) finding — one report per CVE x package.
 
@@ -950,9 +1062,26 @@ async def create_dependency_report(
     - Re-reporting the same CVE/package already filed.
 
     **Reachability**: do NOT silently downgrade or suppress a finding
-    because the vulnerable code path may be unreachable — instead state
-    reachability as an ``assumptions`` / confidence factor. Report the
-    finding; let the reader weigh exploitability.
+    because the vulnerable code path may be unreachable — report it, and
+    record what the usage analysis showed via the structured
+    ``reachability`` + ``reachability_evidence`` fields (see the
+    dependency-cve-scanning skill for the analysis procedure). The level
+    is an evidence ladder, never an exploitability verdict:
+
+    - ``not_imported`` — the package is never imported/required by
+      application code (strongest de-prioritization signal; still not
+      proof of safety — dynamic loading, reflection, or framework wiring
+      can evade static search).
+    - ``imported`` — application code imports the package, but usage of
+      the advisory's affected API was not confirmed.
+    - ``vulnerable_symbol_used`` — the advisory's affected
+      function/class/API appears in application code.
+    - ``reachable_call_path`` — a call-graph tool (e.g. ``govulncheck``)
+      proved a path from application code to the vulnerable function.
+    - ``unknown`` — usage analysis was not performed or was inconclusive.
+
+    Severity is still derived solely from ``advisory_cvss`` — the
+    reachability level never changes the rating, only prioritization.
 
     **Formatting**: use markdown in text fields (``**bold**``, ``inline
     code`` for package/version identifiers, fenced code blocks for
@@ -978,6 +1107,30 @@ async def create_dependency_report(
         technical_analysis: Optional deeper mechanism/root-cause detail.
         fix_effort: One of ``trivial`` / ``low`` / ``medium`` / ``high``
             (dependency upgrades are usually ``trivial``/``low``).
+        introduced_by: For a **transitive** dependency, the direct
+            dependency (from the project's own manifest) that pulls the
+            vulnerable package in, as ``name@version`` (e.g.
+            ``express@4.18.1``). Omit when the vulnerable package is
+            itself a direct dependency.
+        dependency_path: The resolution chain from the direct dependency
+            to the vulnerable package, joined with `` > `` (e.g.
+            ``express@4.18.1 > body-parser@1.20.0 > qs@6.10.2``). Omit
+            for direct dependencies.
+        manifest_path: **Required.** The repo-relative path of the
+            lockfile/manifest where the vulnerable version was observed —
+            trivy's ``Target`` (e.g. ``package-lock.json``,
+            ``services/api/pom.xml``). Strip any scan-workspace or repo
+            checkout directory prefix so the path is relative to the
+            repository root. This binds the finding to its exact file so
+            remediation can target the right repository.
+        reachability: Usage-evidence level from static analysis — one of
+            ``not_imported`` / ``imported`` / ``vulnerable_symbol_used`` /
+            ``reachable_call_path`` / ``unknown``. Claim only what the
+            evidence proves; when in doubt use ``unknown``.
+        reachability_evidence: The concrete proof for the claimed level
+            (required for any level other than ``unknown``): repo-relative
+            ``file:line`` of the import or symbol usage, the matched
+            advisory symbols, or the govulncheck call-path excerpt.
     """
     agent_id, agent_name = _caller_identity(ctx)
 
@@ -997,6 +1150,11 @@ async def create_dependency_report(
         advisory_cvss=advisory_cvss,
         technical_analysis=technical_analysis,
         fix_effort=fix_effort,
+        introduced_by=introduced_by,
+        dependency_path=dependency_path,
+        manifest_path=manifest_path,
+        reachability=reachability,
+        reachability_evidence=reachability_evidence,
         agent_id=agent_id,
         agent_name=agent_name,
     )

strix/tools/respond/tool.py

@@ -15,7 +15,7 @@ def _ctx(ctx: RunContextWrapper) -> dict[str, Any]:
 
 
 @function_tool
-async def respond_to_user(ctx: RunContextWrapper, message: str) -> str:
+async def respond_to_user(ctx: RunContextWrapper, message: str = "") -> str:
     """Answer the user and hand control back to them.
 
     This is the ONLY way to yield to the user. Delivering the message and
@@ -45,6 +45,10 @@ async def respond_to_user(ctx: RunContextWrapper, message: str) -> str:
             have followed the tool calls that led here. Lead with the
             answer or the decision you need, and if you are blocked, say
             exactly what you need from them.
+
+            Omit it when you have just said your piece as plain text and
+            only need to wait: that text has already reached them, and
+            repeating it makes them read the same answer twice.
     """
     inner = _ctx(ctx)
     coordinator = coordinator_from_context(inner)

strix/tools/todo/tools.py

@@ -110,12 +110,19 @@ def _get_agent_todos(agent_id: str) -> dict[str, dict[str, Any]]:
 
 
 def _normalize_priority(priority: str | None, default: str = "normal") -> str:
-    candidate = (priority or default or "normal").lower()
+    candidate = str(priority or default or "normal").strip().lower()
     if candidate not in VALID_PRIORITIES:
         raise ValueError(f"Invalid priority. Must be one of: {', '.join(VALID_PRIORITIES)}")
     return candidate
 
 
+def _coerce_priority(priority: str | None, default: str = "normal") -> str:
+    try:
+        return _normalize_priority(priority, default)
+    except ValueError:
+        return default
+
+
 def _sorted_todos(agent_id: str) -> list[dict[str, Any]]:
     todos_list = [
         {**todo, "todo_id": todo_id} for todo_id, todo in _get_agent_todos(agent_id).items()
@@ -285,11 +292,16 @@ async def create_todo(ctx: RunContextWrapper, todos: str) -> str:
             - ``description`` (str, optional): extra context or
               acceptance criteria.
             - ``priority`` (str, optional): one of ``"low"`` /
-              ``"normal"`` / ``"high"`` / ``"critical"``. Defaults to
-              ``"normal"``.
+              ``"normal"`` / ``"high"`` / ``"critical"``. Anything else,
+              including omitting it, falls back to ``"normal"`` rather
+              than failing.
 
             Example: ``[{"title": "Probe /admin", "priority": "high"},
             {"title": "Check JWT alg=none"}]``.
+
+        A title already on the list, or repeated within this call, is
+        skipped rather than duplicated; skipped titles come back under
+        ``skipped``.
     """
     agent_id = _agent_id_from(ctx)
     try:
@@ -302,13 +314,21 @@ async def create_todo(ctx: RunContextWrapper, todos: str) -> str:
             )
 
         agent_todos = _get_agent_todos(agent_id)
+        seen = {todo["title"].strip().lower() for todo in agent_todos.values()}
         created: list[dict[str, Any]] = []
+        skipped: list[dict[str, str]] = []
         for task in tasks:
-            task_priority = _normalize_priority(task.get("priority"))
+            title = task["title"]
+            key = title.lower()
+            if key in seen:
+                skipped.append({"title": title, "reason": "duplicate title"})
+                continue
+            seen.add(key)
+            task_priority = _coerce_priority(task.get("priority"))
             todo_id = str(uuid.uuid4())[:6]
             timestamp = datetime.now(UTC).isoformat()
             agent_todos[todo_id] = {
-                "title": task["title"],
+                "title": title,
                 "description": task.get("description"),
                 "priority": task_priority,
                 "status": "pending",
@@ -316,7 +336,7 @@ async def create_todo(ctx: RunContextWrapper, todos: str) -> str:
                 "updated_at": timestamp,
                 "completed_at": None,
             }
-            created.append({"todo_id": todo_id, "title": task["title"], "priority": task_priority})
+            created.append({"todo_id": todo_id, "title": title, "priority": task_priority})
     except (ValueError, TypeError) as e:
         return json.dumps(
             {"success": False, "error": f"Failed to create todo: {e}"},
@@ -330,6 +350,7 @@ async def create_todo(ctx: RunContextWrapper, todos: str) -> str:
             "success": True,
             "created": created,
             "created_count": len(created),
+            "skipped": skipped,
             "todos": _sorted_todos(agent_id),
             "total_count": len(_get_agent_todos(agent_id)),
         },

tests/test_agent_factory_tool_arguments.py

@@ -70,7 +70,6 @@ async def test_encoded_list_is_decoded_for_an_array_parameter(schema: dict[str,
         "auth",
         "Endpoint /admin leaks user data, and session tokens never expire",
         '"auth"',
-        "",
     ],
 )
 async def test_free_form_strings_are_never_split_into_an_array(value: str) -> None:
@@ -79,6 +78,29 @@ async def test_free_form_strings_are_never_split_into_an_array(value: str) -> No
     assert parsed["tags"] == value
 
 
+@pytest.mark.asyncio
+@pytest.mark.parametrize("schema", [_ARRAY, _NULLABLE_ARRAY])
+@pytest.mark.parametrize("value", ["", "   "])
+async def test_empty_string_becomes_an_empty_array(schema: dict[str, Any], value: str) -> None:
+    parsed = await _roundtrip(schema, {"tags": value})
+
+    assert parsed["tags"] == []
+
+
+@pytest.mark.asyncio
+async def test_empty_string_becomes_an_empty_object() -> None:
+    parsed = await _roundtrip(_OBJECT, {"modifications": ""})
+
+    assert parsed["modifications"] == {}
+
+
+@pytest.mark.asyncio
+async def test_empty_string_for_a_string_parameter_is_untouched() -> None:
+    parsed = await _roundtrip(_STRING, {"todos": ""})
+
+    assert parsed["todos"] == ""
+
+
 @pytest.mark.asyncio
 async def test_encoded_mapping_is_decoded_for_an_object_parameter() -> None:
     parsed = await _roundtrip(_OBJECT, {"modifications": '{"method": "POST"}'})

tests/test_disable_streaming.py

@@ -31,7 +31,7 @@ from openai.types.responses import (
 
 from strix.config import codex, loader
 from strix.config.loader import load_settings
-from strix.config.models import StrixProvider, _NonStreamingModel
+from strix.config.models import StrixProvider, _NonStreamingModel, _TurnGuardModel
 
 
 if TYPE_CHECKING:
@@ -299,10 +299,11 @@ def test_get_model_wraps_when_disabled(
     load_settings()
 
     model = StrixProvider().get_model("openai/gpt-4o-mini")
-    assert isinstance(model, _NonStreamingModel)
+    assert isinstance(model, _TurnGuardModel)
+    assert isinstance(model._inner, _NonStreamingModel)
 
 
-def test_get_model_unwrapped_by_default(
+def test_get_model_keeps_streaming_by_default(
     monkeypatch: pytest.MonkeyPatch, _reset_settings: None
 ) -> None:
     inner = _DummyModel()
@@ -310,17 +311,20 @@ def test_get_model_unwrapped_by_default(
     load_settings()
 
     model = StrixProvider().get_model("openai/gpt-4o-mini")
-    assert model is inner
+    assert isinstance(model, _TurnGuardModel)
+    assert model._inner is inner
 
 
-def test_get_model_does_not_wrap_subscription_model(
+def test_get_model_guards_subscription_model_but_keeps_it_streaming(
     monkeypatch: pytest.MonkeyPatch, _reset_settings: None
 ) -> None:
-    # Subscription (ChatGPT) models are always streamed and must not be wrapped.
+    # Subscription (ChatGPT) models are always streamed, so LLM_DISABLE_STREAMING
+    # must not apply — but a runaway response needs capping there too.
     monkeypatch.setattr(codex, "subscription_model", lambda *_: "gpt-5.5")
     monkeypatch.setattr(codex, "get_subscription_client", lambda: AsyncOpenAI(api_key="x"))
     monkeypatch.setenv("LLM_DISABLE_STREAMING", "true")
     load_settings()
 
     model = StrixProvider().get_model("gpt-5.5")
-    assert not isinstance(model, _NonStreamingModel)
+    assert isinstance(model, _TurnGuardModel)
+    assert not isinstance(model._inner, _NonStreamingModel)

tests/test_execution.py

@@ -1228,3 +1228,40 @@ async def test_wait_kind_survives_a_snapshot_round_trip() -> None:
     assert restored.wait_kinds["root"] == "user"
     assert restored.idle_resume_counts["root"] == 1
     assert await execution._plain_waiting_timeout(restored, "root") is None
+
+
+@pytest.mark.asyncio
+async def test_interactive_nudge_offers_waiting_without_repeating() -> None:
+    """The nudge is the instruction an agent reads when it is stranded here.
+
+    It is where the option to wait on what was already said has to be, not only
+    in the system prompt: an agent that ended a turn on plain text reasons off
+    this text, and without the clause it restates its answer to reach a tool
+    call, so the user reads it twice.
+
+    The clause holds whatever the turn did, because the agent is the one who
+    knows whether it spoke — this fires for a turn that produced no text at all.
+    """
+    items = await execution._append_tool_required_message(
+        session=None,
+        context={"parent_id": None},
+        attempt=1,
+        limit=3,
+        interactive=True,
+    )
+
+    assert "with no message if you have already said it" in items[0]["content"]
+
+
+@pytest.mark.asyncio
+async def test_autonomous_nudge_does_not_offer_the_user() -> None:
+    """There is nobody attached to an autonomous run to wait for."""
+    items = await execution._append_tool_required_message(
+        session=None,
+        context={"parent_id": None},
+        attempt=1,
+        limit=3,
+        interactive=False,
+    )
+
+    assert "respond_to_user" not in items[0]["content"]

tests/test_inputs.py

@@ -299,6 +299,16 @@ def test_make_model_settings_forces_required_for_anyllm_routed_openai_model() ->
     assert settings.tool_choice == "required"
 
 
+def test_make_model_settings_disables_parallel_tool_calls_by_default() -> None:
+    assert make_model_settings("none", model_name="gpt-4o").parallel_tool_calls is False
+
+
+def test_make_model_settings_omits_parallel_tool_calls_without_tools() -> None:
+    settings = make_model_settings("none", model_name="gpt-4o", has_tools=False)
+
+    assert settings.parallel_tool_calls is None
+
+
 def test_make_model_settings_sets_request_timeout() -> None:
     settings = make_model_settings(
         "none",
@@ -351,3 +361,32 @@ def test_make_model_settings_timeout_survives_reasoning_resolve() -> None:
 
     assert settings.extra_args is not None
     assert settings.extra_args["timeout"] == 120.0
+
+
+def test_openrouter_attribution_rides_on_the_request_headers() -> None:
+    # litellm.headers is ignored once a request carries any header of its own,
+    # so the attribution must be part of the per-request headers.
+    headers = make_model_settings(
+        None, model_name="openrouter/anthropic/claude-sonnet-4-5"
+    ).extra_headers
+    assert headers == {
+        "HTTP-Referer": "https://strix.ai",
+        "X-Title": "Strix",
+        "X-OpenRouter-Categories": "cli-agent",
+    }
+
+
+def test_openrouter_attribution_absent_for_other_providers() -> None:
+    assert make_model_settings(None, model_name="anthropic/claude-sonnet-4-5").extra_headers is None
+
+
+def test_user_headers_override_openrouter_attribution() -> None:
+    headers = make_model_settings(
+        None,
+        model_name="openrouter/anthropic/claude-sonnet-4-5",
+        extra_headers={"X-Title": "Custom", "X-Tenant": "acme"},
+    ).extra_headers
+    assert headers is not None
+    assert headers["X-Title"] == "Custom"
+    assert headers["X-Tenant"] == "acme"
+    assert headers["HTTP-Referer"] == "https://strix.ai"

tests/test_reporting_fields.py

@@ -141,6 +141,7 @@ async def test_dependency_report_sets_class_and_metadata(report_state: ReportSta
         remediation_steps="Upgrade to 4.17.21.",
         assumptions="Assumes the template sink is reachable.",
         package_ecosystem="npm",
+        manifest_path="package-lock.json",
         fixed_version="4.17.21",
         cwe="CWE-94",
         advisory_cvss=7.2,
@@ -160,10 +161,76 @@ async def test_dependency_report_sets_class_and_metadata(report_state: ReportSta
         "package_name": "lodash",
         "installed_version": "4.17.20",
         "package_ecosystem": "npm",
+        "manifest_path": "package-lock.json",
         "fixed_version": "4.17.21",
     }
 
 
+async def test_dependency_report_records_transitive_chain(report_state: ReportState) -> None:
+    result = await _do_create_dependency(
+        title="CVE-2022-24999 in qs 6.10.2",
+        description="Prototype pollution in qs parsing.",
+        target="repo/package.json",
+        cve="CVE-2022-24999",
+        package_name="qs",
+        installed_version="6.10.2",
+        impact="Denial of service via crafted query strings.",
+        remediation_steps="Upgrade express to 4.18.2, which resolves qs 6.11.0.",
+        assumptions="qs parses all incoming query strings by default.",
+        package_ecosystem="npm",
+        manifest_path="package-lock.json",
+        fixed_version="6.10.3",
+        cwe="CWE-1321",
+        advisory_cvss=7.5,
+        technical_analysis=None,
+        fix_effort="trivial",
+        introduced_by="express@4.18.1",
+        dependency_path="express@4.18.1 > body-parser@1.20.0 > qs@6.10.2",
+    )
+    assert result["success"] is True
+    report = report_state.vulnerability_reports[0]
+    assert report["dependency_metadata"]["introduced_by"] == "express@4.18.1"
+    assert (
+        report["dependency_metadata"]["dependency_path"]
+        == "express@4.18.1 > body-parser@1.20.0 > qs@6.10.2"
+    )
+    assert (
+        "**Transitive dependency:** introduced by the direct dependency `express@4.18.1`."
+        in report["evidence"]
+    )
+    assert (
+        "**Dependency chain:** `express@4.18.1 > body-parser@1.20.0 > qs@6.10.2`"
+        in report["evidence"]
+    )
+
+
+async def test_dependency_report_omits_blank_chain_fields(report_state: ReportState) -> None:
+    result = await _do_create_dependency(
+        title="CVE-2024-0001 in sample 1.0.0",
+        description="Published advisory affects the pinned version.",
+        target="repo/package.json",
+        cve="CVE-2024-0001",
+        package_name="sample",
+        installed_version="1.0.0",
+        impact="Impact.",
+        remediation_steps="Upgrade.",
+        assumptions="Assumptions.",
+        package_ecosystem="npm",
+        manifest_path="package-lock.json",
+        fixed_version=None,
+        cwe=None,
+        advisory_cvss=5.0,
+        technical_analysis=None,
+        fix_effort="trivial",
+        introduced_by="  ",
+        dependency_path=None,
+    )
+    assert result["success"] is True
+    report = report_state.vulnerability_reports[0]
+    assert "introduced_by" not in report["dependency_metadata"]
+    assert "dependency_path" not in report["dependency_metadata"]
+
+
 async def test_dependency_report_with_zero_cvss_remains_low_severity(
     report_state: ReportState,
 ) -> None:
@@ -178,6 +245,7 @@ async def test_dependency_report_with_zero_cvss_remains_low_severity(
         remediation_steps="Upgrade to 1.0.1.",
         assumptions="Assumes the package is included in deployed builds.",
         package_ecosystem="npm",
+        manifest_path="package-lock.json",
         fixed_version="1.0.1",
         cwe=None,
         advisory_cvss=0.0,
@@ -192,6 +260,124 @@ async def test_dependency_report_with_zero_cvss_remains_low_severity(
     assert report["cvss"] == 0.0
 
 
+async def test_dependency_report_records_reachability(report_state: ReportState) -> None:
+    result = await _do_create_dependency(
+        title="CVE-2021-23337 in lodash 4.17.20",
+        description="Command injection via template.",
+        target="repo/package.json",
+        cve="CVE-2021-23337",
+        package_name="lodash",
+        installed_version="4.17.20",
+        impact="Command injection where template is used.",
+        remediation_steps="Upgrade to 4.17.21.",
+        assumptions="Assumes the template sink is reachable.",
+        package_ecosystem="npm",
+        manifest_path="package-lock.json",
+        fixed_version="4.17.21",
+        cwe=None,
+        advisory_cvss=7.2,
+        technical_analysis=None,
+        fix_effort="low",
+        reachability="vulnerable_symbol_used",
+        reachability_evidence="src/render.ts:14 calls `_.template()`.",
+    )
+
+    assert result["success"] is True
+    report = report_state.vulnerability_reports[0]
+    assert report["dependency_metadata"]["reachability"] == "vulnerable_symbol_used"
+    assert (
+        report["dependency_metadata"]["reachability_evidence"]
+        == "src/render.ts:14 calls `_.template()`."
+    )
+    assert "**Usage analysis:**" in report["evidence"]
+    assert "not a proof of exploitability or of safety" in report["evidence"]
+    # The level must never influence the rating — that stays advisory_cvss only.
+    assert report["severity"] == "high"
+
+
+async def test_dependency_report_rejects_reachability_without_evidence(
+    report_state: ReportState,
+) -> None:
+    result = await _do_create_dependency(
+        title="CVE-2024-0001 in sample 1.0.0",
+        description="Published advisory affects the pinned version.",
+        target="repo/package.json",
+        cve="CVE-2024-0001",
+        package_name="sample",
+        installed_version="1.0.0",
+        impact="Impact.",
+        remediation_steps="Upgrade.",
+        assumptions="Assumptions.",
+        package_ecosystem="npm",
+        manifest_path="package-lock.json",
+        fixed_version="1.0.1",
+        cwe=None,
+        advisory_cvss=5.0,
+        technical_analysis=None,
+        fix_effort="low",
+        reachability="not_imported",
+    )
+
+    assert result["success"] is False
+    assert any("reachability_evidence is required" in e for e in result["errors"])
+    assert not report_state.vulnerability_reports
+
+
+async def test_dependency_report_rejects_unknown_reachability_level(
+    report_state: ReportState,
+) -> None:
+    result = await _do_create_dependency(
+        title="CVE-2024-0001 in sample 1.0.0",
+        description="Published advisory affects the pinned version.",
+        target="repo/package.json",
+        cve="CVE-2024-0001",
+        package_name="sample",
+        installed_version="1.0.0",
+        impact="Impact.",
+        remediation_steps="Upgrade.",
+        assumptions="Assumptions.",
+        package_ecosystem="npm",
+        manifest_path="package-lock.json",
+        fixed_version="1.0.1",
+        cwe=None,
+        advisory_cvss=5.0,
+        technical_analysis=None,
+        fix_effort="low",
+        reachability="not_exploitable",
+        reachability_evidence="vibes",
+    )
+
+    assert result["success"] is False
+    assert any("Invalid reachability" in e for e in result["errors"])
+    assert not report_state.vulnerability_reports
+
+
+async def test_dependency_report_omits_unknown_reachability(report_state: ReportState) -> None:
+    result = await _do_create_dependency(
+        title="CVE-2024-0001 in sample 1.0.0",
+        description="Published advisory affects the pinned version.",
+        target="repo/package.json",
+        cve="CVE-2024-0001",
+        package_name="sample",
+        installed_version="1.0.0",
+        impact="Impact.",
+        remediation_steps="Upgrade.",
+        assumptions="Analysis was inconclusive.",
+        package_ecosystem="npm",
+        manifest_path="package-lock.json",
+        fixed_version="1.0.1",
+        cwe=None,
+        advisory_cvss=5.0,
+        technical_analysis=None,
+        fix_effort="low",
+    )
+
+    assert result["success"] is True
+    metadata = report_state.vulnerability_reports[0]["dependency_metadata"]
+    assert "reachability" not in metadata
+    assert "reachability_evidence" not in metadata
+
+
 async def test_dependency_report_requires_advisory_cvss(report_state: ReportState) -> None:
     result = await _do_create_dependency(
         title="CVE-2024-0001 in sample 1.0.0",
@@ -204,6 +390,7 @@ async def test_dependency_report_requires_advisory_cvss(report_state: ReportStat
         remediation_steps="Upgrade to 1.0.1.",
         assumptions="Assumes the package ships in deployed builds.",
         package_ecosystem="npm",
+        manifest_path="package-lock.json",
         fixed_version="1.0.1",
         cwe=None,
         advisory_cvss=None,
@@ -259,6 +446,7 @@ async def test_dependency_report_dedupe_candidate_includes_dependency_metadata(
         remediation_steps="Upgrade to 1.0.1.",
         assumptions="Assumes the package is included in deployed builds.",
         package_ecosystem="npm",
+        manifest_path="package-lock.json",
         fixed_version="1.0.1",
         cwe=None,
         advisory_cvss=0.0,
@@ -276,6 +464,7 @@ async def test_dependency_report_dedupe_candidate_includes_dependency_metadata(
             "package_name": "sample",
             "installed_version": "1.0.0",
             "package_ecosystem": "npm",
+            "manifest_path": "package-lock.json",
             "fixed_version": "1.0.1",
         },
         "technical_analysis": None,
@@ -294,6 +483,7 @@ async def test_dependency_report_rejects_bad_cve(report_state: ReportState) -> N
         remediation_steps="r",
         assumptions="a",
         package_ecosystem="npm",
+        manifest_path="package-lock.json",
         fixed_version=None,
         cwe=None,
         advisory_cvss=None,
@@ -316,6 +506,7 @@ async def test_dependency_report_requires_ecosystem(report_state: ReportState) -
         remediation_steps="Upgrade to 1.0.1.",
         assumptions="Assumes the package is included in deployed builds.",
         package_ecosystem="",
+        manifest_path="package-lock.json",
         fixed_version="1.0.1",
         cwe=None,
         advisory_cvss=0.0,
@@ -328,6 +519,62 @@ async def test_dependency_report_requires_ecosystem(report_state: ReportState) -
     assert not report_state.vulnerability_reports
 
 
+async def test_dependency_report_requires_manifest_path(report_state: ReportState) -> None:
+    result = await _do_create_dependency(
+        title="CVE-2024-0001 in sample 1.0.0",
+        description="Published advisory affects the pinned version.",
+        target="repo/package.json",
+        cve="CVE-2024-0001",
+        package_name="sample",
+        installed_version="1.0.0",
+        impact="Low-impact dependency advisory.",
+        remediation_steps="Upgrade to 1.0.1.",
+        assumptions="Assumes the package is included in deployed builds.",
+        package_ecosystem="npm",
+        manifest_path=None,
+        fixed_version="1.0.1",
+        cwe=None,
+        advisory_cvss=5.0,
+        technical_analysis=None,
+        fix_effort="low",
+    )
+
+    assert result["success"] is False
+    assert any("manifest_path is required" in error for error in result["errors"])
+    assert not report_state.vulnerability_reports
+
+
+@pytest.mark.parametrize(
+    "bad_path",
+    ["/etc/passwd", "..\\pom.xml", "services/../pom.xml", "./package.json", "C:/repo/pom.xml"],
+)
+async def test_dependency_report_rejects_unsafe_manifest_path(
+    report_state: ReportState, bad_path: str
+) -> None:
+    result = await _do_create_dependency(
+        title="CVE-2024-0001 in sample 1.0.0",
+        description="Published advisory affects the pinned version.",
+        target="repo/package.json",
+        cve="CVE-2024-0001",
+        package_name="sample",
+        installed_version="1.0.0",
+        impact="Low-impact dependency advisory.",
+        remediation_steps="Upgrade to 1.0.1.",
+        assumptions="Assumes the package is included in deployed builds.",
+        package_ecosystem="npm",
+        manifest_path=bad_path,
+        fixed_version="1.0.1",
+        cwe=None,
+        advisory_cvss=5.0,
+        technical_analysis=None,
+        fix_effort="low",
+    )
+
+    assert result["success"] is False
+    assert any("manifest_path" in error for error in result["errors"])
+    assert not report_state.vulnerability_reports
+
+
 def test_dedupe_comparison_preserves_cve_identity() -> None:
     cleaned = _prepare_report_for_comparison(
         {
@@ -406,6 +653,72 @@ async def test_dependency_dedupe_rejects_same_cve_package_identity() -> None:
     assert result["confidence"] == 1.0
 
 
+async def test_dependency_dedupe_keeps_findings_from_distinct_manifests() -> None:
+    existing = [
+        {
+            "id": "vuln-0001",
+            "title": "CVE-2024-0001 in sample",
+            "cve": "CVE-2024-0001",
+            "dependency_metadata": {
+                "package_name": "sample",
+                "installed_version": "1.0.0",
+                "package_ecosystem": "npm",
+                "manifest_path": "services/api/package-lock.json",
+            },
+        }
+    ]
+    candidate = {
+        "title": "CVE-2024-0001 in sample (web)",
+        "description": "Same advisory observed in a second workspace.",
+        "target": "repo/package.json",
+        "cve": "CVE-2024-0001",
+        "dependency_metadata": {
+            "package_name": "sample",
+            "installed_version": "1.0.0",
+            "package_ecosystem": "npm",
+            "manifest_path": "services/web/package-lock.json",
+        },
+    }
+
+    result = await check_duplicate(candidate, existing)
+
+    assert result["is_duplicate"] is False
+    assert result["confidence"] == 1.0
+
+
+async def test_dependency_dedupe_rejects_same_manifest_identity() -> None:
+    existing = [
+        {
+            "id": "vuln-0001",
+            "title": "CVE-2024-0001 in sample",
+            "cve": "CVE-2024-0001",
+            "dependency_metadata": {
+                "package_name": "sample",
+                "installed_version": "1.0.0",
+                "package_ecosystem": "npm",
+                "manifest_path": "services/api/package-lock.json",
+            },
+        }
+    ]
+    candidate = {
+        "title": "CVE-2024-0001 in sample re-reported",
+        "description": "Same advisory, same manifest.",
+        "target": "repo/package.json",
+        "cve": "CVE-2024-0001",
+        "dependency_metadata": {
+            "package_name": "sample",
+            "installed_version": "1.0.0",
+            "package_ecosystem": "npm",
+            "manifest_path": "services/api/package-lock.json",
+        },
+    }
+
+    result = await check_duplicate(candidate, existing)
+
+    assert result["is_duplicate"] is True
+    assert result["duplicate_id"] == "vuln-0001"
+
+
 async def test_dependency_dedupe_detects_legacy_same_cve_package() -> None:
     existing = [
         {
@@ -559,6 +872,8 @@ def test_vuln_tool_exposes_new_params() -> None:
     dep_props = create_dependency_report.params_json_schema["properties"]
     for field in ("package_name", "installed_version", "cve", "advisory_cvss"):
         assert field in dep_props
+    for field in ("reachability", "reachability_evidence", "manifest_path"):
+        assert field in dep_props
     dep_required = create_dependency_report.params_json_schema["required"]
     assert "package_ecosystem" in dep_required
     assert "advisory_cvss" in dep_required

tests/test_respond_to_user.py

@@ -64,3 +64,31 @@ async def test_a_message_that_already_arrived_is_taken_instead_of_parking() -> N
     assert result["wait_outcome"] == "message_arrived"
     assert result["pending_messages"] == 1
     assert coordinator.statuses["root"] == "running"
+
+
+async def _call_without_message(context: dict[str, Any]) -> dict[str, Any]:
+    ctx = ToolContext(
+        context=context,
+        tool_name="respond_to_user",
+        tool_call_id="call-1",
+        tool_arguments="{}",
+    )
+    raw = await respond_to_user.on_invoke_tool(ctx, "{}")
+    return json.loads(raw)  # type: ignore[no-any-return]
+
+
+@pytest.mark.asyncio
+async def test_parks_without_a_message() -> None:
+    """An agent that has already said its piece as plain text can just wait.
+
+    The nudge is what leaves it here, and while a message was required the only
+    way to stop was to send the same answer a second time.
+    """
+    context = await _context(interactive=True)
+
+    result = await _call_without_message(context)
+
+    assert result["success"] is True
+    assert result["wait_outcome"] == "waiting"
+    assert result["message"] == ""
+    assert context["coordinator"].statuses["root"] == "waiting"

tests/test_runner_interrupt.py

@@ -0,0 +1,108 @@
+from __future__ import annotations
+
+import asyncio
+import types
+from typing import Any
+
+import pytest
+from agents import ModelSettings
+
+import strix.tools.notes.tools as notes_tools
+import strix.tools.todo.tools as todo_tools
+from strix.core import runner
+from strix.core.agents import AgentCoordinator
+from strix.runtime import session_manager
+
+
+def _wire_runner(monkeypatch: pytest.MonkeyPatch, tmp_path: Any) -> None:
+    monkeypatch.setattr(runner, "run_dir_for", lambda _scan_id: tmp_path)
+    monkeypatch.setattr(runner, "runtime_state_dir", lambda _run_dir: tmp_path)
+    monkeypatch.setattr(runner, "setup_scan_logging", lambda _run_dir: lambda: None)
+    monkeypatch.setattr(runner, "set_scan_id", lambda _scan_id: None)
+
+    settings = types.SimpleNamespace(
+        llm=types.SimpleNamespace(
+            model="openai/gpt-4o",
+            reasoning_effort="high",
+            force_required_tool_choice=False,
+            timeout=300,
+            prompt_cache=True,
+            extra_headers=None,
+        ),
+        runtime=types.SimpleNamespace(max_context_images=3),
+    )
+    monkeypatch.setattr(runner, "load_settings", lambda: settings)
+    monkeypatch.setattr(runner, "configure_sdk_model_defaults", lambda _settings: None)
+    monkeypatch.setattr(
+        runner, "uses_chat_completions_tool_schema", lambda _model, _settings: False
+    )
+    monkeypatch.setattr(todo_tools, "hydrate_todos_from_disk", lambda _state_dir: None)
+    monkeypatch.setattr(notes_tools, "hydrate_notes_from_disk", lambda _state_dir: None)
+
+    async def _create_or_reuse(*_args: Any, **_kwargs: Any) -> dict[str, Any]:
+        return {"client": object(), "session": object(), "caido_client": None}
+
+    async def _cleanup(*_args: Any, **_kwargs: Any) -> None:
+        return None
+
+    monkeypatch.setattr(session_manager, "create_or_reuse", _create_or_reuse)
+    monkeypatch.setattr(session_manager, "cleanup", _cleanup)
+    monkeypatch.setattr(runner, "build_root_task", lambda _scan_config: "task")
+    monkeypatch.setattr(runner, "build_scope_context", lambda _scan_config: "")
+    monkeypatch.setattr(runner, "make_model_settings", lambda *_a, **_k: ModelSettings())
+    monkeypatch.setattr(runner, "build_strix_agent", lambda **_kwargs: object())
+    monkeypatch.setattr(runner, "make_child_factory", lambda **_kwargs: lambda **_k: object())
+    monkeypatch.setattr(runner, "open_agent_session", lambda _root_id, _db: object())
+
+
+def _root_status(coordinator: AgentCoordinator) -> str:
+    roots = [aid for aid, parent in coordinator.parent_of.items() if parent is None]
+    assert len(roots) == 1
+    return coordinator.statuses[roots[0]]
+
+
+@pytest.mark.parametrize("interrupt", [KeyboardInterrupt, asyncio.CancelledError])
+@pytest.mark.asyncio
+async def test_user_interrupt_leaves_the_root_running_for_resume(
+    monkeypatch: pytest.MonkeyPatch, tmp_path: Any, interrupt: type[BaseException]
+) -> None:
+    _wire_runner(monkeypatch, tmp_path)
+
+    async def _interrupt(*_args: Any, **_kwargs: Any) -> None:
+        raise interrupt()
+
+    monkeypatch.setattr(runner, "run_agent_loop", _interrupt)
+    coordinator = AgentCoordinator()
+
+    with pytest.raises(interrupt):
+        await runner.run_strix_scan(
+            scan_config={"targets": [], "scan_mode": "deep"},
+            scan_id="scan-test",
+            image="img",
+            coordinator=coordinator,
+        )
+
+    assert _root_status(coordinator) == "running"
+
+
+@pytest.mark.asyncio
+async def test_a_real_crash_still_marks_root_failed(
+    monkeypatch: pytest.MonkeyPatch, tmp_path: Any
+) -> None:
+    _wire_runner(monkeypatch, tmp_path)
+
+    async def _boom(*_args: Any, **_kwargs: Any) -> None:
+        raise RuntimeError("boom")
+
+    monkeypatch.setattr(runner, "run_agent_loop", _boom)
+    coordinator = AgentCoordinator()
+
+    with pytest.raises(RuntimeError, match="boom"):
+        await runner.run_strix_scan(
+            scan_config={"targets": [], "scan_mode": "deep"},
+            scan_id="scan-test",
+            image="img",
+            coordinator=coordinator,
+        )
+
+    assert _root_status(coordinator) == "failed"

tests/test_runner_teardown.py

@@ -0,0 +1,93 @@
+from __future__ import annotations
+
+import asyncio
+import types
+from typing import Any
+
+import pytest
+from agents import ModelSettings
+
+import strix.tools.notes.tools as notes_tools
+import strix.tools.todo.tools as todo_tools
+from strix.core import runner
+from strix.core.agents import AgentCoordinator
+from strix.runtime import session_manager
+
+
+def _wire_runner(monkeypatch: pytest.MonkeyPatch, tmp_path: Any) -> None:
+    monkeypatch.setattr(runner, "run_dir_for", lambda _scan_id: tmp_path)
+    monkeypatch.setattr(runner, "runtime_state_dir", lambda _run_dir: tmp_path)
+    monkeypatch.setattr(runner, "setup_scan_logging", lambda _run_dir: lambda: None)
+    monkeypatch.setattr(runner, "set_scan_id", lambda _scan_id: None)
+
+    settings = _settings()
+    monkeypatch.setattr(runner, "load_settings", lambda: settings)
+    monkeypatch.setattr(runner, "configure_sdk_model_defaults", lambda _s: None)
+    monkeypatch.setattr(runner, "uses_chat_completions_tool_schema", lambda _m, _s: False)
+    monkeypatch.setattr(todo_tools, "hydrate_todos_from_disk", lambda _d: None)
+    monkeypatch.setattr(notes_tools, "hydrate_notes_from_disk", lambda _d: None)
+
+    async def _create_or_reuse(*_a: Any, **_k: Any) -> dict[str, Any]:
+        return {"client": object(), "session": object(), "caido_client": None}
+
+    async def _cleanup(*_a: Any, **_k: Any) -> None:
+        return None
+
+    monkeypatch.setattr(session_manager, "create_or_reuse", _create_or_reuse)
+    monkeypatch.setattr(session_manager, "cleanup", _cleanup)
+    monkeypatch.setattr(runner, "build_root_task", lambda _c: "task")
+    monkeypatch.setattr(runner, "build_scope_context", lambda _c: "")
+    monkeypatch.setattr(runner, "make_model_settings", lambda *_a, **_k: ModelSettings())
+    monkeypatch.setattr(runner, "build_strix_agent", lambda **_k: object())
+    monkeypatch.setattr(runner, "make_child_factory", lambda **_k: lambda **_kk: object())
+    monkeypatch.setattr(runner, "open_agent_session", lambda _root_id, _db: object())
+
+
+def _settings() -> Any:
+    return types.SimpleNamespace(
+        llm=types.SimpleNamespace(
+            model="openai/gpt-4o",
+            reasoning_effort="high",
+            force_required_tool_choice=False,
+            timeout=300,
+            prompt_cache=True,
+            extra_headers=None,
+        ),
+        runtime=types.SimpleNamespace(max_context_images=3),
+    )
+
+
+@pytest.mark.asyncio
+async def test_a_live_child_is_settled_before_sessions_close(
+    monkeypatch: pytest.MonkeyPatch, tmp_path: Any
+) -> None:
+    _wire_runner(monkeypatch, tmp_path)
+    coordinator = AgentCoordinator()
+    child_started = asyncio.Event()
+    child_task: dict[str, asyncio.Task[None]] = {}
+
+    async def _root_finishes(**kwargs: Any) -> None:
+        root_id = kwargs["agent_id"]
+
+        async def _child_mid_turn() -> None:
+            child_started.set()
+            await asyncio.sleep(3600)
+
+        await coordinator.register("child", "Child", parent_id=root_id)
+        task = asyncio.create_task(_child_mid_turn())
+        child_task["t"] = task
+        await coordinator.attach_runtime("child", task=task)
+        await child_started.wait()
+
+    monkeypatch.setattr(runner, "run_agent_loop", _root_finishes)
+
+    await runner.run_strix_scan(
+        scan_config={"targets": [], "scan_mode": "deep"},
+        scan_id="scan-test",
+        image="img",
+        coordinator=coordinator,
+    )
+
+    task = child_task["t"]
+    assert task.done(), "the child task was left running past scan teardown"
+    assert task.cancelled(), "the child was not cancelled cleanly on a finish"

tests/test_session_fd.py

@@ -0,0 +1,117 @@
+from __future__ import annotations
+
+import asyncio
+from pathlib import Path
+from typing import Any, cast
+
+import pytest
+
+from strix.core.sessions import open_agent_session
+
+
+def _count_open_fds() -> int | None:
+    for path in (Path("/proc/self/fd"), Path("/dev/fd")):
+        if path.is_dir():
+            return len(list(path.iterdir()))
+    return None
+
+
+@pytest.mark.asyncio
+async def test_sessions_hold_no_descriptors_while_parked(tmp_path: Path) -> None:
+    """Descriptor use must track live operations, not the number of sessions.
+
+    The SDK keeps a connection per (session, pool thread) open for the session's
+    whole life. An agent parks rather than exits, so its session lives for the
+    scan, and fan-out multiplies those handles until the process runs out of file
+    descriptors (#1018). A session that is not mid-operation should hold none.
+    """
+    baseline = _count_open_fds()
+    if baseline is None:
+        pytest.skip("no /proc/self/fd or /dev/fd on this platform")
+
+    sessions = [open_agent_session(f"a{i}", tmp_path / f"s{i}.db") for i in range(60)]
+    try:
+        for _ in range(4):
+            await asyncio.gather(
+                *(s.add_items([{"role": "user", "content": "x"}]) for s in sessions)
+            )
+            await asyncio.gather(*(s.get_items() for s in sessions))
+        parked = _count_open_fds()
+        assert parked is not None
+        # 60 parked sessions, yet descriptors are back at the baseline.
+        assert parked - baseline <= 5, f"parked fds grew by {parked - baseline}"
+    finally:
+        for s in sessions:
+            s.close()
+
+
+@pytest.mark.asyncio
+async def test_in_flight_descriptors_track_concurrency_not_session_count(
+    tmp_path: Path,
+) -> None:
+    baseline = _count_open_fds()
+    if baseline is None:
+        pytest.skip("no /proc/self/fd or /dev/fd on this platform")
+
+    sessions = [open_agent_session(f"a{i}", tmp_path / f"s{i}.db") for i in range(200)]
+    peak = baseline
+    try:
+
+        async def sample() -> None:
+            nonlocal peak
+            for _ in range(500):
+                current = _count_open_fds()
+                if current is not None:
+                    peak = max(peak, current)
+                await asyncio.sleep(0)
+
+        async def load() -> None:
+            for _ in range(4):
+                await asyncio.gather(
+                    *(s.add_items([{"role": "user", "content": "x"}]) for s in sessions)
+                )
+
+        await asyncio.gather(load(), sample())
+        # 200 sessions, but peak is bounded by the thread pool, well under 200.
+        assert peak - baseline < 100, f"in-flight fds peaked at +{peak - baseline}"
+    finally:
+        for s in sessions:
+            s.close()
+
+
+@pytest.mark.asyncio
+async def test_history_survives_the_per_operation_connection(tmp_path: Path) -> None:
+    session = open_agent_session("agent-1", tmp_path / "agents.db")
+    try:
+        for i in range(30):
+            await session.add_items([{"role": "user", "content": f"m{i}"}])
+        items = [cast("dict[str, Any]", i) for i in await session.get_items()]
+        assert [i["content"] for i in items] == [f"m{i}" for i in range(30)]
+    finally:
+        session.close()
+
+
+@pytest.mark.asyncio
+async def test_concurrent_sessions_sharing_one_file_stay_consistent(tmp_path: Path) -> None:
+    db = tmp_path / "shared.db"
+    sessions = [open_agent_session(f"a{i}", db) for i in range(10)]
+    try:
+        await asyncio.gather(
+            *(s.add_items([{"role": "user", "content": s.session_id}]) for s in sessions)
+        )
+        # Each session sees only its own row despite sharing the file.
+        for s in sessions:
+            items = [cast("dict[str, Any]", i) for i in await s.get_items()]
+            assert [i["content"] for i in items] == [s.session_id]
+    finally:
+        for s in sessions:
+            s.close()
+
+
+@pytest.mark.asyncio
+async def test_a_closed_session_refuses_operations(tmp_path: Path) -> None:
+    session = open_agent_session("agent-1", tmp_path / "agents.db")
+    await session.add_items([{"role": "user", "content": "x"}])
+    session.close()
+    with pytest.raises(RuntimeError, match="closed"):
+        await session.add_items([{"role": "user", "content": "y"}])

tests/test_skill_dir_extension.py

@@ -1,8 +1,10 @@
+from collections.abc import Iterator
 from pathlib import Path
 
 import pytest
 
 import strix.skills as skills_mod
+from strix.agents.prompt import render_system_prompt
 from strix.skills import (
     get_all_skill_names,
     get_available_skills,
@@ -12,10 +14,11 @@ from strix.skills import (
     skill_search_dirs,
     validate_requested_skills,
 )
+from strix.utils.resource_paths import get_strix_resource_path
 
 
 @pytest.fixture(autouse=True)
-def _clear_extra_dirs() -> None:
+def _clear_extra_dirs() -> Iterator[None]:
     original = list(skills_mod._EXTRA_SKILL_DIRS)
     skills_mod._EXTRA_SKILL_DIRS.clear()
     try:
@@ -37,9 +40,11 @@ def _write_root_skill(root: Path, name: str, body: str) -> None:
 
 def test_no_registration_leaves_builtin_only() -> None:
     assert registered_skill_dirs() == ()
-    builtin = skills_mod.get_strix_resource_path("skills")
+    builtin = get_strix_resource_path("skills")
     assert skill_search_dirs() == (builtin,)
-    assert {"nmap", "subfinder"}.issubset(get_available_skills()["tooling"])
+    assert {"nmap", "subfinder"}.issubset(
+        {skill["name"] for skill in get_available_skills()["tooling"]}
+    )
 
 
 def test_register_is_idempotent_and_ordered(tmp_path: Path) -> None:
@@ -61,16 +66,125 @@ def test_registered_dir_adds_new_skill(tmp_path: Path) -> None:
     register_skill_dir(tmp_path)
 
     assert "widget" in get_all_skill_names()
-    assert get_available_skills()["extra"] == ["widget"]
+    assert get_available_skills()["extra"] == [{"name": "widget", "description": ""}]
     assert load_skills(["widget"]) == {"widget": "widget body"}
 
 
+def test_available_skill_includes_frontmatter_description(tmp_path: Path) -> None:
+    _write_skill(
+        tmp_path,
+        "extra",
+        "widget",
+        "---\nname: widget\ndescription: Useful widget guidance\n---\nwidget body",
+    )
+    register_skill_dir(tmp_path)
+
+    assert get_available_skills()["extra"] == [
+        {"name": "widget", "description": "Useful widget guidance"}
+    ]
+
+
+def test_available_skill_supports_colon_in_description(tmp_path: Path) -> None:
+    _write_skill(
+        tmp_path,
+        "extra",
+        "widget",
+        '---\nname: widget\ndescription: "Useful widget: handles YAML"\n---\nwidget body',
+    )
+    register_skill_dir(tmp_path)
+
+    assert get_available_skills()["extra"] == [
+        {"name": "widget", "description": "Useful widget: handles YAML"}
+    ]
+
+
+def test_available_skill_normalizes_quoted_description(tmp_path: Path) -> None:
+    _write_skill(
+        tmp_path,
+        "extra",
+        "widget",
+        '---\nname: widget\ndescription: "Useful: widget guidance"\n---\nwidget body',
+    )
+    register_skill_dir(tmp_path)
+
+    assert get_available_skills()["extra"] == [
+        {"name": "widget", "description": "Useful: widget guidance"}
+    ]
+
+
+def test_available_skill_normalizes_multiline_descriptions(tmp_path: Path) -> None:
+    _write_skill(
+        tmp_path,
+        "extra",
+        "block",
+        "---\nname: block\n\ndescription: |\n"
+        "  First paragraph\n\n  Second paragraph\n\n---\nblock body",
+    )
+    _write_skill(
+        tmp_path,
+        "extra",
+        "plain",
+        "---\nname: plain\n\ndescription: First line\n  Second line\n\n---\nplain body",
+    )
+    register_skill_dir(tmp_path)
+
+    available = {skill["name"]: skill["description"] for skill in get_available_skills()["extra"]}
+    assert available == {
+        "block": "First paragraph Second paragraph",
+        "plain": "First line Second line",
+    }
+
+
+def test_available_skill_supports_block_scalar_trailing_comment(tmp_path: Path) -> None:
+    _write_skill(
+        tmp_path,
+        "extra",
+        "commented",
+        "---\nname: commented\ndescription: | # paragraph\n"
+        "  First line\n  Second line\n---\ncommented body",
+    )
+    register_skill_dir(tmp_path)
+
+    assert get_available_skills()["extra"] == [
+        {"name": "commented", "description": "First line Second line"}
+    ]
+
+
+def test_malformed_frontmatter_keeps_skill_body(tmp_path: Path) -> None:
+    _write_skill(
+        tmp_path,
+        "extra",
+        "broken",
+        "---\nname: [broken\ndescription: should be empty\n---\nbroken body",
+    )
+    register_skill_dir(tmp_path)
+
+    assert get_available_skills()["extra"] == [{"name": "broken", "description": ""}]
+    assert load_skills(["extra/broken"]) == {"broken": "broken body"}
+
+
+def test_system_prompt_renders_skill_descriptions() -> None:
+    prompt = render_system_prompt(scan_mode="quick", is_root=True)
+
+    assert "- technologies/firebase: Firebase security testing covering" in prompt
+
+
+def test_system_prompt_omits_empty_skill_description(tmp_path: Path) -> None:
+    _write_skill(tmp_path, "extra", "widget", "---\nname: widget\ndescription:\n---\nwidget body")
+    register_skill_dir(tmp_path)
+
+    prompt = render_system_prompt(scan_mode="quick", is_root=True)
+
+    assert "- extra/widget\n" in prompt
+    assert "- extra/widget: " not in prompt
+
+
 def test_registered_root_skill_is_discoverable_and_valid(tmp_path: Path) -> None:
     _write_root_skill(tmp_path, "widget", "widget body")
     register_skill_dir(tmp_path)
 
     assert "widget" in get_all_skill_names()
-    assert get_available_skills()["root"] == ["widget"]
+    assert get_available_skills()["root"] == [{"name": "widget", "description": ""}]
     assert validate_requested_skills(["widget"]) is None
     assert validate_requested_skills(["root/widget"]) is None
     assert load_skills(["widget"]) == {"widget": "widget body"}
@@ -83,8 +197,8 @@ def test_ambiguous_bare_skill_requires_qualified_name(tmp_path: Path) -> None:
     register_skill_dir(tmp_path)
 
     assert "widget" in get_all_skill_names()
-    assert get_available_skills()["alpha"] == ["widget"]
-    assert get_available_skills()["beta"] == ["widget"]
+    assert get_available_skills()["alpha"] == [{"name": "widget", "description": ""}]
+    assert get_available_skills()["beta"] == [{"name": "widget", "description": ""}]
     assert validate_requested_skills(["alpha/widget"]) is None
     assert validate_requested_skills(["beta/widget"]) is None
 

tests/test_stream_idle_timeout.py

@@ -0,0 +1,173 @@
+"""Tests for the model-stream idle watchdog.
+
+A turn that streams a few tokens and then goes silent is not covered by the
+request timeout: the read timeout resets on every byte, keepalives included.
+The watchdog bounds the gap between events so the turn fails and can be
+retried instead of parking the agent forever.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import threading
+import time
+from http.server import BaseHTTPRequestHandler, HTTPServer
+from typing import TYPE_CHECKING, Any
+
+import pytest
+from agents.model_settings import ModelSettings
+from agents.models.interface import Model, ModelTracing
+from agents.models.openai_chatcompletions import OpenAIChatCompletionsModel
+from openai import AsyncOpenAI
+
+from strix.config import loader
+from strix.config.loader import load_settings
+from strix.config.models import StrixProvider, _TurnGuardModel, _with_idle_timeout
+
+
+if TYPE_CHECKING:
+    from collections.abc import AsyncIterator, Iterator
+
+
+_STALL_SECONDS = 30.0
+
+
+def _chunk(text: str) -> bytes:
+    payload = {
+        "id": "chatcmpl-1",
+        "object": "chat.completion.chunk",
+        "created": 0,
+        "model": "gw-model",
+        "choices": [{"index": 0, "delta": {"content": text}, "finish_reason": None}],
+    }
+    return b"data: " + json.dumps(payload).encode() + b"\n\n"
+
+
+class _StallingHandler(BaseHTTPRequestHandler):
+    """Streams a couple of tokens, then stops producing anything."""
+
+    stop = threading.Event()
+
+    def log_message(self, *args: Any) -> None:
+        pass
+
+    def do_POST(self) -> None:
+        length = int(self.headers.get("Content-Length", 0))
+        self.rfile.read(length)
+        self.send_response(200)
+        self.send_header("Content-Type", "text/event-stream")
+        self.end_headers()
+        self.wfile.write(_chunk("Now"))
+        self.wfile.write(_chunk(" spawning"))
+        self.wfile.flush()
+        self.stop.wait(_STALL_SECONDS)
+
+
+@pytest.fixture
+def stalling_gateway() -> Iterator[str]:
+    _StallingHandler.stop.clear()
+    server = HTTPServer(("127.0.0.1", 0), _StallingHandler)
+    thread = threading.Thread(target=server.serve_forever, daemon=True)
+    thread.start()
+    try:
+        yield f"http://127.0.0.1:{server.server_address[1]}/v1"
+    finally:
+        _StallingHandler.stop.set()
+        server.shutdown()
+        server.server_close()
+
+
+def _stream(base_url: str, *, idle_timeout: float) -> AsyncIterator[Any]:
+    client = AsyncOpenAI(api_key="tok", base_url=base_url, max_retries=0, timeout=_STALL_SECONDS)
+    inner: Model = OpenAIChatCompletionsModel(model="gw-model", openai_client=client)
+    guarded = _TurnGuardModel(inner, stream_idle_timeout=idle_timeout)
+    return guarded.stream_response(
+        None,
+        "go",
+        ModelSettings(),
+        [],
+        None,
+        [],
+        ModelTracing.DISABLED,
+        previous_response_id=None,
+        conversation_id=None,
+        prompt=None,
+    )
+
+
+async def _drain(base_url: str, *, idle_timeout: float) -> list[Any]:
+    return [event async for event in _stream(base_url, idle_timeout=idle_timeout)]
+
+
+@pytest.mark.asyncio
+async def test_stalled_stream_hangs_without_the_watchdog(stalling_gateway: str) -> None:
+    # Repro: tokens arrive, then nothing. Un-watched, the turn just sits there;
+    # the request timeout is far away and would reset on any keepalive byte.
+    with pytest.raises(TimeoutError):
+        await asyncio.wait_for(_drain(stalling_gateway, idle_timeout=0), timeout=2)
+
+
+@pytest.mark.asyncio
+async def test_stalled_stream_is_abandoned_by_the_watchdog(stalling_gateway: str) -> None:
+    started = time.monotonic()
+    with pytest.raises(TimeoutError, match="produced no event"):
+        await _drain(stalling_gateway, idle_timeout=1)
+
+    assert time.monotonic() - started < _STALL_SECONDS
+
+
+@pytest.mark.asyncio
+async def test_events_keep_flowing_while_the_stream_is_alive() -> None:
+    async def _live() -> AsyncIterator[Any]:
+        for i in range(5):
+            await asyncio.sleep(0.05)
+            yield f"event-{i}"
+
+    seen: list[Any] = [event async for event in _with_idle_timeout(_live(), 1.0)]
+
+    assert seen == [f"event-{i}" for i in range(5)]
+
+
+@pytest.fixture
+def _reset_settings(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]:
+    for key in ("STRIX_LLM", "LLM_DISABLE_STREAMING", "LLM_STREAM_IDLE_TIMEOUT"):
+        monkeypatch.delenv(key, raising=False)
+    monkeypatch.setattr(loader, "_cached", None)
+    monkeypatch.setattr(loader, "_override", None)
+    yield
+
+
+class _DummyModel(Model):
+    async def get_response(self, *args: Any, **kwargs: Any) -> Any:
+        raise NotImplementedError
+
+    def stream_response(self, *args: Any, **kwargs: Any) -> Any:
+        raise NotImplementedError
+
+
+def test_idle_timeout_is_configurable(
+    monkeypatch: pytest.MonkeyPatch, _reset_settings: None
+) -> None:
+    monkeypatch.setattr("strix.config.models.MultiProvider.get_model", lambda *_: _DummyModel())
+    monkeypatch.setenv("LLM_STREAM_IDLE_TIMEOUT", "45")
+    load_settings()
+
+    model = StrixProvider().get_model("openai/gpt-4o-mini")
+    assert isinstance(model, _TurnGuardModel)
+    assert model._stream_idle_timeout == 45
+
+
+def test_idle_timeout_is_off_without_streaming(
+    monkeypatch: pytest.MonkeyPatch, _reset_settings: None
+) -> None:
+    # LLM_DISABLE_STREAMING turns the whole request into one event, so an idle
+    # gap would just be the request duration — the request timeout bounds that.
+    monkeypatch.setattr("strix.config.models.MultiProvider.get_model", lambda *_: _DummyModel())
+    monkeypatch.setenv("LLM_STREAM_IDLE_TIMEOUT", "45")
+    monkeypatch.setenv("LLM_DISABLE_STREAMING", "true")
+    load_settings()
+
+    model = StrixProvider().get_model("openai/gpt-4o-mini")
+    assert isinstance(model, _TurnGuardModel)
+    assert model._stream_idle_timeout == 0

tests/test_todo.py

@@ -0,0 +1,105 @@
+from __future__ import annotations
+
+import json
+from typing import Any
+
+import pytest
+from agents.tool_context import ToolContext
+
+from strix.tools.todo import tools
+from strix.tools.todo.tools import _coerce_priority, create_todo
+
+
+@pytest.fixture(autouse=True)
+def _isolate_store() -> Any:
+    tools._todos_storage.clear()
+    yield
+    tools._todos_storage.clear()
+
+
+async def _create(todos: list[Any], agent_id: str = "root") -> dict[str, Any]:
+    ctx = ToolContext(
+        context={"agent_id": agent_id},
+        tool_name="create_todo",
+        tool_call_id="call-1",
+        tool_arguments="{}",
+    )
+    raw = await create_todo.on_invoke_tool(ctx, json.dumps({"todos": json.dumps(todos)}))
+    return json.loads(raw)  # type: ignore[no-any-return]
+
+
+def test_unknown_priority_falls_back_to_normal() -> None:
+    assert _coerce_priority("medium") == "normal"
+    assert _coerce_priority("urgent") == "normal"
+    assert _coerce_priority("high") == "high"
+
+
+@pytest.mark.asyncio
+async def test_one_bad_priority_no_longer_discards_the_batch() -> None:
+    result = await _create(
+        [
+            {"title": "Recon", "priority": "medium"},
+            {"title": "Probe /admin", "priority": "sky-high"},
+            {"title": "Report"},
+        ]
+    )
+
+    assert result["success"] is True
+    assert result["created_count"] == 3
+    by_title = {c["title"]: c["priority"] for c in result["created"]}
+    assert by_title["Recon"] == "normal"
+    assert by_title["Probe /admin"] == "normal"
+    assert by_title["Report"] == "normal"
+
+
+@pytest.mark.asyncio
+async def test_duplicate_titles_within_a_batch_are_skipped() -> None:
+    result = await _create(
+        [
+            {"title": "Subdomain enumeration"},
+            {"title": "Content discovery"},
+            {"title": "Subdomain enumeration"},
+            {"title": "content discovery"},
+        ]
+    )
+
+    assert result["created_count"] == 2
+    assert {c["title"] for c in result["created"]} == {
+        "Subdomain enumeration",
+        "Content discovery",
+    }
+    assert len(result["skipped"]) == 2
+    assert all(s["reason"] == "duplicate title" for s in result["skipped"])
+
+
+@pytest.mark.asyncio
+async def test_a_title_already_on_the_list_is_not_created_again() -> None:
+    await _create([{"title": "Crawl with katana"}])
+    result = await _create([{"title": "crawl with katana"}, {"title": "JS analysis"}])
+
+    assert [c["title"] for c in result["created"]] == ["JS analysis"]
+    assert [s["title"] for s in result["skipped"]] == ["crawl with katana"]
+    assert result["total_count"] == 2
+
+
+def test_coerce_never_raises() -> None:
+    assert _coerce_priority("nonsense") == "normal"
+    assert _coerce_priority(None) == "normal"
+    assert _coerce_priority("high") == "high"
+    for value in (2, ["high"], {"p": 1}, True):
+        assert _coerce_priority(value) == "normal"  # type: ignore[arg-type]
+
+
+@pytest.mark.asyncio
+async def test_non_string_priority_does_not_fail_the_batch() -> None:
+    result = await _create(
+        [
+            {"title": "Recon", "priority": 2},
+            {"title": "Probe", "priority": ["high"]},
+            {"title": "Report"},
+        ]
+    )
+
+    assert result["success"] is True
+    assert result["created_count"] == 3
+    assert {c["priority"] for c in result["created"]} == {"normal"}

tests/test_tool_call_ids.py

@@ -0,0 +1,249 @@
+"""Tests for tool-call id uniqueness.
+
+Providers that number tool calls per turn (``exec_command:0``, ``:1``, ...)
+restart the counter on every turn, so the same id eventually appears twice in
+one conversation. Strict providers then reject the whole request, and because
+the history is replayed on every retry the agent can never recover. A gateway
+that validates id uniqueness the way those providers do proves both the
+failure and the fix.
+"""
+
+from __future__ import annotations
+
+import json
+import threading
+from http.server import BaseHTTPRequestHandler, HTTPServer
+from typing import TYPE_CHECKING, Any
+
+import pytest
+from agents import Agent, Runner, function_tool
+from agents.models.interface import Model, ModelProvider
+from agents.models.openai_chatcompletions import OpenAIChatCompletionsModel
+from agents.run import RunConfig
+from openai import AsyncOpenAI
+from openai.types.responses import ResponseFunctionToolCall
+
+from strix.config.models import _NonStreamingModel, _TurnGuardModel
+from strix.config.tool_call_ids import TurnCallIdRewriter, dedupe_history_call_ids
+
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+
+
+def _tool_call_completion(call_id: str, n: int = 1) -> dict[str, Any]:
+    return {
+        "id": "chatcmpl-1",
+        "object": "chat.completion",
+        "created": 0,
+        "model": "gw-model",
+        "choices": [
+            {
+                "index": 0,
+                "finish_reason": "tool_calls",
+                "message": {
+                    "role": "assistant",
+                    "content": None,
+                    "tool_calls": [
+                        {
+                            "id": call_id,
+                            "type": "function",
+                            "function": {"name": "do_thing", "arguments": json.dumps({"n": n})},
+                        }
+                    ],
+                },
+            }
+        ],
+        "usage": {"prompt_tokens": 5, "completion_tokens": 2, "total_tokens": 7},
+    }
+
+
+def _text_completion(text: str) -> dict[str, Any]:
+    return {
+        "id": "chatcmpl-2",
+        "object": "chat.completion",
+        "created": 0,
+        "model": "gw-model",
+        "choices": [
+            {"index": 0, "finish_reason": "stop", "message": {"role": "assistant", "content": text}}
+        ],
+        "usage": {"prompt_tokens": 5, "completion_tokens": 3, "total_tokens": 8},
+    }
+
+
+_REQUESTS: list[list[dict[str, Any]]] = []
+
+
+def _assistant_call_ids(messages: list[dict[str, Any]]) -> list[str]:
+    return [str(call.get("id")) for message in messages for call in message.get("tool_calls") or []]
+
+
+def _tool_results(messages: list[dict[str, Any]]) -> list[str]:
+    return [str(m.get("content")) for m in messages if m.get("role") == "tool"]
+
+
+class _StrictHandler(BaseHTTPRequestHandler):
+    """Gateway that rejects a history reusing a tool-call id, like strict providers do."""
+
+    def log_message(self, *args: Any) -> None:
+        pass
+
+    def do_POST(self) -> None:
+        length = int(self.headers.get("Content-Length", 0))
+        body = json.loads(self.rfile.read(length) or b"{}")
+        messages = body.get("messages", [])
+        _REQUESTS.append(messages)
+        call_ids = _assistant_call_ids(messages)
+
+        if len(call_ids) != len(set(call_ids)):
+            self._respond(
+                400,
+                {
+                    "error": {
+                        "message": (
+                            "tool messages need a resolvable tool name: carry `tool`/`name`, "
+                            "or match a preceding assistant tool_call by order"
+                        )
+                    }
+                },
+            )
+            return
+
+        turn = len(_REQUESTS)
+        if turn <= 2:
+            # The provider restarts its per-turn counter, so both turns say ":0".
+            self._respond(200, _tool_call_completion("exec_command:0", n=turn))
+        else:
+            self._respond(200, _text_completion("all done"))
+
+    def _respond(self, status: int, payload: dict[str, Any]) -> None:
+        encoded = json.dumps(payload).encode()
+        self.send_response(status)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(encoded)))
+        self.end_headers()
+        self.wfile.write(encoded)
+
+
+@pytest.fixture
+def strict_gateway() -> Iterator[str]:
+    _REQUESTS.clear()
+    server = HTTPServer(("127.0.0.1", 0), _StrictHandler)
+    thread = threading.Thread(target=server.serve_forever, daemon=True)
+    thread.start()
+    try:
+        yield f"http://127.0.0.1:{server.server_address[1]}/v1"
+    finally:
+        server.shutdown()
+        server.server_close()
+
+
+def _model(base_url: str) -> Model:
+    # The gateway answers plain JSON, so the run loop's streamed turns are
+    # served non-streamed; the ids on the wire are the same either way.
+    client = AsyncOpenAI(api_key="tok", base_url=base_url, max_retries=0)
+    return _NonStreamingModel(OpenAIChatCompletionsModel(model="gw-model", openai_client=client))
+
+
+async def _run_agent(base_url: str, *, wrap: bool) -> Any:
+    @function_tool
+    def do_thing(n: int) -> str:
+        return f"did {n}"
+
+    class _Provider(ModelProvider):
+        def get_model(self, model_name: str | None) -> Model:  # noqa: ARG002
+            model = _model(base_url)
+            return _TurnGuardModel(model) if wrap else model
+
+    agent = Agent(name="t", instructions="use the tool", tools=[do_thing], model="gw-model")
+    result = Runner.run_streamed(
+        agent, input="please", run_config=RunConfig(model_provider=_Provider())
+    )
+    async for _ in result.stream_events():
+        pass
+    return result
+
+
+@pytest.mark.asyncio
+async def test_recycled_call_id_erases_a_turn_without_the_wrapper(strict_gateway: str) -> None:
+    # Repro: two turns run a tool and both are labelled ``exec_command:0``, so
+    # the colliding call and its result are dropped as duplicates. The agent
+    # ends the run having silently lost a turn of its own work — and a provider
+    # that does not drop them instead rejects the malformed history outright.
+    result = await _run_agent(strict_gateway, wrap=False)
+
+    assert result.final_output == "all done"
+    assert _assistant_call_ids(_REQUESTS[-1]) == ["exec_command:0"]
+    assert _tool_results(_REQUESTS[-1]) == ["did 2"]
+
+
+@pytest.mark.asyncio
+async def test_recycled_call_id_is_rewritten_so_no_turn_is_lost(strict_gateway: str) -> None:
+    result = await _run_agent(strict_gateway, wrap=True)
+
+    assert result.final_output == "all done"
+    call_ids = _assistant_call_ids(_REQUESTS[-1])
+    assert len(call_ids) == len(set(call_ids)) == 2
+    assert call_ids[0] == "exec_command:0"
+    assert call_ids[1].startswith("call_")
+    assert _tool_results(_REQUESTS[-1]) == ["did 1", "did 2"]
+
+
+def test_history_dedupe_keeps_outputs_paired_with_their_call() -> None:
+    items = [
+        {"type": "function_call", "call_id": "exec_command:0", "name": "a", "arguments": "{}"},
+        {"type": "function_call_output", "call_id": "exec_command:0", "output": "first"},
+        {"type": "function_call", "call_id": "exec_command:0", "name": "b", "arguments": "{}"},
+        {"type": "function_call_output", "call_id": "exec_command:0", "output": "second"},
+    ]
+
+    rebuilt, changed = dedupe_history_call_ids(items)
+
+    assert changed
+    ids = [item["call_id"] for item in rebuilt]
+    assert ids[0] == ids[1] == "exec_command:0"
+    assert ids[2] == ids[3] != "exec_command:0"
+    assert rebuilt[3]["output"] == "second"
+
+
+def test_history_dedupe_pairs_parallel_calls_by_order() -> None:
+    items = [
+        {"type": "function_call", "call_id": "dup", "name": "a", "arguments": "{}"},
+        {"type": "function_call", "call_id": "dup", "name": "b", "arguments": "{}"},
+        {"type": "function_call_output", "call_id": "dup", "output": "for-a"},
+        {"type": "function_call_output", "call_id": "dup", "output": "for-b"},
+    ]
+
+    rebuilt, changed = dedupe_history_call_ids(items)
+
+    assert changed
+    assert rebuilt[0]["call_id"] == rebuilt[2]["call_id"] == "dup"
+    assert rebuilt[1]["call_id"] == rebuilt[3]["call_id"]
+    assert rebuilt[1]["call_id"] != "dup"
+
+
+def test_history_dedupe_leaves_unique_ids_alone() -> None:
+    items = [
+        {"type": "function_call", "call_id": "call_a", "name": "a", "arguments": "{}"},
+        {"type": "function_call_output", "call_id": "call_a", "output": "x"},
+        {"type": "function_call", "call_id": "call_b", "name": "b", "arguments": "{}"},
+    ]
+
+    rebuilt, changed = dedupe_history_call_ids(items)
+
+    assert not changed
+    assert rebuilt == items
+
+
+def test_turn_rewriter_is_stable_across_repeated_sightings() -> None:
+    history = [{"type": "function_call", "call_id": "exec_command:0", "name": "a"}]
+    rewriter = TurnCallIdRewriter(history)
+    call = ResponseFunctionToolCall(
+        call_id="exec_command:0", name="a", arguments="{}", type="function_call"
+    )
+
+    first = rewriter.rewrite_item(call)
+    second = rewriter.rewrite_item(first)
+
+    assert first.call_id != "exec_command:0"
+    assert second.call_id == first.call_id

tests/test_tool_call_limits.py

@@ -0,0 +1,189 @@
+"""Tests for the per-response tool-call cap.
+
+A degenerate generation can emit hundreds of tool calls in one assistant
+response — a wait/poll loop the model writes out ahead of time. The run loop
+honours every one of them, so the agent stops reacting for hours. The cap
+keeps the first N calls of a response and drops the tail.
+"""
+
+from __future__ import annotations
+
+import json
+import threading
+from http.server import BaseHTTPRequestHandler, HTTPServer
+from typing import TYPE_CHECKING, Any
+
+import pytest
+from agents import Agent, Runner, function_tool
+from agents.models.interface import Model, ModelProvider
+from agents.models.openai_chatcompletions import OpenAIChatCompletionsModel
+from agents.run import RunConfig
+from openai import AsyncOpenAI
+
+from strix.config import loader
+from strix.config.loader import load_settings
+from strix.config.models import StrixProvider, _NonStreamingModel, _TurnGuardModel
+
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+
+
+_RUNAWAY_CALLS = 200
+_CAP = 32
+
+
+def _runaway_completion() -> dict[str, Any]:
+    return {
+        "id": "chatcmpl-1",
+        "object": "chat.completion",
+        "created": 0,
+        "model": "gw-model",
+        "choices": [
+            {
+                "index": 0,
+                "finish_reason": "tool_calls",
+                "message": {
+                    "role": "assistant",
+                    "content": None,
+                    "tool_calls": [
+                        {
+                            "id": f"call_{i}",
+                            "type": "function",
+                            "function": {"name": "wait_for_message", "arguments": "{}"},
+                        }
+                        for i in range(_RUNAWAY_CALLS)
+                    ],
+                },
+            }
+        ],
+        "usage": {"prompt_tokens": 5, "completion_tokens": 2, "total_tokens": 7},
+    }
+
+
+def _text_completion() -> dict[str, Any]:
+    return {
+        "id": "chatcmpl-2",
+        "object": "chat.completion",
+        "created": 0,
+        "model": "gw-model",
+        "choices": [
+            {
+                "index": 0,
+                "finish_reason": "stop",
+                "message": {"role": "assistant", "content": "done"},
+            }
+        ],
+        "usage": {"prompt_tokens": 5, "completion_tokens": 3, "total_tokens": 8},
+    }
+
+
+_TURNS: list[int] = []
+
+
+class _RunawayHandler(BaseHTTPRequestHandler):
+    """First turn queues a huge poll loop; the next turn ends the run."""
+
+    def log_message(self, *args: Any) -> None:
+        pass
+
+    def do_POST(self) -> None:
+        length = int(self.headers.get("Content-Length", 0))
+        self.rfile.read(length)
+        _TURNS.append(1)
+        payload = _runaway_completion() if len(_TURNS) == 1 else _text_completion()
+        encoded = json.dumps(payload).encode()
+        self.send_response(200)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(encoded)))
+        self.end_headers()
+        self.wfile.write(encoded)
+
+
+@pytest.fixture
+def runaway_gateway() -> Iterator[str]:
+    _TURNS.clear()
+    server = HTTPServer(("127.0.0.1", 0), _RunawayHandler)
+    thread = threading.Thread(target=server.serve_forever, daemon=True)
+    thread.start()
+    try:
+        yield f"http://127.0.0.1:{server.server_address[1]}/v1"
+    finally:
+        server.shutdown()
+        server.server_close()
+
+
+def _model(base_url: str) -> Model:
+    client = AsyncOpenAI(api_key="tok", base_url=base_url, max_retries=0)
+    return _NonStreamingModel(OpenAIChatCompletionsModel(model="gw-model", openai_client=client))
+
+
+async def _run_agent(base_url: str, *, cap: int) -> list[int]:
+    executed: list[int] = []
+
+    @function_tool
+    def wait_for_message() -> str:
+        executed.append(1)
+        return "nothing new"
+
+    class _Provider(ModelProvider):
+        def get_model(self, model_name: str | None) -> Model:  # noqa: ARG002
+            return _TurnGuardModel(_model(base_url), max_tool_calls_per_turn=cap)
+
+    agent = Agent(name="t", instructions="orchestrate", tools=[wait_for_message], model="gw-model")
+    result = Runner.run_streamed(
+        agent, input="go", run_config=RunConfig(model_provider=_Provider())
+    )
+    async for _ in result.stream_events():
+        pass
+    assert result.final_output == "done"
+    return executed
+
+
+@pytest.mark.asyncio
+async def test_runaway_response_runs_every_queued_call_when_uncapped(runaway_gateway: str) -> None:
+    # Repro: one response queues 200 calls and the run loop honours all of them.
+    executed = await _run_agent(runaway_gateway, cap=0)
+
+    assert len(executed) == _RUNAWAY_CALLS
+
+
+@pytest.mark.asyncio
+async def test_runaway_response_is_capped(runaway_gateway: str) -> None:
+    executed = await _run_agent(runaway_gateway, cap=_CAP)
+
+    assert len(executed) == _CAP
+
+
+@pytest.mark.asyncio
+async def test_response_below_the_cap_is_untouched(runaway_gateway: str) -> None:
+    executed = await _run_agent(runaway_gateway, cap=_RUNAWAY_CALLS + 1)
+
+    assert len(executed) == _RUNAWAY_CALLS
+
+
+@pytest.fixture
+def _reset_settings(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]:
+    for key in ("STRIX_LLM", "LLM_DISABLE_STREAMING", "LLM_MAX_TOOL_CALLS_PER_TURN"):
+        monkeypatch.delenv(key, raising=False)
+    monkeypatch.setattr(loader, "_cached", None)
+    monkeypatch.setattr(loader, "_override", None)
+    yield
+
+
+class _DummyModel(Model):
+    async def get_response(self, *args: Any, **kwargs: Any) -> Any:
+        raise NotImplementedError
+
+    def stream_response(self, *args: Any, **kwargs: Any) -> Any:
+        raise NotImplementedError
+
+
+def test_cap_is_configurable(monkeypatch: pytest.MonkeyPatch, _reset_settings: None) -> None:
+    monkeypatch.setattr("strix.config.models.MultiProvider.get_model", lambda *_: _DummyModel())
+    monkeypatch.setenv("LLM_MAX_TOOL_CALLS_PER_TURN", "7")
+    load_settings()
+
+    model = StrixProvider().get_model("openai/gpt-4o-mini")
+    assert isinstance(model, _TurnGuardModel)
+    assert model._max_tool_calls_per_turn == 7

tests/test_tui_backend_controller.py

@@ -234,12 +234,11 @@ async def test_confirming_the_mount_starts_the_scan_without_a_target() -> None:
 
 
 @pytest.mark.asyncio
-async def test_declining_the_mount_returns_to_the_start_screen() -> None:
-    started = False
+async def test_declining_the_mount_runs_without_one() -> None:
+    started: list[bool] = []
 
-    async def start(_verify: bool = True) -> None:
-        nonlocal started
-        started = True
+    async def start(verify: bool = True) -> None:
+        started.append(verify)
 
     os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
     os.environ["ANTHROPIC_API_KEY"] = "test-key"
@@ -250,14 +249,34 @@ async def test_declining_the_mount_returns_to_the_start_screen() -> None:
     result = await controller.handle("setup.confirm_mount", {"approved": False})
 
     assert result == {"approved": False}
-    # Nothing was prepared, so the session goes back to the start screen and can
-    # be launched again.
-    assert started is False
+    # Declining skips the directory; it does not abandon the scan.
+    assert started == [False]
     assert controller.workspace_mount is None
     assert controller.pending_workspace_mount is None
-    assert controller.setup_mode is True
-    assert controller.scan_started is False
-    assert controller.scan_state == "setup"
+    assert controller.setup_mode is False
+    assert controller.scan_started is True
+    assert controller.scan_state == "running"
+
+
+@pytest.mark.asyncio
+async def test_approving_the_mount_runs_with_it() -> None:
+    started: list[bool] = []
+
+    async def start(verify: bool = True) -> None:
+        started.append(verify)
+
+    os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
+    os.environ["ANTHROPIC_API_KEY"] = "test-key"
+    loader._cached = None
+    controller = TuiController(args(), on_start=start)
+    await controller.handle("setup.start", {"verify": False, "mount_working_dir": True})
+
+    result = await controller.handle("setup.confirm_mount", {"approved": True})
+
+    assert result == {"approved": True}
+    assert started == [False]
+    assert controller.workspace_mount == str(Path.cwd())
+    assert controller.scan_state == "running"
 
 
 @pytest.mark.asyncio

tests/test_tui_resume_history.py

@@ -7,19 +7,26 @@ shows what the user actually typed; resuming has to match that.
 
 from __future__ import annotations
 
+import ast
 import json
 import sqlite3
+from pathlib import Path
 from typing import TYPE_CHECKING, Any
 
 import pytest
 
+from strix.core import execution
 from strix.core.paths import runtime_state_dir
 from strix.interface.tui.backend.live_view import TuiLiveView as GoTuiLiveView
-from strix.interface.tui.live_view import TuiLiveView, _is_internal_agent_turn
+from strix.interface.tui.live_view import (
+    _INTERNAL_TURN_PREFIXES,
+    TuiLiveView,
+    _is_internal_agent_turn,
+)
 
 
 if TYPE_CHECKING:
-    from pathlib import Path
+    from types import ModuleType
 
 
 def _write_run(run_dir: Path, items: list[dict[str, Any]], agent_id: str = "root") -> None:
@@ -176,11 +183,60 @@ def test_internal_turn_classifier_matches_every_injected_form() -> None:
         "[CRITICAL] Turn budget: 480/500 used (96%).",
         "== Inherited context from parent (background only) ==",
         "Your previous message ended a turn without a tool call.",
-        "Your previous response ended the autonomous Strix run without a lifecycle tool call.",
+        "Your previous response ended the autonomous run without a lifecycle tool call.",
     ):
         assert _is_internal_agent_turn(content), content
 
 
+def _injected_strings(module: ModuleType) -> list[str]:
+    """Every string a module can inject, and nothing it merely mentions.
+
+    Parsing rather than searching the text keeps comments out of it, so a stale
+    copy of a message left in a comment cannot pass for the message itself. It
+    also joins adjacent literals for free, which the line wrapping needs, and
+    docstrings are dropped because they describe the code rather than run in it.
+    """
+    tree = ast.parse(Path(module.__file__ or "").read_text(encoding="utf-8"))
+    docstrings = set()
+    for node in ast.walk(tree):
+        if not isinstance(node, ast.Module | ast.ClassDef | ast.FunctionDef | ast.AsyncFunctionDef):
+            continue
+        first = node.body[0] if node.body else None
+        if isinstance(first, ast.Expr) and isinstance(first.value, ast.Constant):
+            docstrings.add(id(first.value))
+
+    literals: list[str] = []
+    for node in ast.walk(tree):
+        if isinstance(node, ast.Constant):
+            if isinstance(node.value, str) and id(node) not in docstrings:
+                literals.append(node.value)
+        elif isinstance(node, ast.JoinedStr):
+            literals.append(
+                "".join(
+                    part.value
+                    for part in node.values
+                    if isinstance(part, ast.Constant) and isinstance(part.value, str)
+                )
+            )
+    return literals
+
+
+def test_internal_turn_prefixes_still_match_what_is_injected() -> None:
+    """The classifier copies sentences out of another module, so they can drift.
+
+    Both nudges are written inline in strix.core.execution, so there is nothing to
+    import and compare against. Read them back out of what that module can inject.
+    """
+    injected = _injected_strings(execution)
+    nudges = [prefix for prefix in _INTERNAL_TURN_PREFIXES if prefix.startswith("Your previous")]
+    assert nudges, "the no-tool-call nudges are no longer in the classifier"
+    for nudge in nudges:
+        assert any(nudge in literal for literal in injected), (
+            f"the classifier expects {nudge!r}, which strix.core.execution no longer "
+            f"injects. A resumed scan would show that nudge as the user's own message."
+        )
+
+
 def test_internal_turn_classifier_keeps_bracketed_user_text() -> None:
     """A leading bracket is not enough: typed text often starts with one."""
     for content in (

tests/test_wait_dedupe.py

@@ -0,0 +1,126 @@
+"""Tests for collapsing repeated waits queued inside one model turn.
+
+An orchestrator that writes out its whole poll loop ahead of time queues
+many ``wait_for_agents`` calls in a single response. Each one parks for its
+full timeout, so the agent stops reacting for hours while its children run
+unsupervised. Only the first wait of a turn parks; the rest return at once.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import time
+from typing import TYPE_CHECKING, Any, cast
+
+import pytest
+from agents import RunContextWrapper
+from agents.tool_context import ToolContext
+
+from strix.core.agents import AgentCoordinator
+from strix.core.hooks import LLM_TURN_KEY, ReportUsageHooks
+from strix.tools.agents_graph.tools import wait_for_agents
+
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+
+
+_WAIT_SECONDS = 2
+
+
+@pytest.fixture
+def _fast_wait(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]:
+    # The real ceiling is 300s per wait; the shape of the bug is the same.
+    monkeypatch.setattr(
+        "strix.tools.agents_graph.tools._WAIT_DEFAULT_TIMEOUT_S", _WAIT_SECONDS, raising=True
+    )
+    yield
+
+
+async def _context() -> dict[str, Any]:
+    coordinator = AgentCoordinator()
+    await coordinator.register("root", "strix", parent_id=None)
+    return {"agent_id": "root", "coordinator": coordinator}
+
+
+async def _wait(inner: dict[str, Any]) -> dict[str, Any]:
+    ctx = ToolContext(
+        context=inner,
+        tool_name="wait_for_agents",
+        tool_call_id="call-1",
+        tool_arguments="{}",
+    )
+    raw: str = await wait_for_agents.on_invoke_tool(
+        ctx, json.dumps({"reason": "waiting for wave 1", "timeout_seconds": _WAIT_SECONDS})
+    )
+    return cast("dict[str, Any]", json.loads(raw))
+
+
+@pytest.mark.asyncio
+async def test_waits_queued_in_one_turn_each_park_without_the_guard(_fast_wait: None) -> None:
+    # Repro: no turn marker in context (as before the fix) — every queued wait
+    # parks for its full timeout, so N waits cost N x timeout.
+    inner = await _context()
+
+    started = time.monotonic()
+    outcomes = [(await _wait(inner))["wait_outcome"] for _ in range(3)]
+    elapsed = time.monotonic() - started
+
+    assert outcomes == ["timeout", "timeout", "timeout"]
+    assert elapsed >= 3 * _WAIT_SECONDS
+
+
+@pytest.mark.asyncio
+async def test_repeated_waits_in_one_turn_are_collapsed(_fast_wait: None) -> None:
+    inner = await _context()
+    inner[LLM_TURN_KEY] = 1
+
+    started = time.monotonic()
+    outcomes = [(await _wait(inner))["wait_outcome"] for _ in range(3)]
+    elapsed = time.monotonic() - started
+
+    assert outcomes == ["timeout", "already_waited", "already_waited"]
+    assert elapsed < 2 * _WAIT_SECONDS
+
+
+@pytest.mark.asyncio
+async def test_a_wait_in_the_next_turn_still_parks(_fast_wait: None) -> None:
+    inner = await _context()
+    inner[LLM_TURN_KEY] = 1
+    assert (await _wait(inner))["wait_outcome"] == "timeout"
+    assert (await _wait(inner))["wait_outcome"] == "already_waited"
+
+    inner[LLM_TURN_KEY] = 2
+
+    assert (await _wait(inner))["wait_outcome"] == "timeout"
+
+
+@pytest.mark.asyncio
+async def test_each_model_turn_bumps_the_turn_marker() -> None:
+    hooks = ReportUsageHooks(model="gw-model")
+    context: RunContextWrapper[dict[str, Any]] = RunContextWrapper(context={})
+    agent = cast("Any", None)
+
+    await hooks.on_llm_start(context, agent, None, [])
+    await hooks.on_llm_start(context, agent, None, [])
+
+    assert context.context[LLM_TURN_KEY] == 2
+
+
+@pytest.mark.asyncio
+async def test_a_collapsed_wait_still_reports_arriving_messages(_fast_wait: None) -> None:
+    inner = await _context()
+    inner[LLM_TURN_KEY] = 1
+    coordinator = cast("AgentCoordinator", inner["coordinator"])
+
+    async def _send() -> None:
+        await asyncio.sleep(0.1)
+        await coordinator.send("root", {"type": "information", "content": "child done"})
+
+    task = asyncio.create_task(_send())
+    first = await _wait(inner)
+    await task
+
+    assert first["wait_outcome"] == "message_arrived"
+    assert (await _wait(inner))["wait_outcome"] == "already_waited"

uv.lock

@@ -2378,7 +2378,7 @@ wheels = [
 
 [[package]]
 name = "strix-agent"
-version = "1.4.1"
+version = "1.5.3"
 source = { editable = "." }
 dependencies = [
     { name = "caido-sdk-client" },