feat: use structured outputs for vuln agent exploitation queues (#267)

* feat: add structured outputs for vuln agent exploitation queues

Use Claude Agent SDK's native outputFormat to get schema-validated JSON
queue data from vulnerability analysis agents instead of relying on
save-deliverable tool calls for queue files.

- Add Zod schemas for all 5 vuln types (injection, xss, auth, ssrf, authz)
- Thread outputFormat through SDK call chain (executor → message handlers)
- Write structured_output to disk as queue JSON before validation
- Handle error_max_structured_output_retries as retryable failure
- Update vuln prompts to use structured output for queues
- Keep save-deliverable for markdown deliverables (unchanged)

* fix: correct structured output schema conversion for Claude Agent SDK

Use draft-07 target for z.toJSONSchema() instead of the default
draft-2020-12, which the SDK's AJV validator doesn't support. Update
pipeline-testing prompts to use structured output instead of raw JSON
responses.

* refactor: remove save-deliverable references for queues in vuln prompts

Queues are now captured via structured outputs, so vuln agents no longer
need to use save-deliverable for queue JSON. Removes references to
"structured response/output" phrasing and aligns all prompts to use
consistent "exploitation queue" terminology.

* refactor: remove queue support from save-deliverable

Queues are now produced via structured outputs, so save-deliverable no
longer needs queue-related code. Removes queue enum values, filename
mappings, JSON validation, and updates all prompt tool descriptions to
match the simplified CLI interface.

* fix: instruct vuln agents to save deliverable before exploitation queue

The structured output tool terminates the agent session when called.
Agents were calling it before saving their deliverable markdown,
causing output validation failures and unnecessary retries.

* refactor: remove explicit exploitation queue output instructions from vuln prompts

The Claude Agent SDK automatically captures structured output on the
last turn when outputFormat is set. Prompts explicitly telling agents
to produce the queue caused them to call StructuredOutput mid-session,
conflicting with the SDK mechanism and silently dropping the output.

Removed exploitation_queue_requirements sections and queue references
from conclusion triggers. Added note that the queue is captured
automatically. Updated Your Output to point to the deliverable markdown.

apps/worker/prompts/vuln-authz.txt

@@ -45,7 +45,7 @@ Success criterion: A complete, code-backed analysis of every potential authoriza
 **Phase Sequence:** RECON (Complete) → **AUTHZ ANALYSIS (You)** → EXPLOITATION (next phase)
 
 **Your Input:** `deliverables/recon_deliverable.md`, `deliverables/pre_recon_deliverable.md` (reconnaissance findings)
-**Your Output:** `deliverables/authz_exploitation_queue.json` (actionable vulnerabilities for exploitation)
+**Your Output:** `deliverables/authz_analysis_deliverable.md` (analysis report for exploitation phase)
 
 **WHAT HAPPENED BEFORE YOU:**
 - Reconnaissance agent mapped application architecture, endpoints, and data flows
@@ -81,10 +81,10 @@ An **exploitable vulnerability** is a logical flaw in the code that represents a
 **Available Tools:**
 - **Task Agent (Code Analysis):** Your primary tool. Use it to ask targeted questions about the source code, trace authorization logic paths, and understand permission models. MANDATORY for all source code analysis.
 - **save-deliverable (CLI Tool):** Saves your deliverable files with automatic validation.
-  - **Usage:** `save-deliverable --type <TYPE> --file-path <path>` or `--content '<json>'`
-  - **Returns:** JSON to stdout: `{"status":"success","filepath":"...","validated":true}` or `{"status":"error","message":"...","retryable":true}`
+  - **Usage:** `save-deliverable --type <TYPE> --file-path <path>` or `--content '<text>'`
+  - **Returns:** JSON to stdout: `{"status":"success","filepath":"..."}` or `{"status":"error","message":"...","retryable":true}`
   - **For large reports:** Write to disk first, then use `--file-path`. Do NOT pass large reports via `--content`.
-  - **For JSON queues:** You may use `--content '{"vulnerabilities": [...]}'`. Queue files are validated automatically.
+
 - **Bash tool:** Use for creating directories, copying files, and other shell commands as needed.
 - **Browser Automation (playwright-cli skill):** For browser interactions with the live web application (multi-step flows and role-based access controls), invoke the `playwright-cli` skill to learn available commands. Always pass `-s={{PLAYWRIGHT_SESSION}}` to every command for session isolation.
 - **TodoWrite Tool:** Use this to create and manage your analysis task list. Create a todo item for each endpoint that needs authorization analysis. Mark items as "in_progress" when working on them and "completed" when done.
@@ -93,7 +93,7 @@ An **exploitable vulnerability** is a logical flaw in the code that represents a
 <data_format_specifications>
 
 <exploitation_queue_format>
-**Purpose:** Defines the structure for a "exploitation queue" saved via the save-deliverable CLI with --type AUTHZ_QUEUE.
+**Purpose:** Defines the format of the exploitation queue JSON.
 **Structure:** The `vulnerability` JSON object MUST follow this exact format:
 	{
 		"ID": "unique ID for each vulnerability (e.g., AUTHZ-VULN-01)",
@@ -238,7 +238,7 @@ An **exploitable vulnerability** is a logical flaw in the code that represents a
 
 For each analysis you perform from the lists above, you must make a final **verdict**:
 
-- If the verdict is **`vulnerable`**, you must document the finding using the save-deliverable CLI to update the exploitation queue.
+- If the verdict is **`vulnerable`**, you must include the finding in your exploitation queue.
 - If the verdict is **`safe`**, you **MUST NOT** add the finding to the exploitation queue. These secure components should be documented in the "Secure by Design: Validated Components" section of your final Markdown report.
 </methodology>
 
@@ -340,27 +340,20 @@ examples:
 
 </deliverable_instructions>
 
-<exploitation_queue_requirements>
-**Exploitation Queue (MANDATORY)**
-Regardless of whether vulnerabilities are found, you MUST create the exploitation queue using the save-deliverable CLI tool:
-- **If vulnerabilities found:** Run save-deliverable CLI with `--type AUTHZ_QUEUE --content '{"vulnerabilities": [...]}'` with each confirmed hypothesis following the `exploitation_queue_format`. Set `externally_exploitable` to `true` ONLY if exploitable via public internet without internal access.
-- **If no vulnerabilities found:** Run save-deliverable CLI with `--type AUTHZ_QUEUE --content '{"vulnerabilities": []}'`.
-- **QUEUE INCLUSION CRITERIA:** ONLY include vulnerabilities where `externally_exploitable = true`. Exclude any vulnerability requiring internal network access, VPN, or direct server access.
-This file serves as the handoff mechanism and must always be created to signal completion.
-</exploitation_queue_requirements>
 
 <conclusion_trigger>
 **COMPLETION REQUIREMENTS (ALL must be satisfied):**
 
 1. **Todo Completion:** ALL tasks in your TodoWrite list must be marked as "completed"
-2. **Deliverable Generation:** Both required deliverables must be successfully saved using the save-deliverable CLI tool:
+2. **Deliverable Generation:** Your deliverable must be successfully saved using the save-deliverable CLI tool:
    - **CHUNKED WRITING (MANDATORY):**
      1. Use the **Write** tool to create `deliverables/authz_analysis_deliverable.md` with the title and first major section
      2. Use the **Edit** tool to append each remaining section — match the last few lines of the file, then replace with those lines plus the new section content
      3. Repeat step 2 for all remaining sections
      4. Run `save-deliverable` with `--type AUTHZ_ANALYSIS --file-path "deliverables/authz_analysis_deliverable.md"`
      **WARNING:** Do NOT write the entire report in a single tool call — exceeds 32K output token limit. Split into multiple Write/Edit operations.
-   - Exploitation queue: Run save-deliverable CLI with `--type AUTHZ_QUEUE --content '{"vulnerabilities": [...]}'`
+
+**Note:** Save your deliverable markdown via save-deliverable first. The exploitation queue is captured automatically at the end of your session.
 
 **ONLY AFTER** both todo completion AND successful deliverable generation, announce "**AUTHORIZATION ANALYSIS COMPLETE**" and stop.