# Orchestrator Task Prompts for Jules (System Analyst & Implementation)

This document contains pre-configured orchestrator prompts strictly following
[`tasks/META_PROMPT.md`](file:///home/tylerg/p/data/auth-yes/tasks/META_PROMPT.md)
and [`tasks/GUIDELINES.md`](file:///home/tylerg/p/data/auth-yes/tasks/GUIDELINES.md).

---

## Progress & Execution Roadmap

| Prompt ID | Task Scope | Status | Target File |
| :--- | :--- | :--- | :--- |
| **Prompt 1.1** | Ingress Grant Vector Injection (`/api/forward-auth`) | ✅ **COMPLETE** | `server/main.ts`, `server/auth-session.ts` |
| **Prompt 1.2** | SDK Real-Time Invalidation Event Bus (`@auth-yes/sdk`) | ✅ **COMPLETE** | `sdk/mod.ts` |
| **Prompt 3.2** | Native SIMD Argon2id Derivation in `spire_ffi` | ✅ **COMPLETE** | `spire_ffi/src/lib.rs`, `server/spire_ffi.ts` |
| **Prompt 2.1** | RFC 9421 HTTP Signatures & `Signature-Key` (`hwk`) | ⏳ **READY TO RUN** | `server/http_signatures.ts`, `sdk/` |
| **Prompt 2.2** | Ghost Cockpit Protocol & WebSocket Freeze/Re-Auth | ⏳ **READY TO RUN** | `docs/GHOST_COCKPIT_SPEC.md`, `sdk/hono.ts` |
| **Prompt 3.1** | WebAuthn PRF Extension & Progressive Fallback | ⏳ **PENDING (Phase 3)** | `server/main.ts`, `ui/views/` |
| **Prompt 3.3** | 2-of-3 SSS Recovery Matrix (Wasm/Rust) | ⏳ **PENDING (Phase 3)** | `ui/views/recovery.tsx` |
| **Prompt 3.4** | RFC 6962 Merkle Tree Audit Ledger & STH | ⏳ **PENDING (Phase 3)** | `server/audit_merkle.ts` |

---

## Phase 1 Prompts

### Prompt 1.1: Ingress Grant Vector Injection (`/api/forward-auth`) — [STATUS: ✅ COMPLETE]

_Completed task: `tasks/complete/2026-0824.03.jul.feat.auth-api.ingress-grant-injection-1200.md`_

---

### Prompt 1.2: SDK Real-Time Invalidation Event Bus (`@auth-yes/sdk`) — [STATUS: ✅ COMPLETE]

_Completed task: `tasks/complete/2026-0824.02.jul.feat.sdk.realtime-invalidation-bus-1200.md`_

---

## Phase 2 Prompts (NEXT BATCH TO RUN)

### Prompt 2.1: RFC 9421 HTTP Message Signatures & Autonomous `Signature-Key` — [STATUS: ⏳ READY]

```text
**Role:** Act as a System Analyst and Solutions Architect. Do not execute code or modify the codebase during this session. Your sole deliverable is to generate a task file in tasks/new/.

**The Objective:** Implement RFC 9421 HTTP Message Signatures verification for edge nodes and headless daemons, utilizing `Signature-Input` and `Signature-Key` with Header Web Key (`hwk`) in Octet Key Pair (`OKP`) format, validated against an $O(1)$ Valkey authorized fingerprint set in under 5 microseconds.

**Suggestions & Initial Thoughts:**
*Here is our starting hypothesis. Treat these as ideas to evaluate, not rigid requirements:*
*   Create a pure Deno WebCrypto/Ed25519 validator module in `server/http_signatures.ts`.
*   Parse RFC 9421 canonical components (`@method`, `@authority`, `@path`, `content-digest`, `created`, `expires`, `nonce`).
*   Extract the inline Ed25519 public key from `Signature-Key: hwk="..."` and verify the SHA-256 fingerprint exists in Valkey's authorized set (`auth:hwk:fingerprints`).
*   Verify the Ed25519 digital signature over the canonical signature base with strict $\pm 30$s timestamp drift tolerance.

**Your Task:** 
1. Research the codebase and analyze this objective against our current architecture in `server/` and `sdk/`. 
2. Critically evaluate our suggestions: Do they make technical sense, or is there a cleaner, more native, or more modular approach?
3. Map out the `Target Files`, prerequisites/dependencies, and explicitly identify potential architectural risks, regressions, or friction.
4. Draft the task file in `tasks/new/` strictly adhering to the naming conventions, header metadata, and mandatory structure defined in `tasks/GUIDELINES.md`.
```

---

### Prompt 2.2: The Ghost Cockpit Protocol Specification & Re-Auth Choreography

```text
**Role:** Act as a System Analyst and Solutions Architect. Do not execute code or modify the codebase during this session. Your sole deliverable is to generate a task file in tasks/new/.

**The Objective:** Formalize the Ghost Cockpit Protocol specification and write server/client reference helpers in `@auth-yes/sdk/hono` to support non-destructive WebSocket telemetry freezes and seamless in-flight WebAuthn re-authentication.

**Suggestions & Initial Thoughts:**
*Here is our starting hypothesis. Treat these as ideas to evaluate, not rigid requirements:*
*   Document the protocol choreography in `docs/GHOST_COCKPIT_SPEC.md`.
*   Create a reusable WebSocket session guard helper in `sdk/hono.ts` that listens to `authSdk.on("invalidate")` and emits the `{ "type": "AUTH_REVOKED", "reason": "SESSION_EXPIRED" }` control frame before closing the socket.
*   Provide a client-side TypeScript snippet demonstrating state-freeze in memory and zero-redirect background WebAuthn re-authentication.

**Your Task:** 
1. Research the codebase and analyze this objective against our current architecture in `sdk/hono.ts` and `docs/`. 
2. Critically evaluate our suggestions: Do they make technical sense, or is there a cleaner, more native, or more modular approach?
3. Map out the `Target Files`, prerequisites/dependencies, and explicitly identify potential architectural risks, regressions, or friction.
4. Draft the task file in `tasks/new/` strictly adhering to the naming conventions, header metadata, and mandatory structure defined in `tasks/GUIDELINES.md`.
```

---

## Phase 3 Prompts

### Prompt 3.1: WebAuthn PRF Extension & Progressive Fallback

```text
**Role:** Act as a System Analyst and Solutions Architect. Do not execute code or modify the codebase during this session. Your sole deliverable is to generate a task file in tasks/new/.

**The Objective:** Implement WebAuthn PRF (Pseudo-Random Function) extension support in Auth-Yes registration and login flows, including progressive feature detection (`getClientExtensionResults()?.prf?.enabled`) and dual-salt evaluation (`eval.first`, `eval.second`) for atomic envelope re-encryption.

**Suggestions & Initial Thoughts:**
*Here is our starting hypothesis. Treat these as ideas to evaluate, not rigid requirements:*
*   In `server/main.ts` (SimpleWebAuthn challenge generation), request the `prf: {}` extension during passkey registration.
*   In `ui/views/register.tsx` and `ui/views/login.tsx`, evaluate the PRF salt during `navigator.credentials.get()`.
*   If PRF is supported by the authenticator, derive the 256-bit AES-GCM Key Encryption Key (KEK) using HKDF over the 32-byte PRF output.
*   If `getClientExtensionResults()?.prf?.enabled` is false, gracefully continue standard signature-only authentication without blocking login.

**Your Task:** 
1. Research the codebase and analyze this objective against our current architecture in `server/` and `ui/`. 
2. Critically evaluate our suggestions: Do they make technical sense, or is there a cleaner, more native, or more modular approach?
3. Map out the `Target Files`, prerequisites/dependencies, and explicitly identify potential architectural risks, regressions, or friction.
4. Draft the task file in `tasks/new/` strictly adhering to the naming conventions, header metadata, and mandatory structure defined in `tasks/GUIDELINES.md`.
```

---

### Prompt 3.2: Native SIMD Argon2id Derivation in `spire_ffi` Rust Crate — [STATUS: ✅ COMPLETE]

_Completed task: `tasks/complete/2026-0824.01.jul.feat.spire-ffi.native-argon2-0352.md`_

---

### Prompt 3.3: 2-of-3 Shamir's Secret Sharing (SSS) Wasm Recovery Matrix

```text
**Role:** Act as a System Analyst and Solutions Architect. Do not execute code or modify the codebase during this session. Your sole deliverable is to generate a task file in tasks/new/.

**The Objective:** Implement constant-time 2-of-3 Shamir's Secret Sharing (SSS) key splitting and reconstruction in WebAssembly/Rust for the client-side zero-downgrade recovery portal, with mandatory in-place memory zeroization (`Uint8Array.fill(0)`).

**Suggestions & Initial Thoughts:**
*Here is our starting hypothesis. Treat these as ideas to evaluate, not rigid requirements:*
*   Implement constant-time polynomial interpolation over GF(256) in Rust and compile to a standalone Wasm module.
*   In `ui/views/recovery.tsx`, execute the 2-of-3 share reconstruction inside an isolated sandbox iframe.
*   Immediately after importing the reconstructed master key into WebCrypto as an unexportable `CryptoKey`, execute `.fill(0)` across all typed arrays to purge key material from heap memory.

**Your Task:** 
1. Research the codebase and analyze this objective against our current architecture in `server/` and `ui/`. 
2. Critically evaluate our suggestions: Do they make technical sense, or is there a cleaner, more native, or more modular approach?
3. Map out the `Target Files`, prerequisites/dependencies, and explicitly identify potential architectural risks, regressions, or friction.
4. Draft the task file in `tasks/new/` strictly adhering to the naming conventions, header metadata, and mandatory structure defined in `tasks/GUIDELINES.md`.
```

---

### Prompt 3.4: RFC 6962 Merkle Tree Audit Ledger with Micro-Batched STH

```text
**Role:** Act as a System Analyst and Solutions Architect. Do not execute code or modify the codebase during this session. Your sole deliverable is to generate a task file in tasks/new/.

**The Objective:** Implement an append-only RFC 6962 Merkle Tree audit ledger in PostgreSQL with 30–60 second micro-batching, Signed Tree Head (STH) computation signed by SPIRE server keys, and distributed witness broadcast over Valkey pub/sub.

**Suggestions & Initial Thoughts:**
*Here is our starting hypothesis. Treat these as ideas to evaluate, not rigid requirements:*
*   Create `server/audit_merkle.ts` implementing Merkle tree leaf computation and inclusion proof generator (`verifyInclusionProof`).
*   Implement a background micro-batcher sealing the tree head every 60 seconds (or 1,000 writes) without blocking relational write throughput.
*   Broadcast the signed STH over Valkey pub/sub (`auth:audit:sth`) to independent witness nodes.

**Your Task:** 
1. Research the codebase and analyze this objective against our current architecture in `server/audit.ts` and `server/valkey.ts`. 
2. Critically evaluate our suggestions: Do they make technical sense, or is there a cleaner, more native, or more modular approach?
3. Map out the `Target Files`, prerequisites/dependencies, and explicitly identify potential architectural risks, regressions, or friction.
4. Draft the task file in `tasks/new/` strictly adhering to the naming conventions, header metadata, and mandatory structure defined in `tasks/GUIDELINES.md`.
```