fix(spoof): CCH x-anthropic-billing-header + complete auto-discovery (v0.1.15+v0.1.16)

[ste-bah]

Summary

THE bug after 2 weeks of agent-launch failures and four wrong-theory hotfixes. Side-by-side comparison with claurst (third-party Rust port at `/tmp/claurst/`) revealed the actual root cause: archon-cli's spoof was missing the Claude Code billing/anti-spoof header. Anthropic was returning 429 with no `retry-after` (matching the fallback default in `classify_error` exactly) — not a real rate limit, but Anthropic rejecting our request as an invalid Claude Code attestation.

Bundles v0.1.15 (CCH fix + initial discovery wiring) + v0.1.16 (auto-discovery completion) into one PR — version 0.1.14 → 0.1.16.

Bug #1 — broken billing header since initial commit (v0.1.15)

`identity.rs::billing_header()` built a billing string in the right format but inserted it as a SYSTEM PROMPT TEXT BLOCK (invisible to Anthropic's HTTP-header billing layer) and omitted the `cch=` field entirely. `compute_fingerprint` used SHA256 of three cherry-picked characters from the first user message — bears no relation to xxhash64-of-body that Anthropic actually validates.

Fix: mirror claurst exactly. New `crates/archon-llm/src/cch.rs` with `xxhash64(body, 0x6E52736AC806831E) & 0xFFFFF` formatted as `cch=<5hex>`. `anthropic.rs` adds HTTP header `x-anthropic-billing-header` per request, computed from the actual serialized body bytes. Deleted the broken `compute_fingerprint` and the system-prompt-block insertion.

Bug #2 — discovery infrastructure unfinished (v0.1.16)

Even after wiring `discover_claude_code_identity()` into production, version discovery from binary strings did NOT work on Bun-templated versions (Claude Code v2.1.119+) — the version is templated at runtime, not a literal in the binary's strings table. Spoof would fall back to the hardcoded `spoof_version="2.1.89"` config default (30 patch versions stale).

Fix: new `version_from_package_json()` walks `bin/claude → ../package.json` and extracts the npm version field. Reliable on v2.1.119. Plus memoization via `std::sync::OnceLock` (was walking 234M binary on every call), and resolver helpers (`resolve_spoof_version` / `resolve_user_agent` / `resolve_entrypoint`) returning `(value, source)` tuples for log surfacing. `session.rs` emits `info!("Spoof identity resolved", version, version_source, ...)` at startup.

Test plan

• cargo check --workspace --tests -j1 --offline: exit 0
• cargo nextest run --workspace -j1 -- --test-threads=2: ALL PASS
  • 4 cch unit tests (format, determinism, body-sensitivity, cross-reference vector)
  • cch_header_sent: spoof mode includes header; clean mode omits
  • cch_matches_body: hash recomputed per request from actual serialized body
  • diagnostic_surfacing: 429 response body surfaces through LlmError → TUI
  • identity_discovery: synthetic-strings extraction + cch_required detection
  • identity_resolution: 12 tests for priority resolution + memoization
• cargo fmt --check: PASS
• cargo build --release --bin archon -j1: PASS
• Real binary smoke (Steven): `target/release/archon`, type `use the coder agent to create a file called testing.txt with the words "hello world" inside it`. Verify:
  • Startup log emits "Spoof identity resolved" with the installed binary's actual version (v2.1.119, NOT v2.1.89)
  • NO 429. Subagent dispatches successfully. `testing.txt` is created with `hello world` content.
  • Two weeks of agent-launch failures resolved.