v0.8.2: cleanup + prose + structure + decomposition + budget + errors

Phase 1 — dedup + hardening (~9 items):
- Remove duplicate *skill-registry* defvar from core-skills
- Merge *backend-registry* into *probabilistic-backends*, delete backend-register
- Remove inject-stimulus alias, standardize on stimulus-inject
- Add pre-eval sandbox (skill-source-scan) blocks restricted symbols before eval
- Remove dead plist-get function; remove duplicate json-alist-to-plist export
- Fix read-framed-message whitespace DoS (4096-iteration max)
- Add *read-eval* nil to dispatcher-approvals-process read-from-string (RCE)
- Add test-op to ASDF; update .asd version 0.4.3→0.7.2

Phase 2 — prose + contracts + reorder:
- Split ROADMAP: 2623→1089 lines (TODO only), CHANGELOG: 260→1528 lines (full DONE history, 14 versions reverse chron)
- Add Contracts + Overview to 6 channel files + embedding-native + programming-standards + symbolic-scope
- Reorder 28 .org files: Contract → Test Suite → Implementation (TDD order)
- Add 7-phase inline prose to think() in core-reason
- Expand USER_MANUAL: 183→461 lines (10 new sections)

Phase 3 — decomposition + export organization:
- Decompose think() into think-assemble-prompt, think-call-llm, think-parse-response orchestrator
- Organize 188 exports into 16 grouped sections by module

Phase 4 — budget enforcement + error protocol:
- Per-session budget enforcement (SESSION_BUDGET_USD env var, budget-exhausted-p, guard in think-call-llm)
- Error condition hierarchy (6 conditions: pipeline-error, llm-error, gate-error, budget-error, protocol-error)
- Restarts in loop-process: skip-signal, use-fallback, abort-pipeline

org/embedding-native.org

@@ -278,6 +278,21 @@ Used in tests and embedding comparisons.
         (/ dot (sqrt (* anorm bnorm))))))
 #+end_src
 
+* Contract
+
+1. (embedding-backend-native text): computes a 768-dim single-float
+   embedding vector via llama.cpp. Returns a simple-vector. Requires
+   the model file at ~*native-model-path*~ and the C wrapper library at
+   ~/usr/local/lib/libllama_wrap.so~.
+2. (embedding-native-load-model): loads the GGUF model file and creates
+   an inference context. Caches globally in ~*native-model*~ /
+   ~*native-context*~ — subsequent calls are no-ops. Calls
+   ~sb-int:set-floating-point-modes~ and ~llama_backend_init~.
+3. (embedding-native-unload): releases native model and context memory.
+   Sets cached globals to nil.
+4. (embedding-native-get-dim): returns the embedding dimension of the
+   loaded model (768 for nomic-embed-text-v1.5), or 0 if not loaded.
+
 * Test Suite
 
 #+begin_src lisp