v3.7.0: Intelligence Routing — self-healing parser system

Layer 1 (FIX 23): Deep URL extraction from nested JSON in explore_agent blocks.
Layer 2 (FIX 24): Auto-proceed on require_escalation / request_escalation_permission.
Layer 3 (FIX 25): Intent-based command synthesis with 5 heuristics when all parsers fail.

Module-level _build_explore_cmd() for reuse across parser + stream path.
54 self-test patterns (up from 41).

CHANGELOG.md

@@ -1,5 +1,48 @@
 # Changelog
 
+## v3.7.0 (2026-05-22)
+
+**Intelligence Routing — Self-Healing Parser System**
+
+When the Command Code model produces output in unpredictable or unrecognized formats, the multi-format parser chain (DSML, XML, explore_agent, bash blocks, raw JSON, fallback regex) can return empty. This causes the Codex agent loop to stall — zero tool calls means nothing to execute.
+
+Intelligence Routing is a **three-layer self-healing system** that ensures the agent loop always continues:
+
+### Layer 1: Deep URL Extraction (FIX 23)
+- **Problem**: `<explore_agent>` body contained `messages: [{"content": "https://..."}]` — URLs hidden inside JSON values. Regex couldn't match because it excluded the `"` character that terminates JSON strings.
+- **Solution**: `_build_explore_cmd()` extracted to module level (was a closure inside `_parse_commandcode_text_tool_calls`). After initial regex fails, tries `json.loads()`, iterates list items, extracts `content` field to find URLs. Added `"` to regex exclusion set.
+- **Self-tests**: Pattern M, O, O2 verify URL extraction from nested JSON.
+
+### Layer 2: Escalation Block Handling (FIX 24)
+- **Problem**: Model produces `<require_escalation>` and `<request_escalation_permission>` blocks when it wants elevated permissions. CC adapter doesn't support escalation — blocks silently dropped → `parsed_tool_calls=0` → stall.
+- **Solution**: Two handlers:
+  - FIX 24a: Closed-tag blocks — extracts URL if present and runs explore command; otherwise echoes auto-proceed.
+  - FIX 24b: Bare/unclosed tags (`<require_escalation />`) — auto-proceeds with diagnostic echo.
+- **Self-tests**: Pattern N, N2 verify both closed and bare escalation blocks.
+
+### Layer 3: Intent-Based Command Synthesis (FIX 25 — THE CORE)
+- **Problem**: After ALL parsers return empty, the agent loop has zero tool calls. Model may have written plain English ("I need to fetch the README"), partial JSON, or completely unrecognized formats.
+- **Solution**: 5-heuristic synthesis chain in `cc_stream_to_sse()`, run when `parsed_tool_calls=0` and text has content:
+  1. **URL in text** → `curl` to fetch it
+  2. **File path reference** ("read the file /path/to/X") → `cat` or `ls` that file
+  3. **Shell command in backticks/quotes** → extract and run it
+  4. **"explore"/"fetch"/"investigate"/"repository" intent** + last user URL → `_build_explore_cmd()` with `_last_user_urls` deque
+  5. **"I need to"/"let me"/"please" intent text** → echo diagnostic with the intent
+- The system NEVER returns empty tool calls when there's text to analyze.
+- **Self-tests**: Patterns M-O2 cover the full pipeline.
+
+### Architecture
+```
+_parse_commandcode_text_tool_calls()  ←  Layer 1 + Layer 2
+cc_stream_to_sse()                    ←  Layer 3 (after parser chain + fallback)
+_last_user_urls deque (maxlen=20)     ←  Session-wide URL memory for heuristic 4
+```
+
+### Test Coverage
+- **54 self-test patterns** (up from 41 in v3.6.0)
+- 13 new tests covering all three Intelligence Routing layers
+- Tests verify: nested JSON URL extraction, closed/bare escalation blocks, module-level explore command builder
+
 ## v3.6.0 (2026-05-22)
 
 **Performance & Stability Hardening — Connection Pooling, Stream Idle Timeouts, Retry-After**