feat: add route-aware pricing estimates (#1695)

Salvaged from PR #1563 by @kshitijk4poor. Cherry-picked with authorship preserved.

- Route-aware pricing architecture replacing static MODEL_PRICING + heuristics
- Canonical usage normalization (Anthropic/OpenAI/Codex API shapes)
- Cache-aware billing (separate cache_read/cache_write rates)
- Cost status tracking (estimated/included/unknown/actual)
- OpenRouter live pricing via models API
- Schema migration v4→v5 with billing metadata columns
- Removed speculative forward-looking entries
- Removed cost display from CLI status bar
- Threaded OpenRouter metadata pre-warm

Co-authored-by: kshitij <82637225+kshitijk4poor@users.noreply.github.com>

tests/test_cli_status_bar.py

@@ -16,6 +16,10 @@ def _make_cli(model: str = "anthropic/claude-sonnet-4-20250514"):
 def _attach_agent(
     cli_obj,
     *,
+    input_tokens: int | None = None,
+    output_tokens: int | None = None,
+    cache_read_tokens: int = 0,
+    cache_write_tokens: int = 0,
     prompt_tokens: int,
     completion_tokens: int,
     total_tokens: int,
@@ -26,6 +30,12 @@ def _attach_agent(
 ):
     cli_obj.agent = SimpleNamespace(
         model=cli_obj.model,
+        provider="anthropic" if cli_obj.model.startswith("anthropic/") else None,
+        base_url="",
+        session_input_tokens=input_tokens if input_tokens is not None else prompt_tokens,
+        session_output_tokens=output_tokens if output_tokens is not None else completion_tokens,
+        session_cache_read_tokens=cache_read_tokens,
+        session_cache_write_tokens=cache_write_tokens,
         session_prompt_tokens=prompt_tokens,
         session_completion_tokens=completion_tokens,
         session_total_tokens=total_tokens,
@@ -68,20 +78,19 @@ class TestCLIStatusBar:
         assert "$0.06" not in text  # cost hidden by default
         assert "15m" in text
 
-    def test_build_status_bar_text_shows_cost_when_enabled(self):
+    def test_build_status_bar_text_no_cost_in_status_bar(self):
         cli_obj = _attach_agent(
             _make_cli(),
             prompt_tokens=10000,
-            completion_tokens=2400,
-            total_tokens=12400,
+            completion_tokens=5000,
+            total_tokens=15000,
             api_calls=7,
-            context_tokens=12400,
+            context_tokens=50000,
             context_length=200_000,
         )
-        cli_obj.show_cost = True
 
         text = cli_obj._build_status_bar_text(width=120)
-        assert "$" in text  # cost is shown when enabled
+        assert "$" not in text  # cost is never shown in status bar
 
     def test_build_status_bar_text_collapses_for_narrow_terminal(self):
         cli_obj = _attach_agent(
@@ -128,8 +137,8 @@ class TestCLIUsageReport:
         output = capsys.readouterr().out
 
         assert "Model:" in output
-        assert "Input cost:" in output
-        assert "Output cost:" in output
+        assert "Cost status:" in output
+        assert "Cost source:" in output
         assert "Total cost:" in output
         assert "$" in output
         assert "0.064" in output