DO-NOT-MERGE · model ratchet: default opus to 4.8 + deprecated-tier sweep + model-id allowlist guard

.env.example

@@ -24,4 +24,4 @@
 #
 # ANTHROPIC_API_KEY=sk-ant-api03-REPLACE_ME
 # Optional model pin
-# ANTHROPIC_MODEL=claude-sonnet-4-7-20260101
+# ANTHROPIC_MODEL=claude-sonnet-4-6

README.md

@@ -224,7 +224,7 @@ max_budget_usd = 5.0                # per-pipeline budget cap (>= 0)
 persona = "falcor"                  # CLI output persona
 
 [models]                            # bring your own provider key — strings live here
-reasoning = "claude-opus-4-7"       # researcher, reviewer, synthesizer, analyst
+reasoning = "claude-opus-4-8"       # researcher, reviewer, synthesizer, analyst
 fast      = "claude-haiku-4-5"      # tester, implementer, verifier, publisher, closer
 balanced  = "claude-sonnet-4-6"     # fallback for unknown role strings
 

src/bonfire/dispatch/pydantic_ai_backend.py

@@ -35,7 +35,7 @@ class PydanticAIBackend:
     Parameters
     ----------
     model
-        The model identifier string (e.g. ``"claude-sonnet-4-20250514"``).
+        The model identifier string (e.g. ``"claude-sonnet-4-6"``).
     """
 
     def __init__(self, model: str = "") -> None:

src/bonfire/models/config.py

@@ -90,7 +90,7 @@ class ModelsConfig(BaseModel):
     configured backend.
     """
 
-    reasoning: str = "claude-opus-4-7"
+    reasoning: str = "claude-opus-4-8"
     fast: str = "claude-haiku-4-5"
     balanced: str = "claude-sonnet-4-6"
 

tests/e2e/prompts/runner-prompt.md

@@ -18,7 +18,7 @@ The project at /workspace/target has one deliberately broken test. Your job is t
 Append two JSONL lines (one JSON object per line, newline-terminated). Use today's unix timestamp for `timestamp` (call `date +%s.%N`). Use the SESSION_ID env var for `session_id`. Approximate the cost and duration based on what you observed.
 
 Line 1 (DispatchRecord — your work counts as one dispatch):
-{"type":"dispatch","timestamp":1714564800.123,"session_id":"<SESSION_ID>","agent_name":"claude-cli","cost_usd":0.42,"duration_seconds":187.5,"model":"claude-sonnet-4-7-20260101"}
+{"type":"dispatch","timestamp":1714564800.123,"session_id":"<SESSION_ID>","agent_name":"claude-cli","cost_usd":0.42,"duration_seconds":187.5,"model":"claude-sonnet-4-6"}
 
 Line 2 (PipelineRecord — your work counts as a one-stage pipeline):
 {"type":"pipeline","timestamp":1714564800.456,"session_id":"<SESSION_ID>","total_cost_usd":0.42,"duration_seconds":187.5,"stages_completed":1}

tests/integration/test_budget_enforcement.py

@@ -309,9 +309,9 @@ async def test_max_budget_usd_reaches_claude_agent_options(self) -> None:
         ):
             backend = ClaudeSDKBackend()
             await backend.execute(
-                Envelope(task="t", agent_name="scout-agent", model="claude-opus-4-7"),
+                Envelope(task="t", agent_name="scout-agent", model="claude-opus-4-8"),
                 options=DispatchOptions(
-                    model="claude-opus-4-7",
+                    model="claude-opus-4-8",
                     max_budget_usd=3.14,
                     max_turns=7,
                 ),
@@ -334,7 +334,7 @@ async def test_max_budget_usd_zero_default_preserved(self) -> None:
             # Default DispatchOptions.max_budget_usd is 0.0 per protocols.py:62.
             await backend.execute(
                 Envelope(task="t", agent_name="scout-agent"),
-                options=DispatchOptions(model="claude-opus-4-7"),
+                options=DispatchOptions(model="claude-opus-4-8"),
             )
 
         assert captured["max_budget_usd"] == pytest.approx(0.0)
@@ -359,9 +359,9 @@ async def test_max_turns_reaches_claude_agent_options(self) -> None:
         ):
             backend = ClaudeSDKBackend()
             await backend.execute(
-                Envelope(task="t", agent_name="knight-agent", model="claude-opus-4-7"),
+                Envelope(task="t", agent_name="knight-agent", model="claude-opus-4-8"),
                 options=DispatchOptions(
-                    model="claude-opus-4-7",
+                    model="claude-opus-4-8",
                     max_turns=42,
                     max_budget_usd=1.0,
                 ),
@@ -381,7 +381,7 @@ async def test_max_turns_default_reaches_sdk(self) -> None:
             backend = ClaudeSDKBackend()
             await backend.execute(
                 Envelope(task="t", agent_name="scout-agent"),
-                options=DispatchOptions(model="claude-opus-4-7"),
+                options=DispatchOptions(model="claude-opus-4-8"),
             )
 
         assert captured["max_turns"] == 10

tests/unit/test_bard_handler.py

@@ -1151,7 +1151,7 @@ async def test_custom_config_does_not_override_slug_constants(
         github_client,
     ) -> None:
         """slug_max_len + suffix_chars are module-scope constants, not config knobs."""
-        cfg = PipelineConfig(model="claude-opus-4-7")
+        cfg = PipelineConfig(model="claude-opus-4-8")
         handler = BardHandler(
             git_workflow=git_workflow,
             github_client=github_client,

tests/unit/test_config.py

@@ -83,13 +83,13 @@ def test_default_construction(self):
     def test_custom_values(self):
         p = PipelineConfig(
             tier="pro",
-            model="claude-opus-4",
+            model="claude-opus-4-8",
             max_turns=20,
             max_budget_usd=50.0,
             persona="anta",
         )
         assert p.tier == "pro"
-        assert p.model == "claude-opus-4"
+        assert p.model == "claude-opus-4-8"
         assert p.max_turns == 20
         assert p.max_budget_usd == 50.0
         assert p.persona == "anta"
@@ -380,7 +380,7 @@ def test_agents_from_toml(self, tmp_path, monkeypatch):
 # Locks the ``[models]`` TOML schema delivered by BON-350:
 #
 #   * §D5 — three string fields (``reasoning``/``fast``/``balanced``)
-#     defaulting to ``claude-opus-4-7``/``claude-haiku-4-5``/``claude-sonnet-4-6``.
+#     defaulting to ``claude-opus-4-8``/``claude-haiku-4-5``/``claude-sonnet-4-6``.
 #   * §D5 — TOML ``[models]`` section loads onto ``BonfireSettings.models``;
 #     missing section falls back to defaults (backward-compatible).
 #   * §D5 — Arbitrary strings accepted (BYOK passthrough).
@@ -399,7 +399,7 @@ def test_default_construction_recommends_anthropic(self):
         from bonfire.models.config import ModelsConfig
 
         m = ModelsConfig()
-        assert m.reasoning == "claude-opus-4-7"
+        assert m.reasoning == "claude-opus-4-8"
         assert m.fast == "claude-haiku-4-5"
         assert m.balanced == "claude-sonnet-4-6"
 
@@ -453,13 +453,13 @@ class TestModelsConfigTomlPartialOverride:
             ),
             (
                 '[models]\nfast = "Y"\n',
-                "claude-opus-4-7",
+                "claude-opus-4-8",
                 "Y",
                 "claude-sonnet-4-6",
             ),
             (
                 '[models]\nbalanced = "Z"\n',
-                "claude-opus-4-7",
+                "claude-opus-4-8",
                 "claude-haiku-4-5",
                 "Z",
             ),

tests/unit/test_cost_analyzer.py

@@ -576,15 +576,15 @@ def test_groups_records_by_model(self, ledger_path: Path) -> None:
                 agent_name="a",
                 cost_usd=0.10,
                 duration_seconds=1.0,
-                model="claude-opus-4-7",
+                model="claude-opus-4-8",
             ),
             DispatchRecord(
                 timestamp=2.0,
                 session_id="s",
                 agent_name="b",
                 cost_usd=0.05,
                 duration_seconds=2.0,
-                model="claude-opus-4-7",
+                model="claude-opus-4-8",
             ),
             DispatchRecord(
                 timestamp=3.0,
@@ -601,7 +601,7 @@ def test_groups_records_by_model(self, ledger_path: Path) -> None:
         assert len(results) == 2
         assert all(isinstance(r, ModelCost) for r in results)
         models_to_records = {r.model: r for r in results}
-        assert set(models_to_records) == {"claude-opus-4-7", "claude-haiku-4-5"}
+        assert set(models_to_records) == {"claude-opus-4-8", "claude-haiku-4-5"}
 
     def test_sort_descending_by_cost(self, ledger_path: Path) -> None:
         """Sage memo D8 — sort key is ``total_cost_usd``, descending. Same
@@ -659,7 +659,7 @@ def test_legacy_empty_model_grouped_visible(self, ledger_path: Path) -> None:
                 agent_name="modern-b",
                 cost_usd=0.10,
                 duration_seconds=1.0,
-                model="claude-opus-4-7",
+                model="claude-opus-4-8",
             ),
         ]
         _write_records(ledger_path, recs)
@@ -668,7 +668,7 @@ def test_legacy_empty_model_grouped_visible(self, ledger_path: Path) -> None:
         assert len(results) == 2
         models = {r.model for r in results}
         assert "" in models
-        assert "claude-opus-4-7" in models
+        assert "claude-opus-4-8" in models
 
     def test_dispatch_count_correct(self, ledger_path: Path) -> None:
         """Sage memo D8 — ``dispatch_count`` reflects the number of records
@@ -704,15 +704,15 @@ def test_total_duration_summed(self, ledger_path: Path) -> None:
                 agent_name="a",
                 cost_usd=0.01,
                 duration_seconds=12.5,
-                model="claude-opus-4-7",
+                model="claude-opus-4-8",
             ),
             DispatchRecord(
                 timestamp=2.0,
                 session_id="s",
                 agent_name="b",
                 cost_usd=0.02,
                 duration_seconds=7.5,
-                model="claude-opus-4-7",
+                model="claude-opus-4-8",
             ),
         ]
         _write_records(ledger_path, recs)
@@ -765,7 +765,7 @@ def test_pathological_corpus_groups_correctly_and_sorts(self, ledger_path: Path)
         spec'd dict-based group, it stays fast.
 
         Cost layout (deterministic):
-            claude-opus-4-7   -> 4000 records * 0.04 = 160.00
+            claude-opus-4-8   -> 4000 records * 0.04 = 160.00
             claude-sonnet-4-6 -> 3000 records * 0.03 =  90.00
             claude-haiku-4-5  -> 2000 records * 0.02 =  40.00
             claude-extra-1    ->  900 records * 0.05 =  45.00
@@ -778,7 +778,7 @@ def test_pathological_corpus_groups_correctly_and_sorts(self, ledger_path: Path)
 
         n_total = 10_000
         layout: list[tuple[str, int, float]] = [
-            ("claude-opus-4-7", 4000, 0.04),
+            ("claude-opus-4-8", 4000, 0.04),
             ("claude-sonnet-4-6", 3000, 0.03),
             ("claude-haiku-4-5", 2000, 0.02),
             ("claude-extra-1", 900, 0.05),
@@ -811,16 +811,16 @@ def test_pathological_corpus_groups_correctly_and_sorts(self, ledger_path: Path)
         # Descending by total_cost_usd.
         names = [m.model for m in results]
         assert names == [
-            "claude-opus-4-7",
+            "claude-opus-4-8",
             "claude-sonnet-4-6",
             "claude-extra-1",
             "claude-haiku-4-5",
             "claude-extra-2",
         ]
         # Spot-check totals.
         by_name = {m.model: m for m in results}
-        assert by_name["claude-opus-4-7"].total_cost_usd == pytest.approx(160.0)
-        assert by_name["claude-opus-4-7"].dispatch_count == 4000
+        assert by_name["claude-opus-4-8"].total_cost_usd == pytest.approx(160.0)
+        assert by_name["claude-opus-4-8"].dispatch_count == 4000
         assert by_name["claude-haiku-4-5"].total_cost_usd == pytest.approx(40.0)
         assert by_name["claude-extra-2"].dispatch_count == 100
 
@@ -855,7 +855,7 @@ def test_mixed_legacy_and_new_rows_round_trip(self, ledger_path: Path) -> None:
                 agent_name="a",
                 cost_usd=0.30,
                 duration_seconds=2.0,
-                model="claude-opus-4-7",
+                model="claude-opus-4-8",
             )
             new_b = DispatchRecord(
                 timestamp=5.0,
@@ -873,23 +873,23 @@ def test_mixed_legacy_and_new_rows_round_trip(self, ledger_path: Path) -> None:
 
         # Three buckets: "", opus, haiku.
         by_name = {m.model: m for m in results}
-        assert set(by_name) == {"", "claude-opus-4-7", "claude-haiku-4-5"}
+        assert set(by_name) == {"", "claude-opus-4-8", "claude-haiku-4-5"}
 
         # Legacy bucket is preserved as a visible "" key with summed cost.
         legacy = by_name[""]
         assert legacy.dispatch_count == 3
         assert legacy.total_cost_usd == pytest.approx(0.85)
 
         # New rows attributed to their model strings.
-        assert by_name["claude-opus-4-7"].dispatch_count == 1
-        assert by_name["claude-opus-4-7"].total_cost_usd == pytest.approx(0.30)
+        assert by_name["claude-opus-4-8"].dispatch_count == 1
+        assert by_name["claude-opus-4-8"].total_cost_usd == pytest.approx(0.30)
         assert by_name["claude-haiku-4-5"].dispatch_count == 1
         assert by_name["claude-haiku-4-5"].total_cost_usd == pytest.approx(0.20)
 
         # Sort descending by cost: legacy (0.85) > opus (0.30) > haiku (0.20).
         assert [m.model for m in results] == [
             "",
-            "claude-opus-4-7",
+            "claude-opus-4-8",
             "claude-haiku-4-5",
         ]
 

tests/unit/test_cost_analyzer_memoization.py

@@ -156,7 +156,7 @@ def test_cache_invalidates_when_ledger_modified(
             agent_name="warrior",
             cost_usd=0.50,
             duration_seconds=60.0,
-            model="claude-opus-4-7",
+            model="claude-opus-4-8",
         )
         _write_records(ledger_path, [*sample_records, new_record])
 
@@ -313,7 +313,7 @@ def test_same_mtime_inode_change_busts_cache(
             agent_name="sage",
             cost_usd=0.77,
             duration_seconds=42.0,
-            model="claude-opus-4-7",
+            model="claude-opus-4-8",
         )
         _write_records(replacement, [*sample_records, extra_record])
         os.replace(replacement, ledger_path)

tests/unit/test_cost_models.py

@@ -363,9 +363,9 @@ def test_dispatch_record_accepts_model(self) -> None:
             agent_name="a",
             cost_usd=0.0,
             duration_seconds=0.0,
-            model="claude-opus-4-7",
+            model="claude-opus-4-8",
         )
-        assert record.model == "claude-opus-4-7"
+        assert record.model == "claude-opus-4-8"
 
     def test_legacy_jsonl_row_without_model_loads(self) -> None:
         """Sage memo D5 — pre-BON-351 ledger rows omit ``model`` entirely.
@@ -397,12 +397,12 @@ class TestModelCost:
     def test_model_cost_construction(self) -> None:
         """Sage memo D5 — four required fields, all positional-by-name."""
         m = ModelCost(
-            model="claude-opus-4-7",
+            model="claude-opus-4-8",
             total_cost_usd=1.0,
             dispatch_count=3,
             total_duration_seconds=12.5,
         )
-        assert m.model == "claude-opus-4-7"
+        assert m.model == "claude-opus-4-8"
         assert m.total_cost_usd == 1.0
         assert m.dispatch_count == 3
         assert m.total_duration_seconds == 12.5

tests/unit/test_dispatch_options_role.py

@@ -159,13 +159,13 @@ def test_role_with_leading_slash_accepted(self) -> None:
     def test_role_paired_with_tools_and_model(self) -> None:
         """Sage D4 + D7 — role travels alongside tools and model."""
         opts = DispatchOptions(
-            model="claude-opus-4-7",
+            model="claude-opus-4-8",
             tools=["Read", "Write", "Edit", "Bash", "Grep", "Glob"],
             role="warrior",
         )
         assert opts.role == "warrior"
         assert opts.tools == ["Read", "Write", "Edit", "Bash", "Grep", "Glob"]
-        assert opts.model == "claude-opus-4-7"
+        assert opts.model == "claude-opus-4-8"
 
 
 # ===========================================================================

tests/unit/test_dispatch_pydantic_ai_backend.py

@@ -96,7 +96,7 @@ def test_import_from_module(self):
         assert _P is not None
 
     def test_construct_with_model_kwarg(self):
-        backend = PydanticAIBackend(model="claude-sonnet-4")
+        backend = PydanticAIBackend(model="claude-sonnet-4-6")
         assert backend is not None
 
     def test_construct_with_no_args(self):