argus-code-review 0.2.8__tar.gz → 0.2.9__tar.gz

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/CHANGELOG.md

@@ -7,6 +7,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.9] - 2026-10-02
+
+### Changed
+
+- Upgraded frontier and default model aliases in `argus.llm.models` (TECH-7124, #31):
+  - `claude-frontier` and `claude-opus` upgraded to `claude-opus-5-5` (previously `claude-fable-5` and `claude-opus-5`).
+  - `claude-default` upgraded to `claude-sonnet-5-5` (previously `claude-sonnet-4-6`).
+  - `gpt-frontier` upgraded to `gpt-6.1-sol` (previously `gpt-5.6-sol`).
+- Updated model pricing rates in `argus.llm.models` for `claude-sonnet-5-5`, `claude-opus-5-5`, and `gpt-6.1-sol` (TECH-7124, #31).
+- Re-verified the Anthropic 1M context beta (`context-1m-2025-08-07`) against `claude-sonnet-5-5` via the Redesign Health Anthropic proxy (TECH-7124, #31).
+- Updated approved model policies in `pr-review-specialist-llm-patterns.md`, runner warning logs, bench defaults, and CLI help text for the new model aliases (TECH-7124, #31).
+
 ## [0.2.8] - 2026-10-02
 
 ### Changed
@@ -368,7 +380,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   packaged set.
 - `argus --version`, `argus prompts list`, and `argus prompts export`.
 
-[Unreleased]: https://github.com/redesignhealth/argus-review/compare/v0.2.8...HEAD
+[Unreleased]: https://github.com/redesignhealth/argus-review/compare/v0.2.9...HEAD
+[0.2.9]: https://github.com/redesignhealth/argus-review/compare/v0.2.8...v0.2.9
 [0.2.8]: https://github.com/redesignhealth/argus-review/compare/v0.2.7...v0.2.8
 [0.2.7]: https://github.com/redesignhealth/argus-review/compare/v0.2.6...v0.2.7
 [0.2.6]: https://github.com/redesignhealth/argus-review/compare/v0.2.5...v0.2.6

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: argus-code-review
-Version: 0.2.8
+Version: 0.2.9
 Summary: Self-orchestrated PR review agent using LangGraph + Claude Agent SDK
 Project-URL: Repository, https://github.com/redesignhealth/argus-review
 Project-URL: Issues, https://github.com/redesignhealth/argus-review/issues
@@ -204,8 +204,7 @@ argus review owner/repo --pr 123 --dismiss "B2 -- pre-existing, not from this PR
 
 # Override the reviewer models (or set ARGUS_SPECIALIST_MODEL/ARGUS_FRONTIER_MODEL instead).
 # --frontier-model controls both the planner/coverage tier AND the cross-cutting
-# reviewer -- claude-fable-5 here is already the planner/coverage default, but
-# it also moves cross-cutting OFF its cheaper claude-opus-5 default onto fable-5.
+# reviewer (defaults to claude-opus-5-5).
 # Cost note: --specialist-model here overrides the bulk reviewer path (system
 # reviewer, specialists, tests-and-docs) from its low-cost Gemini default onto
 # claude-sdk with the specified model, and also updates the writer and lite-review
@@ -214,7 +213,7 @@ argus review owner/repo --pr 123 --dismiss "B2 -- pre-existing, not from this PR
 # the 1M-context beta from that same highest-volume path, since the beta is
 # only verified against the unoverridden default (autocompact may thrash on
 # long reviews under this override -- see argus/runners.py for the tradeoff).
-argus review owner/repo --pr 123 --specialist-model claude-opus-5 --frontier-model claude-fable-5
+argus review owner/repo --pr 123 --specialist-model claude-opus-5-5 --frontier-model claude-opus-5-5
 
 # Clear an already-set ARGUS_SPECIALIST_MODEL/ARGUS_FRONTIER_MODEL for just this
 # run by passing an empty string -- useful when the env var is set globally

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/README.md

@@ -153,8 +153,7 @@ argus review owner/repo --pr 123 --dismiss "B2 -- pre-existing, not from this PR
 
 # Override the reviewer models (or set ARGUS_SPECIALIST_MODEL/ARGUS_FRONTIER_MODEL instead).
 # --frontier-model controls both the planner/coverage tier AND the cross-cutting
-# reviewer -- claude-fable-5 here is already the planner/coverage default, but
-# it also moves cross-cutting OFF its cheaper claude-opus-5 default onto fable-5.
+# reviewer (defaults to claude-opus-5-5).
 # Cost note: --specialist-model here overrides the bulk reviewer path (system
 # reviewer, specialists, tests-and-docs) from its low-cost Gemini default onto
 # claude-sdk with the specified model, and also updates the writer and lite-review
@@ -163,7 +162,7 @@ argus review owner/repo --pr 123 --dismiss "B2 -- pre-existing, not from this PR
 # the 1M-context beta from that same highest-volume path, since the beta is
 # only verified against the unoverridden default (autocompact may thrash on
 # long reviews under this override -- see argus/runners.py for the tradeoff).
-argus review owner/repo --pr 123 --specialist-model claude-opus-5 --frontier-model claude-fable-5
+argus review owner/repo --pr 123 --specialist-model claude-opus-5-5 --frontier-model claude-opus-5-5
 
 # Clear an already-set ARGUS_SPECIALIST_MODEL/ARGUS_FRONTIER_MODEL for just this
 # run by passing an empty string -- useful when the env var is set globally

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/argus/bench_default.toml

@@ -33,9 +33,7 @@ caching  = "auto"
 
 [roles.cross-cutting]
 platform    = "claude-sdk"
-# Opus, not frontier (Fable): matches argus.runners._CROSS_CUTTING_MODEL --
-# evals showed no measurable quality gain from frontier on this stage, at
-# ~2x the per-token cost.
+# Matches argus.runners._CROSS_CUTTING_MODEL (resolves to claude-opus-5-5).
 model       = "claude-opus"
 prompt_name = "pr-review-cross-cutting"
 caching     = "auto"

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/argus/cli.py

@@ -368,10 +368,7 @@ def _add_review_args(parser: argparse.ArgumentParser) -> None:
         default=_MODEL_OVERRIDE_UNSET,
         help=(
             "Override the model used by the planner, coverage check, and "
-            "cross-cutting reviewer (defaults: claude-fable-5 for the first "
-            "two, claude-opus-5 for cross-cutting -- note this one flag "
-            "collapses both onto the SAME model when set, moving "
-            "cross-cutting off its cheaper default; or ARGUS_FRONTIER_MODEL "
+            "cross-cutting reviewer (default: claude-opus-5-5, or ARGUS_FRONTIER_MODEL "
             "if already set in the environment). Same effect as setting "
             "ARGUS_FRONTIER_MODEL. Pass an empty string to clear an "
             "already-set ARGUS_FRONTIER_MODEL for this run."

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/argus/config.py

@@ -91,7 +91,7 @@ class Settings(BaseSettings):
         ARGUS_SPECIALIST_MODEL: Override the model used by the system
             reviewer, specialist reviewers, the writer, and the lite-review
             path (``argus.llm.models.CLAUDE_DEFAULT``, default
-            ``claude-sonnet-4-6``). Set via ``--specialist-model``; read
+            ``claude-sonnet-5-5``). Set via ``--specialist-model``; read
             directly from ``os.environ`` by ``argus.llm.models`` at import
             time and by ``argus.bench`` (where setting it forces bulk reviewers
             to claude-sdk with claude-default). Also read off a ``Settings``

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/argus/llm/models.py

@@ -13,9 +13,9 @@ gpt-5.5 was NOT on the approved model list (see
 gpt-5.4, with a regression-guard test
 (``test_gpt_frontier_pinned_to_approved_model`` in
 ``tests/test_llm_models.py``) added specifically to catch a repeat. The
-alias has since been bumped again, this time to ``gpt-5.6-sol`` -- unlike
-the gpt-5.5 attempt, the ``gpt-5.6`` family genuinely IS on the approved
-model list (the entire family is approved in
+alias has since been bumped again, this time to ``gpt-6.1-sol`` (TECH-7124) -- unlike
+the gpt-5.5 attempt, the ``gpt-6.1-sol`` model genuinely IS on the approved
+model list (the model is approved in
 ``pr-review-specialist-llm-patterns.md`` alongside this change), so this is
 not a repeat of that mistake. Any future bump of this alias must likewise
 confirm the target model is on the approved list -- and update the policy
@@ -48,11 +48,15 @@ Per-token model pricing is sourced centrally from ``argus.llm.pricing``
 
 Tier semantics:
     *frontier* -- best reasoning available in the family; slow / expensive.
-    *opus*     -- next tier down from frontier -- strong reasoning at roughly
-                  half frontier's per-token cost. Introduced for call sites
-                  (e.g. the cross-cutting reviewer) where evals showed no
-                  measurable quality gain from frontier, so the cost isn't
-                  justified.
+                  Under Claude 5.5, ``claude-frontier`` and ``claude-opus``
+                  intentionally share ``claude-opus-5-5``.
+    *opus*     -- historically the next tier down from frontier -- strong reasoning
+                  at roughly half frontier's per-token cost (e.g. Opus 5 vs Fable 5).
+                  Under Claude 5.5, ``claude-frontier`` and ``claude-opus``
+                  intentionally share ``claude-opus-5-5``, so the prior cost
+                  differentiation rationale no longer applies while preserving
+                  the distinct alias keys for call sites (e.g. the cross-cutting
+                  reviewer) and override compatibility.
     *default*  -- workhorse balance of cost and capability.
     *mini*     -- fast and cheap; suitable for high-volume, low-stakes calls.
 
@@ -63,9 +67,10 @@ Runtime overrides:
 
     ``ARGUS_FRONTIER_MODEL`` (``--frontier-model``) overrides both
     ``CLAUDE_FRONTIER`` (planner, coverage) and ``CLAUDE_OPUS``
-    (cross-cutting) -- there is a single frontier-tier knob at the CLI, even
-    though the two aliases keep independent defaults so cross-cutting still
-    runs on the cheaper Opus tier when no override is given.
+    (cross-cutting) -- there is a single frontier-tier knob at the CLI.
+    Under Claude 5.5, both aliases intentionally share the same default
+    (``claude-opus-5-5``), and setting ``ARGUS_FRONTIER_MODEL`` overrides both
+    onto the specified model.
 
     Both env vars must be set before this module is first imported --
     ``cli.py`` sets them from the CLI flags ahead of any deferred import of
@@ -82,21 +87,18 @@ from argus.llm.pricing import estimate_cost_usd
 logger = logging.getLogger(__name__)
 
 ALIAS_MAP: Final[dict[str, str]] = {
-    # OpenAI -- gpt-5.4 / gpt-5.6 families
-    # gpt-frontier is bumped to gpt-5.6-sol, and gpt-mini is bumped to
-    # gpt-5.6-luna, as the gpt-5.6 family is now on the approved model list
-    # (see pr-review-specialist-llm-patterns.md), whose Default column was
-    # updated to gpt-5.6-luna in the same change. gpt-5.5/gpt-5.5-mini
-    # remain NOT on the approved list -- do not bump either alias to them
-    # until the policy table is updated (see the module docstring above).
+    # OpenAI -- gpt-5.4 / gpt-5.6 / gpt-6 families
+    # gpt-frontier is bumped to gpt-6.1-sol (TECH-7124), and gpt-mini is bumped to
+    # gpt-5.6-luna, as both are on the approved model list
+    # (see pr-review-specialist-llm-patterns.md).
     # test_llm_models.py pins both of these exact values as a regression
     # guard.
-    "gpt-frontier": "gpt-5.6-sol",
+    "gpt-frontier": "gpt-6.1-sol",
     "gpt-mini": "gpt-5.6-luna",
     # Anthropic
-    "claude-frontier": "claude-fable-5",
-    "claude-opus": "claude-opus-5",
-    "claude-default": "claude-sonnet-4-6",
+    "claude-frontier": "claude-opus-5-5",
+    "claude-opus": "claude-opus-5-5",
+    "claude-default": "claude-sonnet-5-5",
     "claude-mini": "claude-haiku-4-5",
     # Google -- gemini-3 family. Real call site: argus.gemini_runner
     # (Track 3), dispatched via argus.bench's "gemini" platform.

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/argus/prompts/pr-review-specialist-llm-patterns.md

@@ -7,8 +7,8 @@ Only approved model families. Check model strings in code against this table:
 
 | Provider | Approved | Default |
 |----------|----------|---------|
-| Anthropic | claude-opus-4, claude-sonnet-4, claude-haiku-4 (use `CLAUDE_MINI`), claude-fable-5 (use `CLAUDE_FRONTIER`), claude-opus-5 (use `CLAUDE_OPUS`), claude-sonnet-4-6 (use `CLAUDE_DEFAULT`) families; claude-sonnet-5 (the previous `CLAUDE_DEFAULT` pin) remains valid as an explicit `ARGUS_SPECIALIST_MODEL`/`--specialist-model` override value, not as a new hardcoded default | claude-sonnet-4-6 |
-| OpenAI | gpt-5.4 family (gpt-5.4, gpt-5.4-mini) and gpt-5.6 family | gpt-5.6-luna |
+| Anthropic | claude-opus-4, claude-sonnet-4, claude-haiku-4 (use `CLAUDE_MINI`), claude-opus-5-5 (use `CLAUDE_FRONTIER` / `CLAUDE_OPUS`), claude-sonnet-5-5 (use `CLAUDE_DEFAULT`) families; legacy Claude models (claude-fable-5, claude-opus-5, claude-sonnet-4-6, claude-sonnet-5) remain valid only as explicit CLI/env runtime overrides (`ARGUS_SPECIALIST_MODEL`/`ARGUS_FRONTIER_MODEL` or `--specialist-model`/`--frontier-model`) for backward compatibility, not as new hardcoded defaults | claude-sonnet-5-5 |
+| OpenAI | gpt-5.4 family (gpt-5.4, gpt-5.4-mini), gpt-5.6 family, and gpt-6.1-sol (use `GPT_FRONTIER`) | gpt-5.6-luna |
 | Google | gemini-3 family | gemini-3.8-flash |
 
 Flag any use of: o3, o1, gpt-4 family, gpt-5-mini, claude-3/3.5 family, gemini-1.5/2.5 family.

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/argus/runners.py

@@ -85,8 +85,7 @@ logger = logging.getLogger(__name__)
 # ---------------------------------------------------------------------------
 
 _SYSTEM_REVIEWER_MODEL = CLAUDE_DEFAULT
-# Opus, not frontier (Fable): evals showed no measurable quality gain from
-# frontier on this stage, at ~2x the per-token cost.
+# Matches argus.bench_default.toml (resolves to claude-opus-5-5).
 _CROSS_CUTTING_MODEL = CLAUDE_OPUS
 # Whether the system reviewer's current model (following any
 # --specialist-model/ARGUS_SPECIALIST_MODEL override) still matches
@@ -97,19 +96,21 @@ _CROSS_CUTTING_MODEL = CLAUDE_OPUS
 # for why a string-equality gate can't be made sound once overrides exist.
 #
 # Caveat shared with argus/graph.py's _TEMPERATURE_UNSUPPORTED_MODELS
-# comment: the empirical verification below was run against whatever
-# ALIAS_MAP["claude-default"] resolved to on 2026-07-31 (claude-sonnet-5 at
-# the time), NOT specifically against claude-sonnet-4-6 (the pin as of this
-# comment, after this same diff's default bump). Gating on the alias means
-# the beta keeps applying across future pin bumps automatically, without a
-# fresh re-verification each time -- the alternative (pinning this gate to
-# the literal claude-sonnet-5 string instead) would have silently withheld
-# the beta from the system reviewer's new default entirely, reinstating the
-# TECH-4734 autocompact-thrashing problem for the common no-override case.
-# Tracking the alias was the deliberate tradeoff; re-verify the beta
-# empirically against the current pin whenever ALIAS_MAP["claude-default"]
-# moves, and correct this comment if a future pin ever fails the probe
-# described below.
+# comment: the empirical verification below was initially run against
+# ALIAS_MAP["claude-default"] on 2026-07-31 (claude-sonnet-5 at the time)
+# and was live re-verified for claude-sonnet-5-5 on 2026-10-02 via the RH
+# Anthropic proxy: POST /v1/messages with model claude-sonnet-5-5, header
+# `anthropic-beta: context-1m-2025-08-07`, max_tokens=16 returned HTTP 200,
+# message model claude-sonnet-5-5, stop_reason=end_turn, no error. Gating
+# on the alias means the beta keeps applying across future pin bumps
+# automatically, without a fresh re-verification each time -- the
+# alternative (pinning this gate to a literal model string instead)
+# would have silently withheld the beta from the system reviewer's new
+# default entirely, reinstating the TECH-4734 autocompact-thrashing problem
+# for the common no-override case. Tracking the alias was the deliberate
+# tradeoff; re-verify the beta empirically against the current pin whenever
+# ALIAS_MAP["claude-default"] moves, and correct this comment if a future
+# pin ever fails the probe described below.
 _SYSTEM_REVIEWER_UNOVERRIDDEN = _SYSTEM_REVIEWER_MODEL == ALIAS_MAP["claude-default"]
 
 # Logged once at import time, not per-session (an earlier per-call version
@@ -132,19 +133,19 @@ else:
         _SYSTEM_REVIEWER_MODEL,
     )
 
-# Same one-time-at-import treatment for the other silent-cost-shift this
-# override mechanism can cause: --frontier-model/ARGUS_FRONTIER_MODEL
+# Same one-time-at-import treatment for the model/default identity change
+# this override mechanism can cause: --frontier-model/ARGUS_FRONTIER_MODEL
 # repoints both CLAUDE_FRONTIER and CLAUDE_OPUS (see argus/llm/models.py),
 # so a frontier override picked for planning/coverage purposes also moves
-# the cross-cutting reviewer off its cheaper Opus default with no other
-# runtime signal that happened.
+# the cross-cutting reviewer off its separately named claude-opus
+# default with no other runtime signal that happened.
 if _CROSS_CUTTING_MODEL != ALIAS_MAP["claude-opus"]:
     logger.warning(
         "Cross-cutting reviewer moved off its default model %r onto %r due to "
         "ARGUS_FRONTIER_MODEL -- this env var/--frontier-model repoints both "
         "the frontier tier and the cross-cutting model together, so a "
         "frontier override for planning purposes also moves cross-cutting "
-        "off its cheaper Opus default.",
+        "off its separately named claude-opus alias.",
         ALIAS_MAP["claude-opus"],
         _CROSS_CUTTING_MODEL,
     )
@@ -1781,6 +1782,11 @@ async def _run_claude_session(
     # proxy's own header-allowlist (which lives in a different repo, rh-mcp's
     # main.py, and could drift independently of this comment).
     #
+    # Live re-verification on 2026-10-02 via RH Anthropic proxy: POST /v1/messages
+    # with model claude-sonnet-5-5, header `anthropic-beta: context-1m-2025-08-07`,
+    # max_tokens=16 returned HTTP 200, message model claude-sonnet-5-5,
+    # stop_reason=end_turn, no error.
+    #
     # Only applied for _SYSTEM_REVIEWER_MODEL (sonnet), not
     # _CROSS_CUTTING_MODEL (opus): sonnet reviewer sessions are the ones
     # observed thrashing at the ~155-180k fixed-prefix floor (TECH-4734

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/tests/test_bench.py

@@ -107,6 +107,7 @@ class TestPackagedDefaultResolutions:
     def test_cross_cutting_matches_packaged_default(self) -> None:
         entry = bench.resolve("cross-cutting")
         assert entry.platform == "claude-sdk"
+        assert entry.model == "claude-opus"
         assert resolve_alias(entry.model) == runners_module._CROSS_CUTTING_MODEL
         assert entry.prompt_name == "pr-review-cross-cutting"
 

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/tests/test_llm_models.py

@@ -11,7 +11,6 @@ import pytest
 
 from argus.llm.models import (
     ALIAS_MAP,
-    CLAUDE_DEFAULT,
     EXPERIMENTAL_MODELS,
     GEMINI_FRONTIER,
     GEMINI_MINI,
@@ -49,13 +48,31 @@ class TestPricingLookup:
             )
 
     def test_claude_default_pricing_rates(self) -> None:
-        """Regression guard: claude-sonnet-4-6 rates in litellm must match
-        expected rates ($3/$15/$0.30 per Mtok)."""
-        cost = get_token_cost(CLAUDE_DEFAULT)
+        """Regression guard: claude-sonnet-5-5 rates in litellm must match
+        expected rates ($2/$10/$0.20 per Mtok)."""
+        cost = get_token_cost(ALIAS_MAP["claude-default"])
         assert cost is not None
-        assert cost.input_cost_per_token == pytest.approx(3e-6)
-        assert cost.output_cost_per_token == pytest.approx(15e-6)
-        assert cost.cache_read_cost_per_token == pytest.approx(0.3e-6)
+        assert cost.input_cost_per_token == pytest.approx(2e-6)
+        assert cost.output_cost_per_token == pytest.approx(10e-6)
+        assert cost.cache_read_cost_per_token == pytest.approx(0.2e-6)
+
+    def test_claude_opus_5_5_pricing_rates(self) -> None:
+        """Regression guard: claude-opus-5-5 rates in litellm must match
+        expected rates ($4/$20/$0.20 per Mtok)."""
+        cost = get_token_cost(ALIAS_MAP["claude-opus"])
+        assert cost is not None
+        assert cost.input_cost_per_token == pytest.approx(4e-6)
+        assert cost.output_cost_per_token == pytest.approx(20e-6)
+        assert cost.cache_read_cost_per_token == pytest.approx(0.2e-6)
+
+    def test_gpt_frontier_pricing_rates(self) -> None:
+        """Regression guard: gpt-6.1-sol rates in litellm must match
+        expected rates ($2/$10/$0.10 per Mtok)."""
+        cost = get_token_cost(ALIAS_MAP["gpt-frontier"])
+        assert cost is not None
+        assert cost.input_cost_per_token == pytest.approx(2e-6)
+        assert cost.output_cost_per_token == pytest.approx(10e-6)
+        assert cost.cache_read_cost_per_token == pytest.approx(0.1e-6)
 
     def test_gemini_pricing_is_real_not_a_placeholder(self) -> None:
         """Gemini has a real, reachable runner (argus.gemini_runner) -- its
@@ -70,19 +87,21 @@ class TestPricingLookup:
 
 class TestEstimateCostUsd:
     def test_computes_expected_cost_for_claude_default(self) -> None:
-        cost = estimate_cost_usd(CLAUDE_DEFAULT, input_tokens=1_000_000, output_tokens=1_000_000)
-        assert cost == pytest.approx(3.00 + 15.00)
+        cost = estimate_cost_usd(
+            ALIAS_MAP["claude-default"], input_tokens=1_000_000, output_tokens=1_000_000
+        )
+        assert cost == pytest.approx(2.00 + 10.00)
 
     def test_cached_input_tokens_billed_separately_at_cache_read_rate(self) -> None:
         """cached_input_tokens is additive (billed at the cache-read rate),
         not a subset subtracted from input_tokens."""
         cost = estimate_cost_usd(
-            CLAUDE_DEFAULT,
+            ALIAS_MAP["claude-default"],
             input_tokens=1_000_000,
             output_tokens=0,
             cached_input_tokens=1_000_000,
         )
-        assert cost == pytest.approx(3.00 + 0.30)
+        assert cost == pytest.approx(2.00 + 0.20)
 
     def test_cache_creation_tokens_billed(self) -> None:
         """cache_creation_tokens is billed at the cache-creation rate."""
@@ -92,7 +111,7 @@ class TestEstimateCostUsd:
             output_tokens=0,
             cache_creation_tokens=1_000_000,
         )
-        assert cost == pytest.approx(3.75)
+        assert cost == pytest.approx(2.50)
 
     def test_zero_tokens_is_zero_cost(self) -> None:
         assert (
@@ -136,13 +155,28 @@ class TestEstimateCostUsd:
         """Regression guard for a round-1 Argus BLOCKING finding on this
         PR: gpt-frontier previously resolved to gpt-5.5, which was not on
         the approved model list and may not have been shipped by OpenAI
-        yet. The alias has since been legitimately re-bumped to gpt-5.6-sol
-        (the entire gpt-5.6 family is now on the approved model list -- see
+        yet. The alias has since been legitimately re-bumped to gpt-6.1-sol
+        (the gpt-6.1-sol model is on the approved model list -- see
         pr-review-specialist-llm-patterns.md). Pin the alias to that
         approved value so a future accidental re-bump to an unapproved
         model string is caught here instead of at review time."""
-        assert ALIAS_MAP["gpt-frontier"] == "gpt-5.6-sol"
-        assert GPT_FRONTIER == "gpt-5.6-sol"
+        assert ALIAS_MAP["gpt-frontier"] == "gpt-6.1-sol"
+        assert GPT_FRONTIER == "gpt-6.1-sol"
+
+    def test_claude_frontier_pinned_to_approved_model(self) -> None:
+        """Regression guard: claude-frontier must pin to claude-opus-5-5
+        under Claude 5.5 per TECH-7124."""
+        assert ALIAS_MAP["claude-frontier"] == "claude-opus-5-5"
+
+    def test_claude_opus_pinned_to_approved_model(self) -> None:
+        """Regression guard: claude-opus must pin to claude-opus-5-5
+        under Claude 5.5 per TECH-7124."""
+        assert ALIAS_MAP["claude-opus"] == "claude-opus-5-5"
+
+    def test_claude_default_pinned_to_approved_model(self) -> None:
+        """Regression guard: claude-default must pin to claude-sonnet-5-5
+        per TECH-7124."""
+        assert ALIAS_MAP["claude-default"] == "claude-sonnet-5-5"
 
     def test_gpt_mini_pinned_to_approved_model(self) -> None:
         """Parallel regression guard for gpt-mini, alongside gpt-frontier's

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/tests/test_llm_models_override.py

@@ -44,10 +44,22 @@ def _reload_after_test() -> Iterator[None]:
     importlib.reload(models)
 
 
-def test_claude_default_is_sonnet_4_6_when_unset(monkeypatch: pytest.MonkeyPatch) -> None:
+def test_claude_default_is_sonnet_5_5_when_unset(monkeypatch: pytest.MonkeyPatch) -> None:
     monkeypatch.delenv("ARGUS_SPECIALIST_MODEL", raising=False)
     importlib.reload(models)
-    assert models.CLAUDE_DEFAULT == "claude-sonnet-4-6"
+    assert models.CLAUDE_DEFAULT == "claude-sonnet-5-5"
+
+
+def test_claude_frontier_is_opus_5_5_when_unset(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.delenv("ARGUS_FRONTIER_MODEL", raising=False)
+    importlib.reload(models)
+    assert models.CLAUDE_FRONTIER == "claude-opus-5-5"
+
+
+def test_claude_opus_is_opus_5_5_when_unset(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.delenv("ARGUS_FRONTIER_MODEL", raising=False)
+    importlib.reload(models)
+    assert models.CLAUDE_OPUS == "claude-opus-5-5"
 
 
 def test_specialist_override_only_affects_claude_default(monkeypatch: pytest.MonkeyPatch) -> None:

{argus_code_review-0.2.8 → argus_code_review-0.2.9}/tests/test_runners_context_usage.py

@@ -724,8 +724,10 @@ class TestOneTimeImportLogs:
                 importlib.reload(runners_module)
             assert any(
                 "Cross-cutting reviewer moved off its default model" in record.message
+                and "off its separately named claude-opus alias" in record.message
                 for record in caplog.records
             )
+            assert not any("cheaper Opus default" in record.message for record in caplog.records)
         finally:
             monkeypatch.delenv("ARGUS_FRONTIER_MODEL", raising=False)
             importlib.reload(models_module)