fix(agent): exempt parseable vLLM/LM Studio output-cap errors from compression-disabled guard

Salvage of #63862. is_output_cap_error() returns False for vLLM/LM Studio
error messages that contain 'prompt contains ... input tokens' (treated as
input-overflow signal). But parse_available_output_tokens_from_error() CAN
extract a valid available_tokens from those same messages. The
compression-disabled guard only checked is_output_cap_error(), so vLLM/LM
Studio users with compression off still got a terminal failure instead of
the max-tokens retry.

Fix: also exempt when parse_available_output_tokens_from_error() returns a
value — that function determines whether the retry path can actually handle
the error, so it's the right predicate for the exemption.

Added test: verify vLLM-format error with compression_disabled=False still
triggers the max-tokens retry path.

Co-authored-by: dmabry <dmabry@users.noreply.github.com>

agent/conversation_loop.py

@@ -3071,7 +3071,10 @@ def run_conversation(
                     FailoverReason.payload_too_large,
                     FailoverReason.context_overflow,
                 }
-                _is_output_cap_error = is_output_cap_error(error_msg)
+                _is_output_cap_error = (
+                    is_output_cap_error(error_msg)
+                    or parse_available_output_tokens_from_error(error_msg) is not None
+                )
                 if (
                     classified.reason in _overflow_reasons
                     and not getattr(agent, "compression_enabled", True)

scripts/release.py

@@ -138,6 +138,7 @@ AUTHOR_MAP = {
     "259353979+testingbuddies24@users.noreply.github.com": "testingbuddies24",  # PR #43192 salvage (strip orphan think-tag close tags in progressive gateway stream so a bare </think> whose open was dropped upstream can't leak to the user)
     "shx_929@163.com": "Lazymonter",  # PR #42914 salvage (retry launchd bootstrap after bootout on EIO for install/start instead of degrading to detached)
     "96322396+WXBR@users.noreply.github.com": "WXBR",  # PR #46183 salvage (persist recovered final_response at the finalize_turn chokepoint so recovery-path breaks don't drop the delivered assistant row)
+    "dmabry@sparky.fabe-gray.ts.net": "dmabry",  # PR #63862 salvage (output-cap retry: use provider available_tokens + request estimate; exempt parseable vLLM/LM Studio errors from compression-disabled guard)
     "sahil.rakhaiya117814@marwadiuniversity.ac.in": "SahilRakhaiya05",  # PR #44073 salvage (fail-closed gateway/external-surface hardening: own-policy defaults, open-policy startup guard, profile-aware multiplex authz, API-server auth, execute_code per-session RPC token)
     "5848605+itenev@users.noreply.github.com": "itenev",  # PR #22753 salvage (asyncify model-context resolution in gateway message path so blocking requests.get can't starve Discord heartbeats)
     "arthur.zhang@ingenico.com": "arthurzhang",  # PR #34718 salvage (redact Slack App-Level xapp- tokens in agent/redact.py + gateway/run.py)

tests/run_agent/test_run_agent.py

@@ -5580,6 +5580,56 @@ class TestRunConversation:
         assert agent.context_compressor.context_length == 200_000
         mock_compress.assert_not_called()
 
+    def test_output_cap_retry_with_compression_disabled_vllm_format(self, agent):
+        """vLLM/LM Studio error messages contain 'prompt contains ... input
+        tokens' which is_output_cap_error() treats as an input-overflow signal
+        (returns False).  But parse_available_output_tokens_from_error() CAN
+        extract a valid available_tokens from them.  The compression-disabled
+        guard must exempt these too — otherwise users on vLLM/LM Studio with
+        compression off get a terminal failure instead of a max-tokens retry.
+        """
+        self._setup_agent(agent)
+        agent.api_mode = "chat_completions"
+        agent.provider = "openrouter"
+        agent.model = "some/model"
+        agent.max_tokens = 65_536
+        agent.compression_enabled = False
+        agent.context_compressor.context_length = 131_072
+        agent.context_compressor.should_compress = MagicMock(return_value=False)
+
+        # vLLM-format error (from tests/test_output_cap_parsing.py)
+        error_msg = (
+            "This model's maximum context length is 131072 tokens. "
+            "However, you requested 1024 output tokens and your prompt "
+            "contains at least 65537 input tokens, for a total of at least "
+            "66561 tokens."
+        )
+        exc = Exception(error_msg)
+        exc.status_code = 400
+        exc.code = 400
+
+        ok_resp = _mock_response(content="done", finish_reason="stop")
+        agent.client.chat.completions.create.side_effect = [exc, ok_resp]
+
+        mock_compress = MagicMock()
+        with (
+            patch.object(agent, "_persist_session"),
+            patch.object(agent, "_save_trajectory"),
+            patch.object(agent, "_cleanup_task_resources"),
+            patch.object(agent.context_compressor, "update_model"),
+            patch.object(agent, "_compress_context", mock_compress),
+        ):
+            result = agent.run_conversation("hello")
+
+        assert len(agent.client.chat.completions.create.call_args_list) == 2
+        second_call = agent.client.chat.completions.create.call_args_list[1].kwargs
+        assert result["completed"] is True
+        assert result.get("compaction_disabled") is None
+        # parse_available_output_tokens_from_error returns 65535 for this message
+        assert second_call["max_tokens"] <= 65471  # 65535 - 64
+        assert agent.context_compressor.context_length == 131_072
+        mock_compress.assert_not_called()
+
 
 class TestHookPayloadSanitizesSimpleNamespace:
     """Regression: ``_hook_jsonable`` referenced ``SimpleNamespace`` without