Merge 8a7e96ef6c into d30e3e052d

headroom/cli/proxy.py

@@ -418,6 +418,18 @@ def dashboard(port: int, no_open: bool) -> None:
         "Env: HEADROOM_NO_CCR_PROACTIVE_EXPANSION."
     ),
 )
+@click.option(
+    "--no-ccr-response-handling",
+    is_flag=True,
+    envvar="HEADROOM_NO_CCR_RESPONSE_HANDLING",
+    help=(
+        "Disable server-side buffering of streaming responses for CCR response "
+        "handling, independent of --no-ccr. A client that offers the "
+        "headroom_retrieve tool itself (e.g. the bundled OpenCode plugin) "
+        "otherwise always takes the buffered-stream path with no opt-out "
+        "(issue #3082). Env: HEADROOM_NO_CCR_RESPONSE_HANDLING."
+    ),
+)
 @click.option(
     "--proxy-extension",
     "proxy_extension",
@@ -1033,6 +1045,7 @@ def proxy(
     lossless: bool,
     ccr_inline_resolve: bool,
     no_ccr_proactive_expansion: bool,
+    no_ccr_response_handling: bool,
     proxy_extension: tuple[str, ...],
     compressor: tuple[str, ...],
     no_subscription_tracking: bool,
@@ -1349,6 +1362,10 @@ def proxy(
         ccr_resolve_markers_inline=ccr_inline_resolve,
         lossless=lossless,
         ccr_proactive_expansion=not no_ccr_proactive_expansion,
+        # Independent of --no-ccr: a client can offer headroom_retrieve itself
+        # (see the --no-ccr-response-handling help text), which unconditionally
+        # takes the buffered-stream path with no other opt-out (issue #3082).
+        ccr_handle_responses=not no_ccr_response_handling,
         # Flatten repeat-flag tuple AND any comma-separated values inside it.
         # `--proxy-extension a,b --proxy-extension c` and `HEADROOM_PROXY_EXTENSIONS=a,b,c`
         # both yield ["a", "b", "c"]. None when nothing was supplied.

tests/test_cli_proxy_env.py

@@ -960,6 +960,89 @@ class TestCLICompressionOnlyFlags:
         assert cfg.ccr_inject_tool is False
 
 
+class TestCLINoCcrResponseHandlingFlag:
+    """--no-ccr-response-handling / HEADROOM_NO_CCR_RESPONSE_HANDLING must flip
+    ccr_handle_responses, independent of --no-ccr (issue #3082).
+
+    Before this flag existed, ccr_handle_responses had no CLI/env wiring at
+    all — a client that offers the headroom_retrieve tool itself (e.g. the
+    bundled OpenCode plugin) always took the buffered-stream path with no
+    supported opt-out, even with --no-ccr set.
+    """
+
+    def test_ccr_handle_responses_defaults_on(self, runner):
+        """Without the flag, ccr_handle_responses stays enabled (no behavior change)."""
+        captured_config = {}
+
+        def mock_run_server(config, **kwargs):
+            captured_config["config"] = config
+
+        with patch("headroom.proxy.server.run_server", mock_run_server):
+            result = runner.invoke(main, ["proxy"], catch_exceptions=False)
+
+        assert result.exit_code == 0, result.output
+        assert captured_config["config"].ccr_handle_responses is True
+
+    def test_no_ccr_response_handling_flag(self, runner):
+        """--no-ccr-response-handling disables ccr_handle_responses only."""
+        captured_config = {}
+
+        def mock_run_server(config, **kwargs):
+            captured_config["config"] = config
+
+        with patch("headroom.proxy.server.run_server", mock_run_server):
+            result = runner.invoke(
+                main, ["proxy", "--no-ccr-response-handling"], catch_exceptions=False
+            )
+
+        assert result.exit_code == 0, result.output
+        cfg = captured_config["config"]
+        assert cfg.ccr_handle_responses is False
+        # Unrelated CCR knobs stay on: this flag is independent of --no-ccr.
+        assert cfg.ccr_inject_tool is True
+        assert cfg.ccr_inject_marker is True
+
+    def test_no_ccr_response_handling_from_env(self, runner):
+        """HEADROOM_NO_CCR_RESPONSE_HANDLING env var disables ccr_handle_responses."""
+        captured_config = {}
+
+        def mock_run_server(config, **kwargs):
+            captured_config["config"] = config
+
+        with patch("headroom.proxy.server.run_server", mock_run_server):
+            result = runner.invoke(
+                main,
+                ["proxy"],
+                env={"HEADROOM_NO_CCR_RESPONSE_HANDLING": "1"},
+                catch_exceptions=False,
+            )
+
+        assert result.exit_code == 0, result.output
+        assert captured_config["config"].ccr_handle_responses is False
+
+    def test_no_ccr_response_handling_combines_with_no_ccr(self, runner):
+        """--no-ccr-response-handling composes with --no-ccr instead of being
+        implied by it: both can be set together for a fully unbuffered,
+        no-retrieval-path configuration."""
+        captured_config = {}
+
+        def mock_run_server(config, **kwargs):
+            captured_config["config"] = config
+
+        with patch("headroom.proxy.server.run_server", mock_run_server):
+            result = runner.invoke(
+                main,
+                ["proxy", "--no-ccr", "--no-ccr-response-handling"],
+                catch_exceptions=False,
+            )
+
+        assert result.exit_code == 0, result.output
+        cfg = captured_config["config"]
+        assert cfg.ccr_inject_tool is False
+        assert cfg.ccr_inject_marker is False
+        assert cfg.ccr_handle_responses is False
+
+
 class TestNoCcrMarkerCompressors:
     """Verify --no-ccr actually suppresses <<ccr:...>> markers
     from every compressor, not just SmartCrusher (#1022)."""