diff --git a/workspace-server/internal/handlers/a2a_proxy.go b/workspace-server/internal/handlers/a2a_proxy.go index 97296d4f..816d5c81 100644 --- a/workspace-server/internal/handlers/a2a_proxy.go +++ b/workspace-server/internal/handlers/a2a_proxy.go @@ -21,6 +21,7 @@ import ( "time" "github.com/Molecule-AI/molecule-monorepo/platform/internal/db" + "github.com/Molecule-AI/molecule-monorepo/platform/internal/envx" "github.com/Molecule-AI/molecule-monorepo/platform/internal/events" "github.com/Molecule-AI/molecule-monorepo/platform/internal/models" "github.com/Molecule-AI/molecule-monorepo/platform/internal/provisioner" @@ -110,11 +111,14 @@ const maxProxyResponseBody = 10 << 20 // a generic 502 page to canvas. 10s is well above realistic intra-region // latencies and well below CF's edge timeout. // -// 3. Transport.ResponseHeaderTimeout — 60s. From request-body-end to -// response-headers-start. Covers cold-start first-byte (the 30-60s OAuth -// flow above), with margin. Body streaming after headers is governed by -// the per-request context deadline, NOT this timeout — so multi-minute -// agent responses still work fine. +// 3. Transport.ResponseHeaderTimeout — 180s default. From request-body-end +// to response-headers-start. Configurable via +// A2A_PROXY_RESPONSE_HEADER_TIMEOUT (envx.Duration). Covers cold-start +// first-byte (30-60s OAuth flow above) with enough room for Opus agent +// turns (big context + internal delegate_task round-trips routinely exceed +// the old 60s ceiling). Body streaming after headers is governed by the +// per-request context deadline, NOT this timeout — so multi-minute agent +// responses still work fine. // // The point of (2) and (3) is to surface a *structured* 503 from // handleA2ADispatchError when the workspace agent is unreachable, so canvas @@ -127,7 +131,7 @@ var a2aClient = &http.Client{ Timeout: 10 * time.Second, KeepAlive: 30 * time.Second, }).DialContext, - ResponseHeaderTimeout: 60 * time.Second, + ResponseHeaderTimeout: envx.Duration("A2A_PROXY_RESPONSE_HEADER_TIMEOUT", 180*time.Second), TLSHandshakeTimeout: 10 * time.Second, // MaxIdleConns / IdleConnTimeout: stdlib defaults are fine; agent // fan-in is bounded by the platform's broadcaster fan-out, not by diff --git a/workspace-server/internal/handlers/a2a_proxy_test.go b/workspace-server/internal/handlers/a2a_proxy_test.go index ceab1b7c..7fa22dac 100644 --- a/workspace-server/internal/handlers/a2a_proxy_test.go +++ b/workspace-server/internal/handlers/a2a_proxy_test.go @@ -2276,3 +2276,43 @@ func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) { t.Errorf("unmet sqlmock expectations: %v", err) } } + +// ==================== a2aClient ResponseHeaderTimeout config ==================== + +func TestA2AClientResponseHeaderTimeout(t *testing.T) { + const defaultTimeout = 180 * time.Second + + // Default (unset env) — a2aClient was initialised at package load time. + if a2aClient.Transport.(*http.Transport).ResponseHeaderTimeout != defaultTimeout { + t.Errorf("a2aClient default ResponseHeaderTimeout = %v, want %v", + a2aClient.Transport.(*http.Transport).ResponseHeaderTimeout, defaultTimeout) + } + + // Env var override — verify parsing logic inline since a2aClient is + // initialised once at package load (env already consumed at import time). + t.Run("A2A_PROXY_RESPONSE_HEADER_TIMEOUT parsed correctly", func(t *testing.T) { + // We can't re-initialise a2aClient, but we can verify the same + // envx.Duration logic inline for the 5m override case. + t.Setenv("A2A_PROXY_RESPONSE_HEADER_TIMEOUT", "5m") + if d, err := time.ParseDuration("5m"); err == nil && d > 0 { + if d != 5*time.Minute { + t.Errorf("ParseDuration(\"5m\") = %v, want 5m", d) + } + } + }) + + t.Run("invalid A2A_PROXY_RESPONSE_HEADER_TIMEOUT falls back to default", func(t *testing.T) { + t.Setenv("A2A_PROXY_RESPONSE_HEADER_TIMEOUT", "not-a-duration") + // Simulate what envx.Duration does with an invalid value. + var fallback = 180 * time.Second + override := fallback + if v := os.Getenv("A2A_PROXY_RESPONSE_HEADER_TIMEOUT"); v != "" { + if d, err := time.ParseDuration(v); err == nil && d > 0 { + override = d + } + } + if override != fallback { + t.Errorf("invalid env var: got %v, want fallback %v", override, fallback) + } + }) +}