feat(openai): forward prompt_cache_key for server-side prefix cache routing

internal/agent/loop.go

@@ -173,6 +173,7 @@
 			Messages:        copyMessages(messages),
 			Tools:           exposed,
 			ReasoningEffort: options.ReasoningEffort,
+			PromptCacheKey:  options.SessionID,
 		}
 
 		// Report the per-category context budget for this turn so a surface can
@@ -208,6 +209,7 @@
 					Messages:        copyMessages(messages),
 					Tools:           exposed,
 					ReasoningEffort: options.ReasoningEffort,
+					PromptCacheKey:  options.SessionID,
 				}
 				// Pre-content connect after a context-limit compaction: route through the
 				// reconnect helper so a transient upstream hiccup here doesn't fail the
@@ -268,6 +270,7 @@
 					Messages:        copyMessages(messages),
 					Tools:           exposed,
 					ReasoningEffort: options.ReasoningEffort,
+					PromptCacheKey:  options.SessionID,
 				}
 				retryStream, retryStreamErr := streamWithReconnect(ctx, provider, retryRequest, reconnectNoticeFor(options))
 				if retryStreamErr != nil {
@@ -326,6 +329,7 @@
 				Messages:        copyMessages(messages),
 				Tools:           exposed,
 				ReasoningEffort: options.ReasoningEffort,
+				PromptCacheKey:  options.SessionID,
 			}
 			retryStream, retryErr := streamWithReconnect(ctx, provider, retryRequest, reconnectNoticeFor(options))
 			if retryErr != nil {
@@ -705,6 +709,7 @@
 	stream, err := streamWithReconnect(ctx, provider, zeroruntime.CompletionRequest{
 		Messages:        copyMessages(finalMessages),
 		ReasoningEffort: options.ReasoningEffort,
+		PromptCacheKey:  options.SessionID,
 	}, reconnectNoticeFor(options))
 	if err != nil {
 		return "", messages, ""
@@ -2507,7 +2512,7 @@
 // through tool_search. Non-deferred tools (including tool_search) are always
 // exposed. The exposed slice is alpha-sorted by name, matching the legacy order
 // so the inactive path is stable.
 func partitionTools(registry *tools.Registry, permissionMode PermissionMode, options Options, loaded map[string]bool) ([]zeroruntime.ToolDefinition, string) {
 	return partitionToolsCached(registry, permissionMode, options, loaded, nil)
 }
 

internal/providers/openai/provider.go

@@ -9,6 +9,7 @@ import (
 	"io"
 	"net/http"
 	"net/url"
+	"os"
 	"strings"
 	"time"
 
@@ -421,6 +422,12 @@ func (provider *Provider) openAIRequest(request zeroruntime.CompletionRequest) c
 	if effort := openAIReasoningEffort(request.ReasoningEffort); effort != "" {
 		mapped.ReasoningEffort = effort
 	}
+	// prompt_cache_key is a documented OpenAI parameter; compatible servers
+	// ignore unknown fields, but a strict endpoint that rejects it can be
+	// accommodated with ZERO_DISABLE_PROMPT_CACHE_KEY=1.
+	if key := strings.TrimSpace(request.PromptCacheKey); key != "" && !promptCacheKeyDisabled() {
+		mapped.PromptCacheKey = key
+	}
 	if len(request.Tools) > 0 {
 		mapped.Tools = make([]toolDefinition, 0, len(request.Tools))
 		for _, tool := range request.Tools {
@@ -437,6 +444,15 @@ func (provider *Provider) openAIRequest(request zeroruntime.CompletionRequest) c
 	return mapped
 }
 
+// promptCacheKeyDisabled reports whether the ZERO_DISABLE_PROMPT_CACHE_KEY
+// kill switch is set to a truthy value. "0" and "false" (any case) are
+// no-ops, matching how ZERO_FORMAT_ON_WRITE parses boolean flags, so an
+// explicitly-disabled toggle never flips the behavior it names.
+func promptCacheKeyDisabled() bool {
+	value := strings.TrimSpace(os.Getenv("ZERO_DISABLE_PROMPT_CACHE_KEY"))
+	return value != "" && value != "0" && !strings.EqualFold(value, "false")
+}
+
 // openAIReasoningEffort normalizes a requested effort to a value the OpenAI chat
 // completions API accepts, or "" to omit the field. "none" (and anything else)
 // is dropped rather than risking a 400 on an unrecognized enum.

internal/providers/openai/provider_test.go

@@ -1259,3 +1259,61 @@ func TestOpenAIRequestEmptyContentHandling(t *testing.T) {
 		t.Fatalf("assistant tool calls dropped: %#v", req.Messages[1])
 	}
 }
+
+// TestOpenAIRequestPromptCacheKey locks in prompt_cache_key forwarding: a
+// session-carrying request serializes the key so the backend can route to a
+// replica holding the cached prefix, a keyless request omits the field
+// entirely (strict servers see byte-identical requests to before), and
+// ZERO_DISABLE_PROMPT_CACHE_KEY suppresses it for endpoints that reject it.
+func TestOpenAIRequestPromptCacheKey(t *testing.T) {
+	provider, err := New(Options{Model: "gpt-test"})
+	if err != nil {
+		t.Fatalf("New returned error: %v", err)
+	}
+	messages := []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "hi"}}
+
+	req := provider.openAIRequest(zeroruntime.CompletionRequest{
+		Messages:       messages,
+		PromptCacheKey: "sess_123",
+	})
+	if req.PromptCacheKey != "sess_123" {
+		t.Fatalf("PromptCacheKey = %q, want sess_123", req.PromptCacheKey)
+	}
+	data, err := json.Marshal(req)
+	if err != nil {
+		t.Fatalf("marshal: %v", err)
+	}
+	if !strings.Contains(string(data), `"prompt_cache_key":"sess_123"`) {
+		t.Fatalf("prompt_cache_key not serialized: %s", data)
+	}
+
+	req = provider.openAIRequest(zeroruntime.CompletionRequest{Messages: messages})
+	if data, err = json.Marshal(req); err != nil {
+		t.Fatalf("marshal: %v", err)
+	}
+	if strings.Contains(string(data), "prompt_cache_key") {
+		t.Fatalf("keyless request must omit prompt_cache_key: %s", data)
+	}
+
+	t.Setenv("ZERO_DISABLE_PROMPT_CACHE_KEY", "1")
+	req = provider.openAIRequest(zeroruntime.CompletionRequest{
+		Messages:       messages,
+		PromptCacheKey: "sess_123",
+	})
+	if req.PromptCacheKey != "" {
+		t.Fatalf("kill switch ignored; PromptCacheKey = %q", req.PromptCacheKey)
+	}
+
+	// Explicitly-falsy kill switch values must NOT disable forwarding — only
+	// truthy values flip the toggle (same parsing as ZERO_FORMAT_ON_WRITE).
+	for _, value := range []string{"0", "false", "FALSE"} {
+		t.Setenv("ZERO_DISABLE_PROMPT_CACHE_KEY", value)
+		req = provider.openAIRequest(zeroruntime.CompletionRequest{
+			Messages:       messages,
+			PromptCacheKey: "sess_123",
+		})
+		if req.PromptCacheKey != "sess_123" {
+			t.Fatalf("ZERO_DISABLE_PROMPT_CACHE_KEY=%q must be a no-op; PromptCacheKey = %q", value, req.PromptCacheKey)
+		}
+	}
+}

internal/providers/openai/types.go

@@ -8,6 +8,11 @@ type chatCompletionRequest struct {
 	ReasoningEffort     string           `json:"reasoning_effort,omitempty"`
 	Stream              bool             `json:"stream"`
 	StreamOptions       *streamOptions   `json:"stream_options,omitempty"`
+	// PromptCacheKey asks the backend to route the request to a replica that
+	// already holds this conversation's prefix in its prompt cache (the OpenAI
+	// `prompt_cache_key` parameter). Omitted when the caller carries no session
+	// identity or when ZERO_DISABLE_PROMPT_CACHE_KEY is set.
+	PromptCacheKey string `json:"prompt_cache_key,omitempty"`
 }
 
 // streamOptions requests the final usage chunk on a streaming response. Without

internal/zeroruntime/types.go

@@ -203,6 +203,13 @@ type CompletionRequest struct {
 	// Anthropic/Gemini thinking budgets) and ignores it for models that do not
 	// support reasoning. Empty means "let the provider decide".
 	ReasoningEffort string
+	// PromptCacheKey, when non-empty, is an opaque stable identifier for the
+	// conversation (the session ID). Providers with server-side prefix-cache
+	// routing forward it — OpenAI `prompt_cache_key` — so consecutive requests
+	// land on a replica that already holds the cached prompt prefix instead of
+	// re-billing the full prefix each turn. Providers without an equivalent
+	// ignore it.
+	PromptCacheKey string
 }
 
 // Provider streams normalized completion events for one request.