release: v0.1.8

Since v0.1.7 — chat-completions dialect correctness (Pi-referenced):
- fix(chat): BYOK/custom endpoints default to Passthrough (vanilla
  OpenAI semantics; Kimi body mutations no longer leak to third-party
  servers); house/Kimi coding endpoints keep the Kimi dialect via
  base-url detection
- fix(chat): dedicated Mistral dialect — exactly-nine-alphanumeric
  tool-call id normalizer (deterministic, call/result-symmetric)
- fix(chat): tool-result images relocate to a batched user message
  (tool messages are text-only on the OpenAI chat wire)
- docs: AGENTS.md records the dialect-selection contract

AGENTS.md

@@ -228,6 +228,37 @@ edges stay deterministic Rust. The harness appends a terminal
       results); everything else — unsigned cross-backend history, `tco_*`
       Responses blobs, stale-model blocks — is stripped, or the request
       400s "Invalid `signature` in `thinking` block".
+- CROSS-PROVIDER REPLAY POLICY (Pi `transform-messages` pattern): the
+  conversation history is provider-agnostic and sessions switch
+  models/backends mid-history, so EACH wire builder owns emitting only
+  items valid for its target — never patch downstream except in the
+  per-backend body adapters. Concretely: the Responses input drops
+  Reasoning items without a native `rs_*` id (foreign capture is id "")
+  and provenance-gates whole turns via `transform_items_for_responses`
+  (`AssistantItem.model_id` vs the request model: foreign Reasoning
+  dropped, foreign BackendToolCall demoted to its `text_summary`);
+  the codex adapter additionally drops bare `rs_*` references (stateless
+  backend); tool-call ids pass through ONE shared ASCII
+  `sanitize_tool_call_id` symmetrically on call+result on BOTH the
+  Messages and Responses legs; Messages image sources go through
+  `parse_base64_image_data_uri` (raster whitelist, no `data:` url
+  sources) and empty user turns get a placeholder. Dangling tool calls
+  are already repaired item-level by `repair_dangling_tool_calls` on the
+  actor's build path. When a provider wire bug surfaces, fix the CLASS
+  across all three builders in the same pass — three sequential
+  single-provider fixes (thinking signature → codex system role → codex
+  reasoning id) motivated this policy.
+- ChatCompletions dialect selection: registry platforms declare
+  `chat_compat` explicitly; BYOK/custom entries default to `Passthrough`
+  (vanilla OpenAI semantics) EXCEPT entries pointed at the house/Kimi
+  coding endpoint, which keep the `Kimi` dialect (base-url detection —
+  Pi-style quirk sniffing). `ChatCompat::Mistral` = StrictOpenAi plus the
+  exactly-nine-`[a-zA-Z0-9]` tool-call id normalizer
+  (`normalize_mistral_tool_call_ids`, deterministic FNV-1a→base36, one
+  map for call+result; persisted `mistral` values resolve here). Chat
+  tool messages are TEXT-ONLY: tool-result images batch into one
+  synthetic user message after the consecutive tool-result run
+  (`conversation_to_chat_messages`).
     - `openai-codex` (ChatGPT Plus/Pro, `scope_key oauth/openai-codex`, port
       1455 `/auth/callback`, FORM body, authorize+token host `auth.openai.com`,
       client `app_EMoam…`, scope `openid profile email offline_access`, the 3

Cargo.lock

@@ -5442,7 +5442,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-acp-lib"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "agent-client-protocol",
  "async-trait",
@@ -5456,7 +5456,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-agent"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "chrono",
  "dirs 6.0.0",
@@ -5486,7 +5486,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-agent-lifecycle"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "async-trait",
  "tokio",
@@ -5495,7 +5495,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-auth"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "async-trait",
  "http 1.4.2",
@@ -5508,7 +5508,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-bin"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "clap",
@@ -5543,7 +5543,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-chat-state"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "indexmap",
  "kigi-compaction",
@@ -5560,7 +5560,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-codebase-graph"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "ahash",
  "clap",
@@ -5596,7 +5596,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-compaction"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -5609,7 +5609,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-config"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "base64",
  "blake3",
@@ -5632,7 +5632,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-config-types"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "agent-client-protocol",
  "indexmap",
@@ -5646,7 +5646,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-crash-handler"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "backtrace",
  "libc",
@@ -5657,7 +5657,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-env"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "tracing",
  "url",
@@ -5665,7 +5665,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-fast-worktree"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "bytes",
@@ -5697,7 +5697,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-file-utils"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "aws-config",
@@ -5721,7 +5721,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-fsnotify"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "criterion",
  "dunce",
@@ -5742,7 +5742,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-gix-status"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "gix",
  "kigi-test-utils",
@@ -5752,7 +5752,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-hooks"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "fastrand",
  "kigi-config",
@@ -5771,7 +5771,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-hooks-plugins-types"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "serde",
  "serde_json",
@@ -5779,7 +5779,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-http"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "kigi-auth",
  "kigi-log",
@@ -5794,7 +5794,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-hunk-tracker"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "chrono",
  "dunce",
@@ -5815,14 +5815,14 @@ dependencies = [
 
 [[package]]
 name = "kigi-interjection-core"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "serde",
 ]
 
 [[package]]
 name = "kigi-log"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "chrono",
@@ -5840,7 +5840,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-markdown"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anstyle",
  "anstyle-lossy",
@@ -5864,14 +5864,14 @@ dependencies = [
 
 [[package]]
 name = "kigi-markdown-core"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "pulldown-cmark",
 ]
 
 [[package]]
 name = "kigi-mcp"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "agent-client-protocol",
  "async-trait",
@@ -5908,7 +5908,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-memory"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "arc-swap",
@@ -5942,7 +5942,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-mermaid"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "fontdb",
  "image",
@@ -5960,7 +5960,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-models"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "kigi-env",
  "serde",
@@ -5970,7 +5970,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-pager-minimal"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "chrono",
  "crossterm",
@@ -5987,7 +5987,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-pager-pty-harness"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "alacritty_terminal",
  "anyhow",
@@ -6012,7 +6012,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-pager-render"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "agent-client-protocol",
  "anstyle",
@@ -6064,7 +6064,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-paths"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "camino",
  "serde",
@@ -6074,7 +6074,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-prompt-queue"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "serde",
  "serde_json",
@@ -6082,7 +6082,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-proto-build"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "pbjson-build",
@@ -6093,7 +6093,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-ratatui-inline"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "ansi-width",
  "anstyle-parse 0.2.7",
@@ -6110,7 +6110,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-ratatui-textarea"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "arboard",
  "chrono",
@@ -6131,7 +6131,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-sampler"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "async-openai",
  "async-stream",
@@ -6154,7 +6154,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-sampling-types"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "assert_matches",
  "async-openai",
@@ -6171,7 +6171,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-sandbox"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "chrono",
@@ -6192,7 +6192,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-secrets"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "regex",
  "serde_json",
@@ -6230,7 +6230,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-shell"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "agent-client-protocol",
  "anyhow",
@@ -6367,7 +6367,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-shell-base"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "chrono",
@@ -6392,7 +6392,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-sqlite-journal"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "libc",
  "rusqlite",
@@ -6403,7 +6403,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-subagent-resolution"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "kigi-sampling-types",
  "kigi-tool-types",
@@ -6418,7 +6418,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-system-power"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "windows-sys 0.59.0",
  "zbus",
@@ -6426,7 +6426,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-test-support"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "agent-client-protocol",
  "anyhow",
@@ -6448,7 +6448,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-test-utils"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "runfiles",
  "tracing",
@@ -6457,11 +6457,11 @@ dependencies = [
 
 [[package]]
 name = "kigi-token-estimation"
-version = "0.1.6"
+version = "0.1.8"
 
 [[package]]
 name = "kigi-tool-protocol"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "kigi-tool-types",
  "serde",
@@ -6472,7 +6472,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-tool-runtime"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -6490,7 +6490,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-tool-types"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "minijinja",
  "schemars 1.2.1",
@@ -6500,7 +6500,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-tools"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "arc-swap",
@@ -6577,7 +6577,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-tools-api"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "kigi-proto-build",
  "kigi-tool-protocol",
@@ -6590,11 +6590,11 @@ dependencies = [
 
 [[package]]
 name = "kigi-tracing-macros"
-version = "0.1.6"
+version = "0.1.8"
 
 [[package]]
 name = "kigi-tty-utils"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "libc",
  "nix 0.30.1",
@@ -6604,7 +6604,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-tui"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "agent-client-protocol",
  "ansi-to-tui",
@@ -6691,7 +6691,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-update"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "dunce",
@@ -6720,14 +6720,14 @@ dependencies = [
 
 [[package]]
 name = "kigi-version"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "semver",
 ]
 
 [[package]]
 name = "kigi-workspace"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "agent-client-protocol",
  "anyhow",
@@ -6806,7 +6806,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-workspace-types"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "base64",
  "chrono",
@@ -8840,7 +8840,7 @@ dependencies = [
 
 [[package]]
 name = "ptyctl"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "alacritty_terminal",
  "anyhow",
@@ -8858,7 +8858,7 @@ dependencies = [
 
 [[package]]
 name = "ptyctl-cli"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "anyhow",
  "axum",

Cargo.toml

@@ -76,7 +76,7 @@ members = [
 ]
 
 [workspace.package]
-version = "0.1.6"
+version = "0.1.8"
 edition = "2024"
 license = "Apache-2.0"
 

crates/codegen/kigi-models/src/lib.rs

@@ -70,9 +70,12 @@ pub enum PlatformChatCompat {
     Kimi,
     DeepSeek,
     Passthrough,
-    /// Strict OpenAI-compatible validator (Mistral, Cerebras) — strips
+    /// Strict OpenAI-compatible validator (Cerebras, NVIDIA) — strips
     /// `stream_options` and private fields.
     StrictOpenAi,
+    /// Mistral: StrictOpenAi plus its exactly-9-alphanumeric tool-call id
+    /// contract (foreign/OpenAI-style ids are deterministically remapped).
+    Mistral,
 }
 
 /// How a platform's API key rides requests (listing, validation, inference).
@@ -599,10 +602,12 @@ const MISTRAL_SPEC: PlatformSpec = PlatformSpec {
     wire_serves_metadata: false,
     wire_api: PlatformWireApi::ChatCompletions,
     listing: ListingDialect::OpenAi,
-    // Mistral's strict validator 422s on `stream_options`, and its reasoning
-    // models return array content — the StrictOpenAi dialect strips
-    // stream_options; the response deserializer handles arrays universally.
-    chat_compat: PlatformChatCompat::StrictOpenAi,
+    // Mistral's strict validator 422s on `stream_options`, its reasoning
+    // models return array content, and tool-call ids must be EXACTLY nine
+    // `[a-zA-Z0-9]` chars — the Mistral dialect strips stream_options and
+    // deterministically remaps non-conforming (foreign/OpenAI-style) ids;
+    // the response deserializer handles arrays universally.
+    chat_compat: PlatformChatCompat::Mistral,
     key_header: PlatformKeyHeader::Bearer,
     // The listing carries embed/moderation/OCR entries; keep tool-calling
     // chat models only.

crates/codegen/kigi-sampler/src/kimi_compat.rs

@@ -51,6 +51,91 @@ pub(crate) fn adapt_chat_completions_body_for(
             strip_kigi_private_message_fields(body);
             strip_stream_options(body);
         }
+        kigi_sampling_types::ChatCompat::Mistral => {
+            strip_kigi_private_message_fields(body);
+            strip_stream_options(body);
+            normalize_mistral_tool_call_ids(body);
+        }
+    }
+}
+
+/// Mistral's validator requires tool-call ids of EXACTLY nine
+/// `[a-zA-Z0-9]` characters. Foreign backends mint arbitrary ids
+/// (OpenAI `call_…`, UUIDs, Anthropic `toolu_…`), so non-conforming ids
+/// are remapped deterministically — ported from Pi's
+/// `mistral-conversations.ts` normalizer: strip non-alphanumerics, keep
+/// the id when the result is already exactly nine chars, otherwise hash
+/// (FNV-1a → base36) down to nine, retrying with an attempt suffix on
+/// collision. ONE map serves `tool_calls[].id` and `tool_call_id` alike,
+/// so call/result pairing survives.
+fn normalize_mistral_tool_call_ids(body: &mut Value) {
+    const LEN: usize = 9;
+
+    fn derive(id: &str, attempt: u32) -> String {
+        let normalized: String = id.chars().filter(char::is_ascii_alphanumeric).collect();
+        if attempt == 0 && normalized.len() == LEN {
+            return normalized;
+        }
+        let seed_base = if normalized.is_empty() {
+            id
+        } else {
+            &normalized
+        };
+        let seed = if attempt == 0 {
+            seed_base.to_string()
+        } else {
+            format!("{seed_base}:{attempt}")
+        };
+        // FNV-1a (stable across builds, unlike std's DefaultHasher) → base36.
+        let mut hash: u64 = 0xcbf2_9ce4_8422_2325;
+        for b in seed.bytes() {
+            hash ^= u64::from(b);
+            hash = hash.wrapping_mul(0x0000_0100_0000_01b3);
+        }
+        let mut out = String::with_capacity(LEN);
+        let digits = b"0123456789abcdefghijklmnopqrstuvwxyz";
+        let mut h = hash;
+        while out.len() < LEN {
+            out.push(digits[(h % 36) as usize] as char);
+            h = h / 36 + 1; // +1 keeps the stream from collapsing to zeros
+        }
+        out
+    }
+
+    let Some(messages) = body.get_mut("messages").and_then(|m| m.as_array_mut()) else {
+        return;
+    };
+    let mut forward: std::collections::HashMap<String, String> = std::collections::HashMap::new();
+    let mut taken: std::collections::HashSet<String> = std::collections::HashSet::new();
+    let mut normalize = |id: &str| -> String {
+        if let Some(mapped) = forward.get(id) {
+            return mapped.clone();
+        }
+        let mut attempt = 0;
+        loop {
+            let candidate = derive(id, attempt);
+            if taken.insert(candidate.clone()) {
+                forward.insert(id.to_string(), candidate.clone());
+                return candidate;
+            }
+            attempt += 1;
+        }
+    };
+    for message in messages.iter_mut() {
+        if let Some(tool_calls) = message.get_mut("tool_calls").and_then(|t| t.as_array_mut()) {
+            for tc in tool_calls {
+                if let Some(id) = tc.get("id").and_then(|v| v.as_str()).map(str::to_owned) {
+                    tc["id"] = Value::String(normalize(&id));
+                }
+            }
+        }
+        if let Some(id) = message
+            .get("tool_call_id")
+            .and_then(|v| v.as_str())
+            .map(str::to_owned)
+        {
+            message["tool_call_id"] = Value::String(normalize(&id));
+        }
     }
 }
 
@@ -666,4 +751,56 @@ mod tests {
         assert_eq!(props["num"]["type"], json!("number"));
         assert_eq!(props["free"]["type"], json!("string"));
     }
+
+    /// Mistral dialect: exactly-nine `[a-zA-Z0-9]` tool-call ids. A
+    /// conforming id survives; foreign ids (OpenAI `call_…`, UUIDs) remap
+    /// deterministically; the SAME map serves `tool_calls[].id` and
+    /// `tool_call_id`, so pairing survives; distinct inputs never collide.
+    #[test]
+    fn mistral_dialect_normalizes_tool_call_ids_symmetrically() {
+        let mut body = serde_json::json!({
+            "messages": [
+                {"role": "assistant", "tool_calls": [
+                    {"id": "abc123XYZ", "type": "function", "function": {"name": "a", "arguments": "{}"}},
+                    {"id": "call_0123456789abcdef", "type": "function", "function": {"name": "b", "arguments": "{}"}}
+                ]},
+                {"role": "tool", "tool_call_id": "abc123XYZ", "content": "r1"},
+                {"role": "tool", "tool_call_id": "call_0123456789abcdef", "content": "r2"},
+            ],
+            "stream_options": {"include_usage": true}
+        });
+        adapt_chat_completions_body_for(kigi_sampling_types::ChatCompat::Mistral, &mut body);
+
+        let msgs = body["messages"].as_array().unwrap();
+        let ids: Vec<String> = msgs[0]["tool_calls"]
+            .as_array()
+            .unwrap()
+            .iter()
+            .map(|tc| tc["id"].as_str().unwrap().to_string())
+            .collect();
+        // Conforming id kept verbatim.
+        assert_eq!(ids[0], "abc123XYZ");
+        // Foreign id remapped to exactly nine alphanumerics.
+        assert_eq!(ids[1].len(), 9, "{ids:?}");
+        assert!(ids[1].chars().all(|ch| ch.is_ascii_alphanumeric()));
+        assert_ne!(ids[0], ids[1], "distinct inputs must not collide");
+        // Results carry the SAME mapped ids.
+        assert_eq!(msgs[1]["tool_call_id"].as_str().unwrap(), ids[0]);
+        assert_eq!(msgs[2]["tool_call_id"].as_str().unwrap(), ids[1]);
+        // StrictOpenAi base behavior rides along.
+        assert!(body.get("stream_options").is_none());
+
+        // Determinism: the same foreign id maps identically in a fresh body.
+        let mut body2 = serde_json::json!({
+            "messages": [
+                {"role": "tool", "tool_call_id": "call_0123456789abcdef", "content": "r"}
+            ]
+        });
+        adapt_chat_completions_body_for(kigi_sampling_types::ChatCompat::Mistral, &mut body2);
+        assert_eq!(
+            body2["messages"][0]["tool_call_id"].as_str().unwrap(),
+            ids[1],
+            "remap must be deterministic across requests (prefix-cache stability)"
+        );
+    }
 }

crates/codegen/kigi-sampling-types/src/conversation.rs

@@ -319,15 +319,15 @@ impl BackendToolCallItem {
                 format!("[backend x_search] {}({})", ct.name, ct.input)
             }
             BackendToolKind::CodeInterpreter(ci) => {
+                // Char-boundary-safe preview: a byte slice (`&c[..100]`)
+                // panicked on CJK/emoji code, crashing every subsequent
+                // request build on every backend.
                 let code_preview = ci
                     .code
                     .as_deref()
-                    .map(|c| {
-                        if c.len() > 100 {
-                            format!("{}...", &c[..100])
-                        } else {
-                            c.to_string()
-                        }
+                    .map(|c| match c.char_indices().nth(100) {
+                        Some((byte_idx, _)) => format!("{}...", &c[..byte_idx]),
+                        None => c.to_string(),
                     })
                     .unwrap_or_default();
                 format!("[backend code_interpreter] {code_preview}")
@@ -1773,31 +1773,18 @@ pub fn conversation_item_to_chat_message(item: ConversationItem) -> ChatRequestM
             }
         }
         ConversationItem::ToolResult(t) => {
-            if t.images.is_empty() {
-                ChatRequestMessage::tool(t.tool_call_id, t.content.as_ref().to_owned())
+            // Tool messages are TEXT-ONLY on the OpenAI chat wire (the spec
+            // allows string/text-parts; image parts 400 on strict
+            // validators). Images ride a synthetic user message appended
+            // after the consecutive tool-result run by
+            // `conversation_to_chat_messages` — the Pi `openai-completions`
+            // relocation. An image-only result gets a pointer placeholder.
+            let text = if t.content.is_empty() && !t.images.is_empty() {
+                "(see attached image)".to_string()
             } else {
-                let mut blocks = vec![ChatContentBlock::Text {
-                    text: t.content.as_ref().to_owned(),
-                }];
-                for img in t.images {
-                    if let ContentPart::Image { url } = img {
-                        blocks.push(ChatContentBlock::ImageUrl {
-                            image_url: ImageUrl {
-                                url: url.as_ref().to_owned(),
-                            },
-                        });
-                    }
-                }
-                ChatRequestMessage {
-                    role: Role::Tool,
-                    content: MessageContent::Blocks(blocks),
-                    name: None,
-                    tool_calls: Vec::new(),
-                    tool_call_id: Some(t.tool_call_id),
-                    model_id: None,
-                    reasoning_content: None,
-                }
-            }
+                t.content.as_ref().to_owned()
+            };
+            ChatRequestMessage::tool(t.tool_call_id, text)
         }
         // Backend tool calls have no Chat Completions equivalent.
         // Emit a synthetic assistant message so the model sees context
@@ -1839,16 +1826,44 @@ pub fn conversation_item_to_chat_message(item: ConversationItem) -> ChatRequestM
 pub fn conversation_to_chat_messages(items: Vec<ConversationItem>) -> Vec<ChatRequestMessage> {
     let mut out: Vec<ChatRequestMessage> = Vec::with_capacity(items.len());
     let mut pending_reasoning: Vec<String> = Vec::new();
+    // Images from the current consecutive tool-result run. Tool messages
+    // are text-only on the OpenAI chat wire, and a user message may not
+    // interrupt the run (tool messages must directly follow their
+    // assistant's tool_calls), so images batch here and flush as ONE
+    // synthetic user message after the run — Pi's `openai-completions`
+    // relocation pattern.
+    let mut pending_tool_images: Vec<ChatContentBlock> = Vec::new();
+    let flush_tool_images = |pending: &mut Vec<ChatContentBlock>,
+                             out: &mut Vec<ChatRequestMessage>| {
+        if pending.is_empty() {
+            return;
+        }
+        let mut blocks = vec![ChatContentBlock::Text {
+            text: "Attached image(s) from tool result:".to_string(),
+        }];
+        blocks.append(pending);
+        out.push(ChatRequestMessage {
+            role: Role::User,
+            content: MessageContent::Blocks(blocks),
+            name: None,
+            tool_calls: Vec::new(),
+            tool_call_id: None,
+            model_id: None,
+            reasoning_content: None,
+        });
+    };
 
     for item in items {
         match item {
             ConversationItem::Reasoning(r) => {
+                flush_tool_images(&mut pending_tool_images, &mut out);
                 let text = reasoning_item_text(&r);
                 if !text.is_empty() {
                     pending_reasoning.push(text);
                 }
             }
             ConversationItem::Assistant(_) => {
+                flush_tool_images(&mut pending_tool_images, &mut out);
                 let mut msg = conversation_item_to_chat_message(item);
                 if !pending_reasoning.is_empty() {
                     msg.reasoning_content = Some(pending_reasoning.join("\n"));
@@ -1864,6 +1879,21 @@ pub fn conversation_to_chat_messages(items: Vec<ConversationItem>) -> Vec<ChatRe
                 // folds onto the following assistant — matching the Responses
                 // API path, which preserves reasoning across backend tool
                 // calls.
+                flush_tool_images(&mut pending_tool_images, &mut out);
+                out.push(conversation_item_to_chat_message(item));
+            }
+            ConversationItem::ToolResult(ref t) => {
+                // Collect the run's images before the text-only conversion.
+                for img in &t.images {
+                    if let ContentPart::Image { url } = img {
+                        pending_tool_images.push(ChatContentBlock::ImageUrl {
+                            image_url: ImageUrl {
+                                url: url.as_ref().to_owned(),
+                            },
+                        });
+                    }
+                }
+                pending_reasoning.clear();
                 out.push(conversation_item_to_chat_message(item));
             }
             other => {
@@ -1871,11 +1901,13 @@ pub fn conversation_to_chat_messages(items: Vec<ConversationItem>) -> Vec<ChatRe
                 // intervening user/tool messages clear it, matching the
                 // pre-refactor behavior where reasoning lived on the
                 // immediately-following assistant turn only.
+                flush_tool_images(&mut pending_tool_images, &mut out);
                 pending_reasoning.clear();
                 out.push(conversation_item_to_chat_message(other));
             }
         }
     }
+    flush_tool_images(&mut pending_tool_images, &mut out);
 
     out
 }
@@ -2188,14 +2220,86 @@ impl From<&ConversationRequest> for rs::CreateResponse {
 /// so they appear inline in the same order the model originally emitted —
 /// which is what lets the server-side prefix KV-cache hit on repeat turns.
 fn build_responses_input(req: &ConversationRequest) -> rs::InputParam {
-    let items: Vec<rs::InputItem> = req
-        .items
+    let transformed = transform_items_for_responses(&req.items, req.model.as_deref());
+    let items: Vec<rs::InputItem> = transformed
         .iter()
         .flat_map(conversation_item_to_input_items)
         .collect();
     rs::InputParam::Items(items)
 }
 
+/// Provenance gate for the Responses input (the Pi `transform-messages`
+/// pattern): opaque provider-issued items replay verbatim only when the
+/// turn that produced them ran on the SAME model this request targets.
+///
+/// Each `[Reasoning | BackendToolCall]* Assistant` run carries its
+/// provenance in `AssistantItem::model_id`. On a confirmed mismatch
+/// (both sides known, different — a mid-session `/model` switch or a
+/// cross-backend history):
+/// - `Reasoning` siblings are DROPPED — their encrypted payloads are
+///   scoped to the issuing model (OpenAI documents encrypted content as
+///   model-bound; foreign backends' blobs are undecryptable outright);
+/// - `BackendToolCall` items are DEMOTED to a synthetic assistant text
+///   summary — exactly the downgrade the Messages and ChatCompletions
+///   builders already perform — because their typed shapes carry
+///   provider-issued ids and tool names the target never declared
+///   (e.g. a grok `x_search` CustomToolCall replayed to codex).
+///
+/// Same-model runs, unknown provenance (pre-provenance histories with
+/// `model_id: None`), and trailing orphans pass through verbatim — that
+/// byte-stability is what lets the server-side prefix KV-cache hit.
+fn transform_items_for_responses(
+    items: &[ConversationItem],
+    target_model: Option<&str>,
+) -> Vec<ConversationItem> {
+    let Some(target) = target_model else {
+        return items.to_vec();
+    };
+    let mut out: Vec<ConversationItem> = Vec::with_capacity(items.len());
+    // Pending run of opaque siblings awaiting their Assistant carrier.
+    let mut run_start: usize = 0;
+    for item in items {
+        match item {
+            ConversationItem::Reasoning(_) | ConversationItem::BackendToolCall(_) => {
+                out.push(item.clone());
+            }
+            ConversationItem::Assistant(a) => {
+                let foreign = a
+                    .model_id
+                    .as_deref()
+                    .is_some_and(|producer| producer != target);
+                if foreign {
+                    // Rewrite the pending run in place.
+                    let mut rewritten: Vec<ConversationItem> = Vec::new();
+                    for pending in out.drain(run_start..) {
+                        match pending {
+                            ConversationItem::Reasoning(_) => {}
+                            ConversationItem::BackendToolCall(b) => {
+                                rewritten.push(ConversationItem::Assistant(AssistantItem {
+                                    content: b.text_summary().into(),
+                                    tool_calls: vec![],
+                                    model_id: a.model_id.clone(),
+                                    model_fingerprint: None,
+                                    reasoning_effort: None,
+                                }));
+                            }
+                            other => rewritten.push(other),
+                        }
+                    }
+                    out.extend(rewritten);
+                }
+                out.push(item.clone());
+                run_start = out.len();
+            }
+            other => {
+                out.push(other.clone());
+                run_start = out.len();
+            }
+        }
+    }
+    out
+}
+
 /// Walk a serialized Responses API request body and inject the
 /// `type: "reasoning_text"` discriminator that the API requires on
 /// `reasoning.content[*]` items.
@@ -2251,9 +2355,23 @@ fn conversation_item_to_input_items(item: &ConversationItem) -> Vec<rs::InputIte
         }
         ConversationItem::Reasoning(r) => {
             // Reasoning items round-trip back to the Responses API in their
-            // native typed form. `status` is output-only (the API rejects it
-            // on input), so strip it before emission; everything else
-            // (summary, content, encrypted_content, id) passes through.
+            // native typed form — but ONLY items the Responses API itself
+            // produced. A native item always carries a server-issued `rs_*`
+            // id; an EMPTY id marks a foreign item (Messages capture stores
+            // the Anthropic signature with id "", chat-completions and the
+            // stream-delta fallback synthesize with id "", legacy upgraders
+            // reconstruct with id ""), and the API rejects it outright:
+            // 400 "Invalid 'input[N].id': ''. Expected an ID that contains
+            // letters, numbers, underscores, or dashes". Foreign reasoning
+            // is unusable by a Responses provider anyway — drop it (the
+            // exact mirror of the Messages builder's
+            // `prune_replayed_thinking`).
+            if r.id.is_empty() {
+                return vec![];
+            }
+            // `status` is output-only (the API rejects it on input), so
+            // strip it before emission; everything else (summary, content,
+            // encrypted_content, id) passes through.
             let mut r = r.clone();
             r.status = None;
             vec![rs::InputItem::Item(rs::Item::Reasoning(r))]
@@ -2274,12 +2392,15 @@ fn conversation_item_to_input_items(item: &ConversationItem) -> Vec<rs::InputIte
                 }));
             }
 
-            // Add each tool call as a FunctionCall item
+            // Add each tool call as a FunctionCall item. The call_id is
+            // normalized to the Responses charset (foreign backends mint
+            // arbitrary ids); the ToolResult arm applies the SAME map so
+            // pairing survives.
             for tc in &a.tool_calls {
                 let arguments = sanitize_tool_arguments(&tc.id, &tc.name, tc.arguments.clone());
                 items.push(rs::InputItem::Item(rs::Item::FunctionCall(
                     rs::FunctionToolCall {
-                        call_id: tc.id.as_ref().to_owned(),
+                        call_id: sanitize_tool_call_id(&tc.id),
                         name: tc.name.clone(),
                         arguments: arguments.as_ref().to_owned(),
                         id: None,
@@ -2313,7 +2434,9 @@ fn conversation_item_to_input_items(item: &ConversationItem) -> Vec<rs::InputIte
             };
             vec![rs::InputItem::Item(rs::Item::FunctionCallOutput(
                 rs::FunctionCallOutputItemParam {
-                    call_id: t.tool_call_id.clone(),
+                    // Same normalization as the FunctionCall arm — pairing
+                    // survives because both sides map identically.
+                    call_id: sanitize_tool_call_id(&t.tool_call_id),
                     output,
                     id: None,
                     status: None,
@@ -2983,6 +3106,53 @@ pub fn dedup_duplicate_tool_results(conversation: &mut Vec<ConversationItem>) ->
 // ============================================================================
 
 /// Convert a ConversationRequest to Anthropic MessagesRequest.
+/// Normalize a tool-call id to the `[A-Za-z0-9_-]+` charset both Anthropic
+/// Messages and the OpenAI Responses API enforce ("Expected an ID that
+/// contains letters, numbers, underscores, or dashes"). Foreign backends
+/// mint arbitrary ids (chat-completions providers, UUID synthesis), so the
+/// wire builders apply this SYMMETRICALLY on the call and its result —
+/// pairing survives because both sides map through the same function.
+/// ASCII-only (the old closure used Unicode `is_alphanumeric`, letting
+/// e.g. CJK ids through to Anthropic's ASCII contract); an empty id maps
+/// to `"_"` so the mandatory field is never empty on the wire.
+fn sanitize_tool_call_id(id: &str) -> String {
+    if id.is_empty() {
+        return "_".to_string();
+    }
+    id.chars()
+        .map(|c| {
+            if c.is_ascii_alphanumeric() || c == '_' || c == '-' {
+                c
+            } else {
+                '_'
+            }
+        })
+        .collect()
+}
+
+/// The raster media types Anthropic accepts for base64 image sources.
+const ANTHROPIC_IMAGE_MEDIA_TYPES: [&str; 4] =
+    ["image/jpeg", "image/png", "image/gif", "image/webp"];
+
+/// Parse a `data:` URI into an Anthropic base64 image source
+/// `(media_type, data)`.
+///
+/// `None` for anything Anthropic would reject — non-base64 data URIs
+/// (previously leaked as `ImageSource::Url` carrying a `data:` payload:
+/// url sources must be http(s) → 400), media types outside the raster
+/// whitelist (`image/svg+xml` → 400), and param-carrying headers
+/// (`data:image/webp;name=x;base64,…` yields media type
+/// `"image/webp;name=x"` → 400). Callers degrade to a short text
+/// placeholder — never the raw URI, which for data URIs can be megabytes.
+fn parse_base64_image_data_uri(url: &str) -> Option<(String, String)> {
+    let rest = url.strip_prefix("data:")?;
+    let (media_type, data) = rest.split_once(";base64,")?;
+    let media_type = media_type.to_ascii_lowercase();
+    ANTHROPIC_IMAGE_MEDIA_TYPES
+        .contains(&media_type.as_str())
+        .then(|| (media_type, data.to_string()))
+}
+
 pub fn build_messages_request(req: &ConversationRequest) -> crate::messages::MessagesRequest {
     use crate::messages::{
         CacheControl, ContentBlock, ImageSource, Message, MessageContent, MessageRole,
@@ -2995,19 +3165,6 @@ pub fn build_messages_request(req: &ConversationRequest) -> crate::messages::Mes
     let mut pending_assistant: Vec<ContentBlock> = Vec::new();
     let mut pending_tool_results: Vec<ContentBlock> = Vec::new();
 
-    // Helper to sanitize tool call IDs (replace [^a-zA-Z0-9_-] with _)
-    let sanitize_tool_call_id = |id: &str| -> String {
-        id.chars()
-            .map(|c| {
-                if c.is_alphanumeric() || c == '_' || c == '-' {
-                    c
-                } else {
-                    '_'
-                }
-            })
-            .collect()
-    };
-
     // Helper to convert ContentPart to Anthropic ContentBlock
     let content_parts_to_anthropic_blocks = |parts: &[ContentPart]| -> Vec<ContentBlock> {
         parts
@@ -3018,28 +3175,9 @@ pub fn build_messages_request(req: &ConversationRequest) -> crate::messages::Mes
                     cache_control: None,
                 },
                 ContentPart::Image { url } => {
-                    // Parse data: URI vs HTTP(S) URL
-                    if url.starts_with("data:") {
-                        // data:image/png;base64,ABC123...
-                        if let Some((header, data)) = url.split_once(',') {
-                            // Extract media type from header: data:image/png;base64
-                            let media_type = header
-                                .strip_prefix("data:")
-                                .and_then(|h| h.strip_suffix(";base64"))
-                                .unwrap_or("image/png")
-                                .to_string();
+                    if let Some((media_type, data)) = parse_base64_image_data_uri(url) {
                         ContentBlock::Image {
-                                source: ImageSource::Base64 {
-                                    media_type,
-                                    data: data.to_string(),
-                                },
-                            }
-                        } else {
-                            // Malformed data URI, treat as text
-                            ContentBlock::Text {
-                                text: format!("[invalid image: {}]", url),
-                                cache_control: None,
-                            }
+                            source: ImageSource::Base64 { media_type, data },
                         }
                     } else if url.starts_with("http://") || url.starts_with("https://") {
                         ContentBlock::Image {
@@ -3047,6 +3185,13 @@ pub fn build_messages_request(req: &ConversationRequest) -> crate::messages::Mes
                                 url: url.as_ref().to_owned(),
                             },
                         }
+                    } else if url.starts_with("data:") {
+                        // Rejected data URI (non-base64 / non-raster media
+                        // type): short placeholder, NEVER the payload.
+                        ContentBlock::Text {
+                            text: "[unsupported image]".to_string(),
+                            cache_control: None,
+                        }
                     } else {
                         // Unknown format, treat as text
                         ContentBlock::Text {
@@ -3096,7 +3241,17 @@ pub fn build_messages_request(req: &ConversationRequest) -> crate::messages::Mes
             ConversationItem::User(u) => {
                 flush_assistant(&mut pending_assistant, &mut messages);
                 flush_tool_results(&mut pending_tool_results, &mut messages);
-                let blocks = content_parts_to_anthropic_blocks(&u.content);
+                // Anthropic rejects empty content: drop empty text parts and
+                // give an all-empty user turn a placeholder (mirrors the
+                // assistant arm's emptiness guard).
+                let mut blocks = content_parts_to_anthropic_blocks(&u.content);
+                blocks.retain(|b| !matches!(b, ContentBlock::Text { text, .. } if text.is_empty()));
+                if blocks.is_empty() {
+                    blocks.push(ContentBlock::Text {
+                        text: "[empty message]".to_string(),
+                        cache_control: None,
+                    });
+                }
                 messages.push(Message {
                     role: MessageRole::User,
                     content: MessageContent::Blocks(blocks),
@@ -3139,23 +3294,26 @@ pub fn build_messages_request(req: &ConversationRequest) -> crate::messages::Mes
                     }];
                     for img in &t.images {
                         if let ContentPart::Image { url } = img {
-                            let source = if let Some(rest) = url.strip_prefix("data:") {
-                                if let Some((media_type, data)) = rest.split_once(";base64,") {
-                                    ImageSource::Base64 {
-                                        media_type: media_type.to_string(),
-                                        data: data.to_string(),
-                                    }
-                                } else {
-                                    ImageSource::Url {
+                            // Same whitelist parse as the user path; a
+                            // rejected data URI must never ride as
+                            // `ImageSource::Url` (url sources are http(s)
+                            // only — Anthropic 400s a `data:` payload).
+                            if let Some((media_type, data)) = parse_base64_image_data_uri(url) {
+                                blocks.push(ContentBlock::Image {
+                                    source: ImageSource::Base64 { media_type, data },
+                                });
+                            } else if url.starts_with("http://") || url.starts_with("https://") {
+                                blocks.push(ContentBlock::Image {
+                                    source: ImageSource::Url {
                                         url: url.as_ref().to_owned(),
-                                    }
-                                }
+                                    },
+                                });
                             } else {
-                                ImageSource::Url {
-                                    url: url.as_ref().to_owned(),
+                                blocks.push(ContentBlock::Text {
+                                    text: "[unsupported image]".to_string(),
+                                    cache_control: None,
+                                });
                             }
-                            };
-                            blocks.push(ContentBlock::Image { source });
                         }
                     }
                     ToolResultContent::Blocks(blocks)
@@ -4621,6 +4779,310 @@ mod tests {
         }
     }
 
+    /// Anthropic image sources: base64 only for whitelisted raster types;
+    /// url sources http(s) only. Previously a non-base64 `data:` URI rode
+    /// as `ImageSource::Url` (400), `image/svg+xml` passed the media type
+    /// through (400), and a param-carrying header produced
+    /// `"image/webp;name=x"` (400). Rejected images degrade to a SHORT
+    /// placeholder — never the multi-megabyte payload. Empty user turns
+    /// get a placeholder block (Anthropic rejects empty content).
+    #[test]
+    fn messages_request_guards_images_and_empty_user_content() {
+        let req = ConversationRequest::from_items(vec![
+            ConversationItem::user_with_parts(vec![
+                ContentPart::Text { text: "".into() },
+                ContentPart::Image {
+                    url: "data:image/png;base64,AAAA".into(),
+                },
+                ContentPart::Image {
+                    url: "data:image/svg+xml;base64,PHN2Zz4=".into(),
+                },
+                ContentPart::Image {
+                    url: "data:text/plain,hello".into(),
+                },
+            ]),
+            assistant_text("a1"),
+            // Empty user turn: must not ship an empty content array.
+            ConversationItem::user(""),
+        ]);
+        let json = serde_json::to_value(build_messages_request(&req)).unwrap();
+        let messages = json["messages"].as_array().unwrap();
+
+        let first_user = &messages[0]["content"].as_array().unwrap();
+        // Valid png passes as base64.
+        assert!(
+            first_user
+                .iter()
+                .any(|b| b["type"] == "image" && b["source"]["media_type"] == "image/png"),
+            "{json:#}"
+        );
+        // svg + non-base64 rejected to short placeholders; never a
+        // data: payload in a url source, never a non-raster media type.
+        for m in messages {
+            if let Some(content) = m.get("content").and_then(|c| c.as_array()) {
+                assert!(!content.is_empty(), "empty content array: {json:#}");
+                for b in content {
+                    if b["type"] == "image" {
+                        let src = &b["source"];
+                        if src["type"] == "url" {
+                            let u = src["url"].as_str().unwrap();
+                            assert!(
+                                u.starts_with("http://") || u.starts_with("https://"),
+                                "url source must be http(s): {u}"
+                            );
+                        } else {
+                            let mt = src["media_type"].as_str().unwrap();
+                            assert!(
+                                ANTHROPIC_IMAGE_MEDIA_TYPES.contains(&mt),
+                                "media type must be whitelisted: {mt}"
+                            );
+                        }
+                    }
+                }
+            }
+        }
+        assert_eq!(
+            first_user
+                .iter()
+                .filter(|b| b["text"] == "[unsupported image]")
+                .count(),
+            2,
+            "both rejected images degrade to placeholders: {json:#}"
+        );
+        // The empty user turn carries the placeholder block.
+        let last_user = messages.last().unwrap();
+        assert_eq!(last_user["content"][0]["text"], "[empty message]");
+    }
+
+    /// Tool-result images take the same whitelist: a rejected data URI in
+    /// a tool result degrades to a text block, never an
+    /// `ImageSource::Url` carrying a `data:` payload.
+    #[test]
+    fn messages_request_guards_tool_result_images() {
+        let req = ConversationRequest::from_items(vec![
+            ConversationItem::user("q"),
+            ConversationItem::Assistant(AssistantItem {
+                content: "".into(),
+                tool_calls: vec![ToolCall {
+                    id: std::sync::Arc::from("tc1"),
+                    name: "read_file".to_string(),
+                    arguments: std::sync::Arc::from("{}"),
+                }],
+                model_id: None,
+                model_fingerprint: None,
+                reasoning_effort: None,
+            }),
+            ConversationItem::tool_result_with_images(
+                "tc1",
+                "saw an image",
+                vec![ContentPart::Image {
+                    url: "data:text/plain,hello".into(),
+                }],
+            ),
+        ]);
+        let json = serde_json::to_value(build_messages_request(&req)).unwrap();
+        let raw = json.to_string();
+        assert!(
+            !raw.contains("data:text/plain"),
+            "rejected data URI must not reach the wire: {json:#}"
+        );
+        assert!(raw.contains("[unsupported image]"), "{json:#}");
+    }
+
+    /// Provenance gate: a turn produced by a DIFFERENT model must not
+    /// replay its opaque items to this request's target — Reasoning
+    /// (model-bound encrypted payloads) is dropped, BackendToolCall
+    /// (provider-issued ids + undeclared tool shapes, e.g. grok x_search
+    /// → codex) is demoted to the same text summary the other builders
+    /// emit. Same-model and unknown-provenance turns stay byte-verbatim
+    /// (KV-cache stability).
+    #[test]
+    fn responses_input_gates_foreign_turns_by_provenance() {
+        let custom_call: rs::CustomToolCall = serde_json::from_value(serde_json::json!({
+            "call_id": "xs_1",
+            "id": "ct_1",
+            "input": "{\"q\":\"news\"}",
+            "name": "x_search",
+        }))
+        .expect("custom tool call fixture");
+        let x_search = ConversationItem::BackendToolCall(BackendToolCallItem {
+            kind: BackendToolKind::XSearch(custom_call),
+        });
+        let foreign_assistant = ConversationItem::Assistant(AssistantItem {
+            content: "grok says hi".into(),
+            tool_calls: vec![],
+            model_id: Some("grok-4".to_string()),
+            model_fingerprint: None,
+            reasoning_effort: None,
+        });
+        let native_assistant = ConversationItem::Assistant(AssistantItem {
+            content: "codex says hi".into(),
+            tool_calls: vec![],
+            model_id: Some("gpt-5.2-codex".to_string()),
+            model_fingerprint: None,
+            reasoning_effort: None,
+        });
+        let mut req = ConversationRequest::from_items(vec![
+            ConversationItem::user("q1"),
+            // Foreign turn: grok reasoning + x_search + assistant.
+            ConversationItem::Reasoning(rs::ReasoningItem {
+                id: "rs_grok_1".to_string(),
+                summary: vec![],
+                content: None,
+                encrypted_content: Some("grok-blob".to_string()),
+                status: None,
+            }),
+            x_search,
+            foreign_assistant,
+            ConversationItem::user("q2"),
+            // Native turn: same model as the request target.
+            ConversationItem::Reasoning(rs::ReasoningItem {
+                id: "rs_codex_1".to_string(),
+                summary: vec![],
+                content: None,
+                encrypted_content: Some("codex-blob".to_string()),
+                status: None,
+            }),
+            native_assistant,
+            ConversationItem::user("q3"),
+        ]);
+        req.model = Some("gpt-5.2-codex".to_string());
+
+        let json = serde_json::to_value(rs::CreateResponse::from(&req)).unwrap();
+        let input = json["input"].as_array().unwrap();
+
+        // Foreign reasoning + x_search gone; the summary text survives.
+        assert!(
+            !input.iter().any(|i| i["id"] == "rs_grok_1"),
+            "foreign reasoning must be dropped:\n{json:#}"
+        );
+        assert!(
+            !input.iter().any(|i| i["type"] == "custom_tool_call"),
+            "foreign backend tool call must not replay typed:\n{json:#}"
+        );
+        assert!(
+            input.iter().any(|i| i["role"] == "assistant"
+                && i["content"]
+                    .as_str()
+                    .is_some_and(|c| c.contains("[backend x_search]"))),
+            "foreign backend tool call demoted to text summary:\n{json:#}"
+        );
+        // Native reasoning verbatim.
+        assert!(
+            input
+                .iter()
+                .any(|i| i["id"] == "rs_codex_1" && i["encrypted_content"] == "codex-blob"),
+            "native reasoning must replay verbatim:\n{json:#}"
+        );
+    }
+
+    /// Both Anthropic Messages and the Responses API enforce
+    /// `[A-Za-z0-9_-]+` tool-call ids; foreign backends mint arbitrary
+    /// ones. The shared sanitizer must be ASCII-only (the old closure's
+    /// Unicode `is_alphanumeric` let CJK ids through), never emit an empty
+    /// id, and map call + result IDENTICALLY so pairing survives.
+    #[test]
+    fn tool_call_ids_sanitized_symmetrically_on_responses_leg() {
+        let weird_id = "调用#1 β";
+        let req = ConversationRequest::from_items(vec![
+            ConversationItem::user("q"),
+            ConversationItem::Assistant(AssistantItem {
+                content: "".into(),
+                tool_calls: vec![ToolCall {
+                    id: std::sync::Arc::from(weird_id),
+                    name: "read_file".to_string(),
+                    arguments: std::sync::Arc::from("{}"),
+                }],
+                model_id: None,
+                model_fingerprint: None,
+                reasoning_effort: None,
+            }),
+            ConversationItem::tool_result(weird_id, "contents"),
+        ]);
+        let json = serde_json::to_value(rs::CreateResponse::from(&req)).unwrap();
+        let input = json["input"].as_array().unwrap();
+        let call_id = input
+            .iter()
+            .find(|i| i["type"] == "function_call")
+            .map(|i| i["call_id"].as_str().unwrap().to_string())
+            .expect("function_call present");
+        let output_id = input
+            .iter()
+            .find(|i| i["type"] == "function_call_output")
+            .map(|i| i["call_id"].as_str().unwrap().to_string())
+            .expect("function_call_output present");
+        assert_eq!(call_id, output_id, "pairing must survive sanitization");
+        assert!(
+            call_id
+                .chars()
+                .all(|c| c.is_ascii_alphanumeric() || c == '_' || c == '-'),
+            "sanitized id must satisfy the wire charset: {call_id:?}"
+        );
+        assert!(!call_id.is_empty());
+        // The sanitizer itself: ASCII passthrough, unicode replaced, empty
+        // never emitted.
+        assert_eq!(sanitize_tool_call_id("toolu_01AB-cd"), "toolu_01AB-cd");
+        assert_eq!(sanitize_tool_call_id("统A1"), "_A1");
+        assert_eq!(sanitize_tool_call_id(""), "_");
+    }
+
+    /// The Responses API requires a server-issued id on every replayed
+    /// reasoning input item — an empty one 400s with "Invalid
+    /// 'input[N].id': ''" (observed on the Codex backend after a
+    /// cross-backend session switched to a GPT model). Empty-id reasoning
+    /// can only be foreign: Messages-captured (Anthropic signature,
+    /// id "") or chat-completions-synthesized (id "", no encrypted
+    /// content). Neither is usable by a Responses provider — drop them;
+    /// native `rs_*` items pass through untouched.
+    #[test]
+    fn responses_input_drops_reasoning_without_native_id() {
+        let req = ConversationRequest::from_items(vec![
+            ConversationItem::user("q1"),
+            // Messages-captured: Anthropic signature, empty id.
+            reasoning("claude thinking", Some("anthropic-sig")),
+            assistant_text("a1"),
+            ConversationItem::user("q2"),
+            // Chat-completions synthesized: empty id, nothing encrypted.
+            ConversationItem::Reasoning(synthesized_reasoning_item("kimi thinking")),
+            assistant_text("a2"),
+            ConversationItem::user("q3"),
+            // Native Responses item: server-issued id.
+            ConversationItem::Reasoning(rs::ReasoningItem {
+                id: "rs_native_1".to_string(),
+                summary: vec![],
+                content: None,
+                encrypted_content: Some("gAAAA-native".to_string()),
+                status: None,
+            }),
+            assistant_text("a3"),
+            ConversationItem::user("q4"),
+        ]);
+
+        let responses_req: rs::CreateResponse = (&req).into();
+        let json = serde_json::to_value(&responses_req).unwrap();
+        let reasoning_items: Vec<&serde_json::Value> = json["input"]
+            .as_array()
+            .unwrap()
+            .iter()
+            .filter(|i| i.get("type").and_then(|t| t.as_str()) == Some("reasoning"))
+            .collect();
+        assert_eq!(
+            reasoning_items.len(),
+            1,
+            "only the native rs_* item may be replayed:\n{json:#}"
+        );
+        assert_eq!(reasoning_items[0]["id"], "rs_native_1");
+        assert_eq!(reasoning_items[0]["encrypted_content"], "gAAAA-native");
+        assert!(
+            !json["input"]
+                .as_array()
+                .unwrap()
+                .iter()
+                .any(|i| i.get("id").and_then(|v| v.as_str()) == Some("")),
+            "no input item may carry an empty id:\n{json:#}"
+        );
+    }
+
     #[test]
     fn test_encrypted_reasoning_included_in_responses_api_request() {
         // Test that when building a Responses API request, encrypted reasoning is included
@@ -4687,12 +5149,15 @@ mod tests {
 
     #[test]
     fn test_only_encrypted_reasoning_included_in_request() {
-        // Test that when there's only encrypted content (no visible summary),
-        // it's still included in the request
+        // Encrypted-only reasoning replays ONLY with a native (server-issued)
+        // id. An id-less encrypted blob is by construction FOREIGN (the
+        // Responses stream always captures the `rs_*` id; Messages capture
+        // stores the Anthropic signature with id "") and the API rejects
+        // empty ids — see `responses_input_drops_reasoning_without_native_id`.
         let req = ConversationRequest::from_items(vec![
             ConversationItem::user("Hello"),
             ConversationItem::Reasoning(rs::ReasoningItem {
-                id: String::new(),
+                id: "rs_hidden_1".to_string(),
                 summary: vec![],
                 content: None,
                 encrypted_content: Some("enc_hidden_thoughts".to_string()),
@@ -4725,6 +5190,7 @@ mod tests {
 
         assert_eq!(reasoning_items.len(), 1);
         let reasoning = reasoning_items[0];
+        assert_eq!(reasoning.id, "rs_hidden_1");
 
         // Encrypted content should be present
         assert_eq!(
@@ -7917,6 +8383,10 @@ mod tests {
 
     #[test]
     fn test_tool_result_with_images_to_chat_completions() {
+        // Tool messages are TEXT-ONLY on the OpenAI chat wire (image parts
+        // 400 on strict validators); the images relocate to a batched user
+        // message in `conversation_to_chat_messages` — see
+        // `chat_tool_result_images_relocate_to_batched_user_message`.
         let item = ConversationItem::tool_result_with_images(
             "call_1",
             "Read image file: photo.png",
@@ -7928,21 +8398,11 @@ mod tests {
         let msg = conversation_item_to_chat_message(item);
         assert_eq!(msg.role, Role::Tool);
         assert_eq!(msg.tool_call_id, Some("call_1".to_string()));
-
-        // Should be Blocks, not Text
-        let MessageContent::Blocks(blocks) = &msg.content else {
-            panic!(
-                "Expected Blocks content for image tool result, got {:?}",
+        assert!(
+            matches!(&msg.content, MessageContent::Text(t) if t == "Read image file: photo.png"),
+            "tool message must be text-only, got {:?}",
             msg.content
         );
-        };
-        assert_eq!(blocks.len(), 2);
-        assert!(
-            matches!(&blocks[0], ChatContentBlock::Text { text } if text == "Read image file: photo.png")
-        );
-        assert!(
-            matches!(&blocks[1], ChatContentBlock::ImageUrl { image_url } if image_url.url == "data:image/png;base64,iVBOR")
-        );
     }
 
     #[test]
@@ -8715,6 +9175,79 @@ mod tests {
         );
     }
 
+    #[test]
+    fn chat_tool_result_images_relocate_to_batched_user_message() {
+        // Tool messages are text-only on the OpenAI chat wire; images from
+        // a CONSECUTIVE tool-result run must batch into ONE user message
+        // AFTER the run (a user message may not interrupt tool responses
+        // answering the same assistant's tool_calls) — Pi's
+        // openai-completions relocation. An image-only result gets a
+        // pointer placeholder.
+        let assistant_with_calls = |ids: &[&str]| {
+            ConversationItem::Assistant(AssistantItem {
+                content: "".into(),
+                tool_calls: ids
+                    .iter()
+                    .map(|id| ToolCall {
+                        id: std::sync::Arc::from(*id),
+                        name: "read_file".to_string(),
+                        arguments: std::sync::Arc::from("{}"),
+                    })
+                    .collect(),
+                model_id: None,
+                model_fingerprint: None,
+                reasoning_effort: None,
+            })
+        };
+        let img = |data: &str| ContentPart::Image {
+            url: format!("data:image/png;base64,{data}").into(),
+        };
+        let msgs = conversation_to_chat_messages(vec![
+            ConversationItem::user("q"),
+            assistant_with_calls(&["tc1", "tc2"]),
+            ConversationItem::tool_result_with_images("tc1", "", vec![img("AAA")]),
+            ConversationItem::tool_result_with_images("tc2", "text out", vec![img("BBB")]),
+            ConversationItem::assistant("done"),
+        ]);
+
+        let roles: Vec<Role> = msgs.iter().map(|m| m.role).collect();
+        assert_eq!(
+            roles,
+            vec![
+                Role::User,
+                Role::Assistant,
+                Role::Tool,
+                Role::Tool,
+                Role::User,
+                Role::Assistant
+            ],
+            "images flush as ONE user message after the tool run: {msgs:#?}"
+        );
+        // Tool messages are text-only; the image-only result carries the
+        // pointer placeholder.
+        assert!(matches!(&msgs[2].content, MessageContent::Text(t) if t == "(see attached image)"));
+        assert!(matches!(&msgs[3].content, MessageContent::Text(t) if t == "text out"));
+        // The batched user message carries the lead text + BOTH images.
+        let MessageContent::Blocks(blocks) = &msgs[4].content else {
+            panic!("image carrier must be a blocks message: {msgs:#?}");
+        };
+        assert_eq!(blocks.len(), 3);
+        assert!(
+            matches!(&blocks[0], ChatContentBlock::Text { text } if text.starts_with("Attached image"))
+        );
+        let urls: Vec<&str> = blocks[1..]
+            .iter()
+            .filter_map(|b| match b {
+                ChatContentBlock::ImageUrl { image_url } => Some(image_url.url.as_str()),
+                _ => None,
+            })
+            .collect();
+        assert_eq!(
+            urls,
+            vec!["data:image/png;base64,AAA", "data:image/png;base64,BBB"]
+        );
+    }
+
     #[test]
     fn conversation_to_chat_messages_folds_reasoning_into_following_assistant() {
         let items = vec![
@@ -9540,6 +10073,40 @@ mod tests {
         assert_prefix_stable(&req2, &req3);
     }
 
+    /// `text_summary`'s code preview truncated at BYTE 100 (`&c[..100]`) —
+    /// a panic on any non-ASCII boundary (CJK/emoji in interpreted code).
+    /// One poisoned history item then crashed every subsequent request
+    /// build on every backend. Truncation must be char-boundary safe.
+    #[test]
+    fn code_interpreter_summary_truncates_multibyte_code_safely() {
+        let item = BackendToolCallItem {
+            kind: BackendToolKind::CodeInterpreter(rs::CodeInterpreterToolCall {
+                code: Some("统计".repeat(60)),
+                container_id: "cont_1".to_string(),
+                id: "ci_1".to_string(),
+                outputs: None,
+                status: rs::CodeInterpreterToolCallStatus::Completed,
+            }),
+        };
+        let summary = item.text_summary();
+        assert!(summary.starts_with("[backend code_interpreter] 统计"));
+        assert!(
+            summary.ends_with("..."),
+            "long code must truncate: {summary}"
+        );
+        // ASCII shorter than the cap stays whole.
+        let short = BackendToolCallItem {
+            kind: BackendToolKind::CodeInterpreter(rs::CodeInterpreterToolCall {
+                code: Some("print(1)".to_string()),
+                container_id: "cont_1".to_string(),
+                id: "ci_2".to_string(),
+                outputs: None,
+                status: rs::CodeInterpreterToolCallStatus::Completed,
+            }),
+        };
+        assert_eq!(short.text_summary(), "[backend code_interpreter] print(1)");
+    }
+
     /// `BackendToolCall` items round-trip through the wire as their
     /// typed Item shape; their serialized position must be stable across
     /// turns. (This is the structural analogue of the old

crates/codegen/kigi-sampling-types/src/types.rs

@@ -1054,6 +1054,10 @@ pub fn patch_reasoning_effort(body: &mut Value, effort: Option<ReasoningEffort>)
 /// 2. `store` is always `false` on this backend, so reasoning continuity
 ///    is stateless: `include: ["reasoning.encrypted_content"]` is required
 ///    for the response to carry replayable encrypted reasoning.
+/// 3. For the same reason, a replayed reasoning item WITHOUT
+///    `encrypted_content` (captured from a stateful api.openai.com session
+///    that never requested the include) references server state
+///    chatgpt.com does not have — drop it rather than 400.
 ///
 /// openai-codex-GATED at the call sites — API-key `openai` Responses
 /// bodies stay byte-identical.
@@ -1104,6 +1108,18 @@ pub fn adapt_body_for_codex_backend(body: &mut Value) {
             entries.push(key);
         }
     }
+
+    // 3. Drop reasoning items with no encrypted payload: stateless codex
+    // cannot resolve a bare `rs_*` reference.
+    if let Some(input) = body.get_mut("input").and_then(|v| v.as_array_mut()) {
+        input.retain(|item| {
+            item.get("type").and_then(|t| t.as_str()) != Some("reasoning")
+                || item
+                    .get("encrypted_content")
+                    .and_then(|v| v.as_str())
+                    .is_some_and(|s| !s.is_empty())
+        });
+    }
 }
 
 /// Neutralize a `reasoning.effort` echo the typed `rs` enum cannot parse
@@ -1244,15 +1260,21 @@ pub enum ChatCompat {
     DeepSeek,
     /// Leave the body as-is (OpenAI-style `reasoning_effort` passes through).
     Passthrough,
-    /// Strict OpenAI-compatible validators (Mistral, Cerebras) reject any
+    /// Strict OpenAI-compatible validators (Cerebras, NVIDIA) reject any
     /// out-of-schema request field with a 4xx (`additionalProperties:false`).
     /// kigi injects `stream_options.include_usage` on every streaming
     /// request, which such validators reject, so it is stripped (streaming
     /// usage falls back to token estimation). `reasoning_effort` passes
     /// through; private message fields are stripped like Passthrough.
-    /// (Serde alias `mistral` keeps sessions persisted before the rename.)
-    #[serde(alias = "mistral")]
     StrictOpenAi,
+    /// Mistral: [`Self::StrictOpenAi`] behavior plus its exactly-nine
+    /// `[a-zA-Z0-9]` tool-call id contract — foreign/OpenAI-style ids are
+    /// deterministically remapped on call+result in one shared map (the
+    /// Pi `mistral-conversations` normalizer). Serializes as `mistral`, so
+    /// sessions persisted before the StrictOpenAi rename (which carried
+    /// the `mistral` alias) resolve here — correct, they were Mistral
+    /// sessions.
+    Mistral,
 }
 
 pub const REASONING_EFFORT_META_KEY: &str = "reasoningEffort";
@@ -1662,6 +1684,38 @@ mod tests {
         assert_eq!(body, before);
     }
 
+    /// Stateless codex cannot resolve a bare `rs_*` reference: reasoning
+    /// input items without an encrypted payload are dropped; items WITH
+    /// one pass through untouched.
+    #[test]
+    fn codex_adapter_drops_reasoning_without_encrypted_payload() {
+        let mut body = json!({
+            "model": "gpt-5.2-codex",
+            "input": [
+                {"type": "message", "role": "user", "content": "q"},
+                {"type": "reasoning", "id": "rs_bare", "summary": []},
+                {"type": "reasoning", "id": "rs_full", "summary": [],
+                 "encrypted_content": "gAAAA-blob"},
+                {"type": "message", "role": "assistant", "content": "a"}
+            ]
+        });
+        adapt_body_for_codex_backend(&mut body);
+        let input = body["input"].as_array().unwrap();
+        assert_eq!(input.len(), 3, "bare rs_* item dropped: {body:#}");
+        assert!(
+            input
+                .iter()
+                .any(|i| i.get("id").and_then(|v| v.as_str()) == Some("rs_full")),
+            "encrypted reasoning passes through: {body:#}"
+        );
+        assert!(
+            !input
+                .iter()
+                .any(|i| i.get("id").and_then(|v| v.as_str()) == Some("rs_bare")),
+            "{body:#}"
+        );
+    }
+
     /// No system items and no prior instructions: input untouched, no
     /// empty-string instructions invented, include still requested.
     #[test]
@@ -1683,9 +1737,15 @@ mod tests {
     /// persisted before the rename still deserialize.
     #[test]
     fn chat_compat_mistral_alias_deserializes_to_strict_openai() {
+        // `mistral` resolves to the dedicated Mistral dialect — including
+        // sessions persisted before the StrictOpenAi rename (they were
+        // Mistral sessions and now get the 9-char id contract too).
         let v: ChatCompat = serde_json::from_str("\"mistral\"").unwrap();
-        assert_eq!(v, ChatCompat::StrictOpenAi);
-        // New value round-trips as strict_open_ai.
+        assert_eq!(v, ChatCompat::Mistral);
+        assert_eq!(
+            serde_json::to_string(&ChatCompat::Mistral).unwrap(),
+            "\"mistral\""
+        );
         let v: ChatCompat = serde_json::from_str("\"strict_open_ai\"").unwrap();
         assert_eq!(v, ChatCompat::StrictOpenAi);
         assert_eq!(

crates/codegen/kigi-shell/src/agent/config.rs

@@ -4099,8 +4099,12 @@ pub fn sampling_config_for_model(
         &credentials.base_url,
     );
     let api_backend = info.api_backend.clone();
-    // Managed platform entries speak their registry dialect; BYOK/custom
-    // entries keep the historical Kimi body adaptation.
+    // Managed platform entries speak their registry dialect. BYOK/custom
+    // entries default to Passthrough (vanilla OpenAI semantics — the
+    // Kimi-specific body mutations `thinking:{…}` + replayed
+    // `reasoning_content` 400 on third-party OpenAI-compatible servers),
+    // EXCEPT entries pointed at the house/Kimi coding endpoint, which keep
+    // the historical Kimi dialect (mirrors Pi's base-url quirk sniffing).
     let chat_compat = info
         .id
         .as_deref()
@@ -4114,8 +4118,15 @@ pub fn sampling_config_for_model(
             kigi_models::PlatformChatCompat::StrictOpenAi => {
                 kigi_sampling_types::ChatCompat::StrictOpenAi
             }
+            kigi_models::PlatformChatCompat::Mistral => kigi_sampling_types::ChatCompat::Mistral,
         })
-        .unwrap_or_default();
+        .unwrap_or_else(|| {
+            if crate::util::is_effective_coding_endpoint_url(&credentials.base_url) {
+                kigi_sampling_types::ChatCompat::Kimi
+            } else {
+                kigi_sampling_types::ChatCompat::Passthrough
+            }
+        });
     // Claude Pro/Max OAuth Messages adaptation: a managed key whose platform is
     // a generic-OAuth Messages provider (claude-pro-max) drives the OAuth
     // identity headers + "You are Claude Code" system prefix in the sampler.
@@ -5963,6 +5974,72 @@ reasoning_effort = "low"
             "agentType should always be in meta, defaulting to DEFAULT_AGENT_TYPE"
         );
     }
+    /// BYOK/custom entries (no managed platform key) default to the
+    /// Passthrough dialect — the historical Kimi default leaked
+    /// Kimi-specific body mutations (`thinking:{…}`, replayed
+    /// `reasoning_content`) to third-party OpenAI-compatible servers.
+    /// The one exception: entries pointed at the house/Kimi coding
+    /// endpoint keep the Kimi dialect (base-url detection, mirroring
+    /// Pi's quirk sniffing).
+    #[test]
+    fn byok_custom_entries_default_to_passthrough_except_house_endpoint() {
+        let make_cfg = |base_url: &str| {
+            let entry_cfg = ModelEntryConfig {
+                id: None, // BYOK: no managed platform key
+                model: "my-custom-model".to_string(),
+                base_url: base_url.to_string(),
+                name: None,
+                description: None,
+                max_completion_tokens: None,
+                temperature: None,
+                top_p: None,
+                api_key: None,
+                env_key: None,
+                api_backend: ApiBackend::default(),
+                auth_scheme: None,
+                extra_headers: IndexMap::new(),
+                context_window: NonZeroU64::new(200_000).unwrap(),
+                auto_compact_threshold_percent: None,
+                system_prompt_label: None,
+                api_base_url: None,
+                use_concise: true,
+                agent_type: default_agent_type(),
+                inference_idle_timeout_secs: None,
+                max_retries: None,
+                hidden: false,
+                supported_in_api: true,
+                reasoning_effort: None,
+                supports_reasoning_effort: false,
+                reasoning_efforts: Vec::new(),
+                capabilities: Vec::new(),
+                supports_backend_search: false,
+                compactions_remaining: None,
+                compaction_at_tokens: None,
+                show_model_fingerprint: false,
+                stream_tool_calls: None,
+                laziness_detector: LazinessDetectorPerModelConfig::default(),
+            };
+            let entry = ModelEntry::from_config_entry(&entry_cfg);
+            let creds = ResolvedCredentials {
+                api_key: Some("sk-byok".into()),
+                base_url: base_url.to_string(),
+                auth_type: kigi_chat_state::AuthType::ApiKey,
+                auth_scheme: Default::default(),
+            };
+            sampling_config_for_model(&entry, creds, None)
+        };
+        assert_eq!(
+            make_cfg("https://api.third-party.example/v1").chat_compat,
+            kigi_sampling_types::ChatCompat::Passthrough,
+            "third-party BYOK must get vanilla OpenAI semantics"
+        );
+        assert_eq!(
+            make_cfg("https://api.kimi.com/coding/v1").chat_compat,
+            kigi_sampling_types::ChatCompat::Kimi,
+            "the house coding endpoint keeps the Kimi dialect"
+        );
+    }
+
     /// Managed `{platform}/{model}` entries stamp `meta.provider` with the
     /// platform's display name so the client's model picker can say which
     /// connected provider each model belongs to. User-defined `[model.*]`

crates/codegen/kigi-shell/src/agent/models_fetch.rs

@@ -1841,8 +1841,9 @@ mod tests {
         let cfg = crate::agent::config::sampling_config_for_model(&model_entry, creds, None);
         assert_eq!(
             cfg.chat_compat,
-            kigi_sampling_types::ChatCompat::StrictOpenAi,
-            "mistral entries use the StrictOpenAi dialect (stream_options strip)"
+            kigi_sampling_types::ChatCompat::Mistral,
+            "mistral entries use the Mistral dialect (StrictOpenAi behavior \
+             plus the exactly-nine-alphanumeric tool-call id contract)"
         );
     }
 

crates/codegen/kigi-shell/tests/test_sampling_client.rs

@@ -472,7 +472,12 @@ async fn responses_upgrade_roundtrips_reconstructed_reasoning_as_typed_input() {
             "\n",
             r#"{"type":"user","content":[{"type":"text","text":"q1"}]}"#,
             "\n",
-            r#"{"type":"assistant","content":"a1","reasoning":{"text":"legacy kigi reasoning","encrypted":"ENC_BLOB_xyz","id":"rs_kigibuild_legacy"},"model_id":"kigi"}"#,
+            // model_id matches the test client's request model: this test
+            // covers the SAME-MODEL continuation (the byte-stable
+            // SGLang-prefix path). A mismatched model_id is the provenance
+            // gate's territory (`transform_items_for_responses`) and drops
+            // the reasoning by design.
+            r#"{"type":"assistant","content":"a1","reasoning":{"text":"legacy kigi reasoning","encrypted":"ENC_BLOB_xyz","id":"rs_kigibuild_legacy"},"model_id":"test-model"}"#,
             "\n",
         ),
     )