llmshim 0.2.1__tar.gz → 0.2.2__tar.gz

{llmshim-0.2.1 → llmshim-0.2.2}/CLAUDE.md

@@ -81,7 +81,7 @@ Callers pass provider-specific controls under these keys. Each provider copies w
 
 ### Unified reasoning controls
 
-Two knobs work across every provider: `reasoning_effort` (`none|low|medium|high|xhigh|max`) and `reasoning_mode` (`standard|pro`). Each provider transform maps them to its native dialect, **clamping to the nearest tier the target model accepts** (all boundaries verified live — e.g. `max` is native only on OpenAI gpt-5.6; Anthropic 4.6 rejects `xhigh` but has `max`; Gemini's enum tops out at `high`; xAI grok-4.20 models reject any reasoning param). `mode: "pro"` is native on OpenAI gpt-5.6/-pro models (`reasoning.mode`), emulated as a one-tier effort bump elsewhere; explicit `none` always wins. Native passthrough (`x-openai.reasoning`, `x-anthropic.thinking`, `x-gemini.thinkingConfig`) bypasses the mapping entirely and always takes precedence. **Full per-provider mapping tables: `docs/src/guides/reasoning.md`** — update it and the pinning tests in `tests/unit_*.rs` together whenever a mapping changes.
+Two knobs work across every provider: `reasoning_effort` (`none|low|medium|high|xhigh|max`) and `reasoning_mode` (`standard|pro`). A third, `reasoning_summary` (`auto|none`), controls reasoning-text visibility → Anthropic `thinking.display` (`auto`→`summarized`, the default when `reasoning_effort` is present so newer models like Sonnet 5 / Opus 4.7-4.8 return reasoning text instead of the API-default `omitted`; `none`→`omitted` for lower latency). Applies to both the adaptive and pre-4.6 enabled thinking builders; a caller-supplied `thinking` block bypasses it. Each provider transform maps them to its native dialect, **clamping to the nearest tier the target model accepts** (all boundaries verified live — e.g. `max` is native only on OpenAI gpt-5.6; Anthropic 4.6 rejects `xhigh` but has `max`; Gemini's enum tops out at `high`; xAI grok-4.20 models reject any reasoning param). `mode: "pro"` is native on OpenAI gpt-5.6/-pro models (`reasoning.mode`), emulated as a one-tier effort bump elsewhere; explicit `none` always wins. Native passthrough (`x-openai.reasoning`, `x-anthropic.thinking`, `x-gemini.thinkingConfig`) bypasses the mapping entirely and always takes precedence. **Full per-provider mapping tables: `docs/src/guides/reasoning.md`** — update it and the pinning tests in `tests/unit_*.rs` together whenever a mapping changes.
 
 ### Tool format translation
 

{llmshim-0.2.1 → llmshim-0.2.2}/Cargo.lock

@@ -958,7 +958,7 @@ checksum = "6373607a59f0be73a39b6fe456b8192fcc3585f602af20751600e974dd455e77"
 
 [[package]]
 name = "llmshim"
-version = "0.2.1"
+version = "0.2.2"
 dependencies = [
  "async-stream",
  "async-trait",

{llmshim-0.2.1 → llmshim-0.2.2}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "llmshim"
-version = "0.2.1"
+version = "0.2.2"
 edition = "2021"
 description = "Blazing fast LLM API translation layer in pure Rust"
 license = "MIT"

{llmshim-0.2.1 → llmshim-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llmshim
-Version: 0.2.1
+Version: 0.2.2
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License

{llmshim-0.2.1 → llmshim-0.2.2}/docs/src/reference/request-fields.md

@@ -23,6 +23,7 @@ renamed or reshaped for the selected provider; unsupported controls are omitted.
 | `stop` | array of strings | Conditional, mapped | Passed as `stop` to Anthropic or mapped to Gemini `stopSequences`; omitted by OpenAI/xAI |
 | `reasoning_effort` | string | Portable, mapped/clamped | Unified effort from `none` through `max` |
 | `reasoning_mode` | string | Portable, mapped/clamped | `standard` or `pro` |
+| `reasoning_summary` | string | Anthropic (`auto`\|`none`) | Reasoning visibility → Anthropic `thinking.display`; `auto`→`summarized` (default with `reasoning_effort`), `none`→`omitted` for lower latency |
 | `tools` | array | Portable, mapped | OpenAI Chat Completions function schema translated to native tools |
 | `tool_choice` | string or object | Portable, mapped | Translated where the provider supports tool choice |
 | `x-openai` | object | Native passthrough | Fields copied to an OpenAI Responses request |

{llmshim-0.2.1 → llmshim-0.2.2}/src/providers/anthropic.rs

@@ -603,6 +603,17 @@ impl Provider for Anthropic {
                     .unwrap_or(false);
                 let effort = normalize_unified_effort(effort, pro);
 
+                // Reasoning-summary visibility. Newer models (Sonnet 5, Opus
+                // 4.7/4.8, ...) default `display` to "omitted" — a signed but
+                // empty thinking block with no thinking_delta text. Default to
+                // "summarized" so reasoning text is returned consistently across
+                // model generations; a latency-sensitive caller opts back into
+                // "omitted" via reasoning_summary. Verified live 2026-07-17.
+                let display = match obj.get("reasoning_summary").and_then(|v| v.as_str()) {
+                    Some("none") | Some("omitted") => "omitted",
+                    _ => "summarized",
+                };
+
                 if effort == "none" {
                     if Self::uses_adaptive_thinking(model) {
                         // Adaptive models think by default even with no config;
@@ -612,7 +623,10 @@ impl Provider for Anthropic {
                     }
                     // Pre-4.6/Haiku: thinking is opt-in; omitting the key IS "none".
                 } else if Self::uses_adaptive_thinking(model) {
-                    body_obj.insert("thinking".to_string(), json!({"type": "adaptive"}));
+                    body_obj.insert(
+                        "thinking".to_string(),
+                        json!({"type": "adaptive", "display": display}),
+                    );
                     // Opus/Sonnet 4.6 reject "xhigh" (their tiers: low/medium/high/max);
                     // Opus 4.7/4.8 + Sonnet 5 accept the full low..max range (verified).
                     let anthropic_effort =
@@ -644,7 +658,8 @@ impl Provider for Anthropic {
                         "thinking".to_string(),
                         json!({
                             "type": "enabled",
-                            "budget_tokens": budget
+                            "budget_tokens": budget,
+                            "display": display
                         }),
                     );
                 }

{llmshim-0.2.1 → llmshim-0.2.2}/tests/integration_thinking.rs

@@ -403,3 +403,34 @@ async fn anthropic_reasoning_roundtrip_accepted_live() {
     assert!(!content.is_empty(), "expected a final answer, got: {resp2}");
     println!("Round-trip accepted. Final answer: {content}");
 }
+
+#[tokio::test]
+#[ignore]
+async fn anthropic_sonnet5_reasoning_summary_default_returns_text_live() {
+    // Issue #37: sonnet-5 defaults display to "omitted" (empty thinking text).
+    // With the fix, reasoning_effort defaults display to "summarized" so real
+    // reasoning text comes back.
+    if std::env::var("ANTHROPIC_API_KEY").is_err() {
+        return;
+    }
+    let router = router();
+    // A prompt that reliably engages adaptive thinking (trivial prompts may be
+    // answered directly even at high effort — "adaptive" means the model decides).
+    let prompt = "Prove or disprove: for every positive integer n, the value \
+        n^2 + n + 41 is prime. Give rigorous reasoning.";
+    let req = json!({
+        "model": "anthropic/claude-sonnet-5",
+        "messages": [{"role": "user", "content": prompt}],
+        "max_tokens": 4000,
+        "reasoning_effort": "high",
+    });
+    let resp = llmshim::completion(&router, &req).await.unwrap();
+    let reasoning = resp["choices"][0]["message"]["reasoning_content"]
+        .as_str()
+        .unwrap_or("");
+    assert!(
+        !reasoning.is_empty(),
+        "expected reasoning text by default (display=summarized), got empty. resp: {resp}"
+    );
+    println!("sonnet-5 reasoning text chars: {}", reasoning.len());
+}

{llmshim-0.2.1 → llmshim-0.2.2}/tests/unit_anthropic.rs

@@ -1753,3 +1753,94 @@ fn stream_redacted_thinking_block_start_emits() {
         "blob-stream"
     );
 }
+
+// ============================================================
+// Reasoning summary visibility (issue #37): thinking.display
+// ============================================================
+
+#[test]
+fn adaptive_thinking_defaults_display_summarized() {
+    let p = provider();
+    let req = json!({
+        "model": "claude-sonnet-5",
+        "messages": [{"role": "user", "content": "hi"}],
+        "reasoning_effort": "high",
+    });
+    let result = p.transform_request("claude-sonnet-5", &req).unwrap();
+    assert_eq!(result.body["thinking"]["type"], "adaptive");
+    assert_eq!(result.body["thinking"]["display"], "summarized");
+    assert_eq!(result.body["output_config"]["effort"], "high");
+}
+
+#[test]
+fn adaptive_thinking_reasoning_summary_none_omits() {
+    let p = provider();
+    let req = json!({
+        "model": "claude-sonnet-5",
+        "messages": [{"role": "user", "content": "hi"}],
+        "reasoning_effort": "high",
+        "reasoning_summary": "none",
+    });
+    let result = p.transform_request("claude-sonnet-5", &req).unwrap();
+    assert_eq!(result.body["thinking"]["display"], "omitted");
+    // The unified control must not leak into the API body.
+    assert!(result.body.get("reasoning_summary").is_none());
+}
+
+#[test]
+fn adaptive_thinking_reasoning_summary_auto_summarizes() {
+    let p = provider();
+    let req = json!({
+        "model": "claude-opus-4-8",
+        "messages": [{"role": "user", "content": "hi"}],
+        "reasoning_effort": "medium",
+        "reasoning_summary": "auto",
+    });
+    let result = p.transform_request("claude-opus-4-8", &req).unwrap();
+    assert_eq!(result.body["thinking"]["display"], "summarized");
+}
+
+#[test]
+fn enabled_thinking_forwards_display() {
+    // Pre-4.6 / Haiku use the enabled-budget path; display is valid there too.
+    let p = provider();
+    let req = json!({
+        "model": "claude-haiku-4-5-20251001",
+        "messages": [{"role": "user", "content": "hi"}],
+        "reasoning_effort": "high",
+    });
+    let result = p
+        .transform_request("claude-haiku-4-5-20251001", &req)
+        .unwrap();
+    assert_eq!(result.body["thinking"]["type"], "enabled");
+    assert_eq!(result.body["thinking"]["display"], "summarized");
+    assert!(result.body["thinking"]["budget_tokens"].as_u64().unwrap() >= 1024);
+}
+
+#[test]
+fn reasoning_effort_none_stays_disabled_without_display() {
+    let p = provider();
+    let req = json!({
+        "model": "claude-sonnet-5",
+        "messages": [{"role": "user", "content": "hi"}],
+        "reasoning_effort": "none",
+    });
+    let result = p.transform_request("claude-sonnet-5", &req).unwrap();
+    assert_eq!(result.body["thinking"]["type"], "disabled");
+    assert!(result.body["thinking"].get("display").is_none());
+}
+
+#[test]
+fn passthrough_thinking_display_untouched() {
+    // A caller-supplied thinking block wins; the effort translation (and its
+    // default display) is bypassed by the has_thinking gate.
+    let p = provider();
+    let req = json!({
+        "model": "claude-sonnet-5",
+        "messages": [{"role": "user", "content": "hi"}],
+        "reasoning_effort": "high",
+        "thinking": {"type": "adaptive", "display": "omitted"},
+    });
+    let result = p.transform_request("claude-sonnet-5", &req).unwrap();
+    assert_eq!(result.body["thinking"]["display"], "omitted");
+}