[codex] Add agent loop eval smoke suite

.cursor/rules/swift-build.mdc

@@ -6,12 +6,26 @@ alwaysApply: false
 
 # Building OsaurusCore
 
-The xcode workspace has pre-existing build failures in external dependencies (`mlx-swift-lm`, `IkigaJSON`). Never use `xcodebuild` to verify changes — it will always fail on those deps and waste tokens.
+Use focused package tests while iterating, and use CI-parity `xcodebuild` only when you need to reproduce the GitHub Actions `test-core` job.
 
-Instead, compile only the OsaurusCore package sources (no linking) to verify your changes:
+Fast local checks from the repository root:
 
 ```bash
-cd /Users/tpae/dev/osaurus/Packages/OsaurusCore && swift build 2>&1 | grep -E "error:" | grep -v "IkigaJSON"
+swift test --package-path Packages/OsaurusCore
+swift test --package-path Packages/OsaurusCLI --parallel
+swift-format lint --strict --recursive Packages App
 ```
 
-If the filtered output is empty, your code compiles cleanly.
+CI-parity check from the repository root:
+
+```bash
+make ci-test
+```
+
+If you only need a compile smoke test for core sources, this is acceptable:
+
+```bash
+swift build --package-path Packages/OsaurusCore
+```
+
+Do not hardcode local absolute paths in docs or scripts. Use repo-root-relative commands unless a tool explicitly requires an absolute path.

.github/pull_request_template.md

@@ -20,7 +20,7 @@ If UI updated, add before/after.
 
 ## Checklist
 
-- [ ] I have read `CONTRIBUTING.md`
+- [ ] I have read `docs/CONTRIBUTING.md`
 - [ ] I added/updated tests where reasonable
 - [ ] I updated docs/README as needed
-- [ ] I verified build on macOS with Xcode 16.4+
+- [ ] I verified build on macOS with a Swift 6.2-capable Xcode toolchain

.github/workflows/ci.yml

@@ -26,7 +26,7 @@ permissions:
 env:
   # Bump to invalidate every cache entry without source surgery (e.g., after a
   # known-bad cache or an Xcode toolchain upgrade we want to flush manually).
-  CACHE_SALT: v2-vmlx-5b84387
+  CACHE_SALT: v3-pr-cold-deriveddata
   # Pin Xcode so cache keys are stable across runner image bumps. When you
   # need to upgrade, change here AND in setup-xcode below.
   XCODE_VERSION: "26.4.1"
@@ -83,9 +83,11 @@ jobs:
 
       - name: Restore DerivedData cache
         id: dd-cache
-        # Always restore so `cache-primary-key` is populated for the save
-        # step at the bottom (the wipe step below handles forced cold
-        # builds without preventing main from repopulating the cache).
+        # Restore only on main pushes / manual maintainer runs. Pull requests
+        # intentionally cold-build DerivedData: exact restore-key hits have
+        # still produced stale Swift modules whose C-module dependencies are
+        # missing when Xcode later compiles EventSource.
+        if: ${{ github.event_name != 'pull_request' }}
         uses: actions/cache/restore@v5
         with:
           path: ~/Library/Developer/Xcode/DerivedData
@@ -97,13 +99,15 @@ jobs:
           restore-keys: |
             dd-${{ runner.os }}-${{ env.CACHE_SALT }}-xcode${{ env.XCODE_VERSION }}-
 
-      # Make "clear the build cache" a one-click operation. Two triggers:
-      #   1. `github.run_attempt != '1'` — i.e. a re-run. The default
+      # Make "clear the build cache" a one-click operation. Three triggers:
+      #   1. Pull requests — always cold-build DerivedData so PRs never trust
+      #      a cached Xcode build product from another ref.
+      #   2. `github.run_attempt != '1'` — i.e. a re-run. The default
       #      "Re-run failed jobs" button is the natural place for someone
       #      who just saw a build failure to land, so we make that the
       #      intuitive escape hatch for cache poison: the first attempt
       #      uses the cache (fast); any re-run forces a cold compile.
-      #   2. `workflow_dispatch.clear_cache=true` — manual force-cold on
+      #   3. `workflow_dispatch.clear_cache=true` — manual force-cold on
       #      a fresh run (e.g. validating a CACHE_SALT bump before PRs
       #      start hitting it).
       #
@@ -116,18 +120,18 @@ jobs:
       # every re-run cost ~2 min in PR #951 run 24937664669 — wasted
       # budget that contributed to the 30-min cold-build cancellation.
       #
-      # We wipe AFTER the restore step (rather than skipping the restore)
-      # so `steps.dd-cache.outputs.cache-primary-key` stays populated and
-      # the `Save DerivedData cache` step at the bottom can still
-      # repopulate the cache on a successful `main` run.
-      - name: Wipe restored DerivedData (re-run or workflow_dispatch clear_cache)
-        if: ${{ github.run_attempt != '1' || (github.event_name == 'workflow_dispatch' && inputs.clear_cache) }}
+      # On main/manual runs we wipe AFTER the restore step (rather than
+      # skipping the restore) so `steps.dd-cache.outputs.cache-primary-key`
+      # stays populated and the `Save DerivedData cache` step at the bottom
+      # can still repopulate the cache on a successful `main` run.
+      - name: Wipe restored DerivedData (PR, re-run, or workflow_dispatch clear_cache)
+        if: ${{ github.event_name == 'pull_request' || github.run_attempt != '1' || (github.event_name == 'workflow_dispatch' && inputs.clear_cache) }}
         run: |
-          REASON="run_attempt=${{ github.run_attempt }}"
+          REASON="event=${{ github.event_name }}, run_attempt=${{ github.run_attempt }}"
           if [ "${{ github.event_name }}" = "workflow_dispatch" ] && [ "${{ inputs.clear_cache }}" = "true" ]; then
             REASON="$REASON, workflow_dispatch clear_cache=true"
           fi
-          echo "::notice title=Cold build forced::Wiping restored DerivedData before build ($REASON). SPM cache preserved (it's source-only and pinned by Package.resolved). To re-run with the warm cache instead, push a new commit or trigger a fresh run."
+          echo "::notice title=Cold build forced::Wiping DerivedData before build ($REASON). SPM cache preserved (it's source-only and pinned by Package.resolved)."
           rm -rf "$HOME/Library/Developer/Xcode/DerivedData"
 
       - name: Resolve dependencies
@@ -248,7 +252,7 @@ jobs:
                 echo
                 echo "**\`run_attempt > 1\` AND \`cache-hit: false\`?** That's the deliberate cold-rebuild path triggered by **Re-run failed jobs** — see the \`Wipe restored DerivedData\` step in this job. If the cold build is exhausting the 45-min budget on every re-run, the codebase has outgrown the budget; bump \`timeout-minutes\` and update its comment block, OR move warm-cache priming to a nightly \`main\` job so PRs always warm-start."
                 echo
-                echo "**Suspect cache poisoning on a fresh attempt?** Click **Re-run failed jobs** — re-runs automatically wipe DerivedData (the SPM cache is preserved because it's pinned by \`Package.resolved\` and can't be poisoned)."
+                echo "**Suspect cache poisoning on a fresh attempt?** Pull requests already cold-build DerivedData; main/manual re-runs wipe DerivedData automatically while preserving the pinned SPM source cache."
               } >> "$GITHUB_STEP_SUMMARY"
             else
               # Mode B.

Packages/OsaurusCore/Models/API/OpenAIAPI.swift

@@ -249,6 +249,9 @@ struct ChatMessage: Codable, Sendable {
     let tool_calls: [ToolCall]?
     /// Required for role=="tool" messages to associate with a prior tool call
     let tool_call_id: String?
+    /// Provider-specific reasoning text that some thinking APIs require on
+    /// follow-up requests after an assistant tool-call turn.
+    let reasoning_content: String?
 
     /// Extract image URLs from content parts (supports both data URLs and http URLs)
     var imageUrls: [String] {
@@ -306,13 +309,15 @@ extension ChatMessage {
         case content
         case tool_calls
         case tool_call_id
+        case reasoning_content
     }
 
     public init(from decoder: Decoder) throws {
         let container = try decoder.container(keyedBy: CodingKeys.self)
         self.role = try container.decode(String.self, forKey: .role)
         self.tool_calls = try? container.decode([ToolCall].self, forKey: .tool_calls)
         self.tool_call_id = try? container.decode(String.self, forKey: .tool_call_id)
+        self.reasoning_content = try? container.decode(String.self, forKey: .reasoning_content)
 
         if let stringContent = try? container.decode(String.self, forKey: .content) {
             self.content = stringContent
@@ -357,6 +362,7 @@ extension ChatMessage {
         // Note: content is intentionally omitted when nil (e.g., assistant messages with tool_calls)
         try container.encodeIfPresent(tool_calls, forKey: .tool_calls)
         try container.encodeIfPresent(tool_call_id, forKey: .tool_call_id)
+        try container.encodeIfPresent(reasoning_content, forKey: .reasoning_content)
     }
 }
 
@@ -367,15 +373,23 @@ extension ChatMessage {
         self.contentParts = nil
         self.tool_calls = nil
         self.tool_call_id = nil
+        self.reasoning_content = nil
     }
 
     /// Initialize with optional tool calls and tool call id
-    init(role: String, content: String?, tool_calls: [ToolCall]?, tool_call_id: String?) {
+    init(
+        role: String,
+        content: String?,
+        tool_calls: [ToolCall]?,
+        tool_call_id: String?,
+        reasoning_content: String? = nil
+    ) {
         self.role = role
         self.content = content
         self.contentParts = nil
         self.tool_calls = tool_calls
         self.tool_call_id = tool_call_id
+        self.reasoning_content = reasoning_content
     }
 
     /// Initialize with multimodal content (text and images)
@@ -399,6 +413,7 @@ extension ChatMessage {
         self.content = text.isEmpty ? nil : text
         self.tool_calls = nil
         self.tool_call_id = nil
+        self.reasoning_content = nil
     }
 
     /// Multimodal init covering image + audio + video. Used by the
@@ -450,6 +465,7 @@ extension ChatMessage {
         self.content = text.isEmpty ? nil : text
         self.tool_calls = nil
         self.tool_call_id = nil
+        self.reasoning_content = nil
     }
 }
 
@@ -824,26 +840,26 @@ public enum JSONValue: Codable, Sendable, Equatable {
 
 extension JSONValue {
     /// Convert JSONValue to Sendable-compatible value for Jinja chat templates.
-    /// Null values are dropped from dictionaries because Jinja's `Value(any:)` cannot
-    /// handle `NSNull` and throws a runtime error. JSON Schema treats a missing key
-    /// the same as `null`, so this is semantically lossless for tool specs.
-    var sendableValue: any Sendable {
+    /// Null values are dropped because Jinja's `Value(any:)` cannot handle
+    /// null/optional placeholders inside erased Swift containers.
+    var sendableValue: (any Sendable)? {
         switch self {
         case .null:
-            return NSNull()
+            return nil
         case .bool(let b):
             return b
         case .number(let n):
             return n
         case .string(let s):
             return s
         case .array(let arr):
-            return arr.map { $0.sendableValue }
+            return arr.compactMap { $0.sendableValue }
         case .object(let obj):
             var dict: [String: any Sendable] = [:]
             for (k, v) in obj {
-                if case .null = v { continue }
-                dict[k] = v.sendableValue
+                if let converted = v.sendableValue {
+                    dict[k] = converted
+                }
             }
             return dict
         }
@@ -881,8 +897,8 @@ extension ToolFunction {
         if let description {
             fn["description"] = description
         }
-        if let parameters {
-            fn["parameters"] = parameters.sendableValue
+        if let parameters, let converted = parameters.sendableValue {
+            fn["parameters"] = converted
         }
         return fn
     }

Packages/OsaurusCore/Models/Chat/ChatSessionStore.swift

@@ -72,6 +72,11 @@ enum ChatSessionStore {
             print("[ChatSessionStore] Failed to open chat-history database: \(error)")
             return
         }
+        #if DEBUG
+            if RuntimeEnvironment.isUnderTests, OsaurusPaths.overrideRoot == nil {
+                return
+            }
+        #endif
         LegacySessionImporter.runIfNeeded()
     }
 }

Packages/OsaurusCore/Services/Chat/ChatEngine.swift

@@ -177,7 +177,8 @@ actor ChatEngine: Sendable, ChatEngineProtocol {
             role: "assistant",
             content: nil,
             tool_calls: toolCalls,
-            tool_call_id: nil
+            tool_call_id: nil,
+            reasoning_content: invocations.compactMap(\.reasoningContent).first
         )
         let choice = ChatChoice(index: 0, message: assistant, finish_reason: "tool_calls")
         let usage = Usage(prompt_tokens: inputTokens, completion_tokens: 0, total_tokens: inputTokens)

Packages/OsaurusCore/Services/Inference/ModelService.swift

@@ -77,12 +77,22 @@ struct ServiceToolInvocation: Error, Sendable {
     let toolCallId: String?
     /// Optional thought signature for Gemini thinking-mode models (e.g. Gemini 2.5)
     let geminiThoughtSignature: String?
+    /// Provider reasoning text that must be echoed on assistant tool-call
+    /// messages for APIs such as DeepSeek thinking mode.
+    let reasoningContent: String?
 
-    init(toolName: String, jsonArguments: String, toolCallId: String? = nil, geminiThoughtSignature: String? = nil) {
+    init(
+        toolName: String,
+        jsonArguments: String,
+        toolCallId: String? = nil,
+        geminiThoughtSignature: String? = nil,
+        reasoningContent: String? = nil
+    ) {
         self.toolName = toolName
         self.jsonArguments = jsonArguments
         self.toolCallId = toolCallId
         self.geminiThoughtSignature = geminiThoughtSignature
+        self.reasoningContent = reasoningContent
     }
 }