test(prompt): update test callers + assertions for new renderer signature

Follow-up to tinyhumansai#447. The main patch changed three signatures that test
callers hadn't been updated for, and flipped one assertion that was
validating the now-removed prose schema duplication.

- `SubagentRunOptions` test constructors in subagent_runner.rs (2
  sites) now pass `toolkit_override: None`.
- `ConnectedIntegration` test constructor in orchestrator_tools.rs
  now passes `connected: true` (the default for test integrations —
  they're treated as authorized so delegation logic still runs).
- 12 `render_subagent_system_prompt` test callers in prompt.rs now
  pass `&[]` for the new `extra_tools` slice and
  `ToolCallFormat::PFormat` for the new `tool_call_format` argument.
- `render_subagent_system_prompt_honors_identity_safety_and_skills_flags`
  used to assert `rendered.contains("Parameters:")` on the Json
  dispatcher branch — that was valid in the old world where the
  prose `## Tools` section dumped full JSON schemas for Json/Native
  formats. The main patch deliberately removes that dump (it was the
  ~30k-token duplication of the native `tools` field), so the test
  now asserts the opposite: no `## Tools` header and no `Parameters:`
  line are emitted for Native/Json dispatchers. The schemas still
  travel through the provider request's `tools` field.

Also picks up `rustfmt` rewraps in action_tool.rs and ops.rs from a
background linter run — pure whitespace, no semantic change.

Verified green against the full `cargo test --lib` suite for every
test touched by this PR:
- openhuman::context::prompt::tests                         (26 passed)
- openhuman::agent::harness::subagent_runner::tests         (19 passed)
- openhuman::composio::ops::tests                           (2 passed)
- openhuman::tools::impl::agent::tests                      (0 scoped)

The 7 remaining failures in `cargo test --lib` are pre-existing
Windows-path/filesystem flakes in subsystems this PR doesn't touch
(self_healing polyfill path separator, cron scheduler shell spawning,
local_ai::paths absolute-path detection, security::policy sandbox
path handling, composio::trigger_history jsonl archive, and a real
pre-existing `Option::unwrap()` panic in browser::screenshot).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: sanil-23

src/openhuman/agent/harness/subagent_runner.rs

@@ -249,8 +249,7 @@ async fn run_typed_mode(
     // are stripped from the parent-filtered indices in this path so
     // the model only sees one way to call each action.
     let mut dynamic_tools: Vec<Box<dyn Tool>> = Vec::new();
-    let is_skills_agent_with_toolkit =
-        definition.id == "skills_agent" && toolkit_filter.is_some();
+    let is_skills_agent_with_toolkit = definition.id == "skills_agent" && toolkit_filter.is_some();
     if is_skills_agent_with_toolkit {
         // Drop EVERY skill-category parent tool. In the new
         // architecture all integration discovery / authorization /
@@ -1385,6 +1384,7 @@ mod tests {
                 SubagentRunOptions {
                     skill_filter_override: None,
                     category_filter_override: None,
+                    toolkit_override: None,
                     context: None,
                     task_id: Some("t1".into()),
                 },
@@ -1515,6 +1515,7 @@ mod tests {
                 SubagentRunOptions {
                     skill_filter_override: Some("notion".into()),
                     category_filter_override: None,
+                    toolkit_override: None,
                     context: None,
                     task_id: None,
                 },

src/openhuman/composio/action_tool.rs

@@ -83,7 +83,10 @@ impl Tool for ComposioActionTool {
 
     async fn execute(&self, args: Value) -> anyhow::Result<ToolResult> {
         let started = std::time::Instant::now();
-        let res = self.client.execute_tool(&self.action_name, Some(args)).await;
+        let res = self
+            .client
+            .execute_tool(&self.action_name, Some(args))
+            .await;
         let elapsed_ms = started.elapsed().as_millis() as u64;
 
         match res {
@@ -111,10 +114,7 @@ impl Tool for ComposioActionTool {
                         elapsed_ms,
                     },
                 );
-                Ok(ToolResult::error(format!(
-                    "{}: {e}",
-                    self.action_name
-                )))
+                Ok(ToolResult::error(format!("{}: {e}", self.action_name)))
             }
         }
     }

src/openhuman/composio/ops.rs

@@ -473,9 +473,7 @@ async fn fetch_connected_integrations_uncached(
     let allowlisted_toolkits: Vec<String> = match client.list_toolkits().await {
         Ok(resp) => resp.toolkits,
         Err(e) => {
-            tracing::warn!(
-                "[composio] fetch_connected_integrations: list_toolkits failed: {e}"
-            );
+            tracing::warn!("[composio] fetch_connected_integrations: list_toolkits failed: {e}");
             return Some(Vec::new());
         }
     };
@@ -488,9 +486,7 @@ async fn fetch_connected_integrations_uncached(
     let connections = match client.list_connections().await {
         Ok(resp) => resp.connections,
         Err(e) => {
-            tracing::warn!(
-                "[composio] fetch_connected_integrations: list_connections failed: {e}"
-            );
+            tracing::warn!("[composio] fetch_connected_integrations: list_connections failed: {e}");
             // Allowlist still useful — render every toolkit as
             // not-connected so the orchestrator can surface them.
             Vec::new()
@@ -517,9 +513,7 @@ async fn fetch_connected_integrations_uncached(
         match client.list_tools(Some(&connected_slugs_vec)).await {
             Ok(resp) => resp.tools,
             Err(e) => {
-                tracing::warn!(
-                    "[composio] fetch_connected_integrations: list_tools failed: {e}"
-                );
+                tracing::warn!("[composio] fetch_connected_integrations: list_tools failed: {e}");
                 Vec::new()
             }
         }

src/openhuman/context/prompt.rs

@@ -1600,8 +1600,10 @@ mod tests {
             "test-model",
             &[0],
             &tools,
+            &[],
             "You are a focused sub-agent.",
             SubagentRenderOptions::narrow(),
+            ToolCallFormat::PFormat,
             &[],
         ));
 
@@ -1664,6 +1666,7 @@ mod tests {
             "reasoning-v1",
             &[0],
             &tools,
+            &[],
             "You are a specialist.",
             SubagentRenderOptions {
                 include_identity: true,
@@ -1680,14 +1683,22 @@ mod tests {
         assert!(rendered.contains("### SOUL.md"));
         assert!(rendered.contains("## Safety"));
         assert!(rendered.contains("## Available Skills"));
-        assert!(rendered.contains("Parameters:"));
-        assert!(rendered.contains("\"type\""));
+        // Native/Json dispatchers: the prose `## Tools` section is
+        // deliberately omitted from the rendered system prompt — schemas
+        // travel through the provider request's `tools` field instead.
+        // Previously this path emitted `- **test_tool**: …\n  Parameters: {…}`
+        // for every tool, which duplicated the native function-calling
+        // channel and inflated token cost (see the #447 patch). Regression
+        // guards: no `## Tools` header, no inline schema.
+        assert!(!rendered.contains("\n## Tools\n"));
+        assert!(!rendered.contains("Parameters:"));
 
         let native = render_subagent_system_prompt_with_format(
             &workspace,
             "reasoning-v1",
             &[0],
             &tools,
+            &[],
             "You are a specialist.",
             SubagentRenderOptions::narrow(),
             ToolCallFormat::Native,
@@ -1729,6 +1740,7 @@ mod tests {
             "test-model",
             &[0],
             &tools,
+            &[],
             "You are the welcome agent.",
             SubagentRenderOptions {
                 include_identity: false,
@@ -1737,6 +1749,7 @@ mod tests {
                 include_profile: true,
                 include_memory_md: false,
             },
+            ToolCallFormat::PFormat,
             &[],
         );
 
@@ -1784,8 +1797,10 @@ mod tests {
             "test-model",
             &[0],
             &tools,
+            &[],
             "You are a narrow specialist.",
             SubagentRenderOptions::narrow(), // include_profile defaults to false
+            ToolCallFormat::PFormat,
             &[],
         );
 
@@ -1820,6 +1835,7 @@ mod tests {
             "test-model",
             &[0],
             &tools,
+            &[],
             "You are a specialist.",
             SubagentRenderOptions {
                 include_identity: true,
@@ -1828,6 +1844,7 @@ mod tests {
                 include_profile: true,
                 include_memory_md: false,
             },
+            ToolCallFormat::PFormat,
             &[],
         );
 
@@ -1858,8 +1875,10 @@ mod tests {
             "test-model",
             &[0],
             &tools,
+            &[],
             "You are the welcome agent.",
             SubagentRenderOptions::narrow(),
+            ToolCallFormat::PFormat,
             &[],
         );
 
@@ -1909,8 +1928,10 @@ mod tests {
             "test-model",
             &[0],
             &tools,
+            &[],
             "# Welcome Agent\n\nYou are the welcome agent.",
             options,
+            ToolCallFormat::PFormat,
             &[],
         );
 
@@ -1953,8 +1974,10 @@ mod tests {
             "test-model",
             &[0],
             &tools,
+            &[],
             "You are a narrow specialist.",
             options,
+            ToolCallFormat::PFormat,
             &[],
         );
 
@@ -1991,6 +2014,7 @@ mod tests {
             "test-model",
             &[0],
             &tools,
+            &[],
             "You are the welcome agent.",
             SubagentRenderOptions {
                 include_identity: false,
@@ -1999,6 +2023,7 @@ mod tests {
                 include_profile: false,
                 include_memory_md: true,
             },
+            ToolCallFormat::PFormat,
             &[],
         );
 
@@ -2035,8 +2060,10 @@ mod tests {
             "test-model",
             &[0],
             &tools,
+            &[],
             "You are a narrow specialist.",
             SubagentRenderOptions::narrow(),
+            ToolCallFormat::PFormat,
             &[],
         );
 
@@ -2073,6 +2100,7 @@ mod tests {
             "test-model",
             &[0],
             &tools,
+            &[],
             "You are the orchestrator.",
             SubagentRenderOptions {
                 include_identity: false,
@@ -2081,6 +2109,7 @@ mod tests {
                 include_profile: true,
                 include_memory_md: true,
             },
+            ToolCallFormat::PFormat,
             &[],
         );
 
@@ -2130,17 +2159,21 @@ mod tests {
             "test-model",
             &[0],
             &tools,
+            &[],
             "You are the orchestrator.",
             opts,
+            ToolCallFormat::PFormat,
             &[],
         );
         let second = render_subagent_system_prompt(
             &workspace,
             "test-model",
             &[0],
             &tools,
+            &[],
             "You are the orchestrator.",
             opts,
+            ToolCallFormat::PFormat,
             &[],
         );
 

src/openhuman/tools/orchestrator_tools.rs

@@ -235,6 +235,7 @@ mod tests {
             toolkit: toolkit.into(),
             description: description.into(),
             tools: vec![],
+            connected: true,
         }
     }