fix(code): bind headless basic tools to workspace, harden lifecycle

- Bind basic file/shell tools (read/write/list/execute) to --workspace via
  Workspace containment (fail-closed), matching the edit group, so an
  auto-approved headless run cannot escape the configured workspace.
- Move workspace resolution + tool loading inside the protected try/finally in
  _run_print_code so init failures still emit the JSON error envelope and always
  run cleanup_runtime().
- Use a private mktemp log in the terminal-bench example instead of a
  predictable /tmp path; drop the stale log_path metadata.
- Add --dangerously-skip-approval to the opt-in real-agent write test and a
  fast regression test for basic-group workspace containment.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-authored-by: Mervin Praison <[email protected]>

.github/scripts/merge-gate.js

@@ -74,11 +74,7 @@ function isClaudeTriggerNoise(c) {
 
 function isClaudeFinalReplyComment(c) {
   const login = (c.user?.login || '').toLowerCase();
-  const fromAutomation =
-    login.includes('praisonai-triage') ||
-    login.includes('github-actions') ||
-    AUTO_ACTORS.some((a) => a.toLowerCase() === login);
-  if (!fromAutomation) return false;
+  if (!login.includes('praisonai-triage')) return false;
   return (c.body || '').includes('Claude finished');
 }
 
@@ -100,47 +96,15 @@ function isConflictRebaseTriggerComment(c) {
 
 function isConflictRebaseCompletionComment(c) {
   const login = (c.user?.login || '').toLowerCase();
-  const fromAutomation =
-    login.includes('praisonai-triage') ||
-    login.includes('github-actions') ||
-    AUTO_ACTORS.some((a) => a.toLowerCase() === login);
-  if (!fromAutomation) return false;
+  if (!login.includes('praisonai-triage') && !login.includes('github-actions')) return false;
   const body = (c.body || '').toLowerCase();
   return (
     body.includes('rebase complete') ||
     body.includes('rebase onto') ||
-    body.includes('force-pushed') ||
     (body.includes('conflict') && body.includes('resolved'))
   );
 }
 
-/** HEAD landed after conflict rebase but no FINAL @claude since that push. */
-function needsFinalReReviewAfterConflictRebase(comments, headPushedAt) {
-  if (!headPushedAt) return false;
-  const headTime = new Date(headPushedAt).getTime();
-  const conflictTriggers = comments.filter(isConflictRebaseTriggerComment);
-  if (conflictTriggers.length === 0) return false;
-
-  const latestConflict = conflictTriggers.reduce((a, b) =>
-    new Date(a.created_at) > new Date(b.created_at) ? a : b
-  );
-  const conflictTime = new Date(latestConflict.created_at).getTime();
-  if (headTime <= conflictTime) return false;
-
-  const rebaseDone = comments.some(
-    (c) =>
-      new Date(c.created_at).getTime() > conflictTime && isConflictRebaseCompletionComment(c)
-  );
-  if (!rebaseDone) return false;
-
-  const finalsAfterHead = comments.filter(
-    (c) =>
-      isFinalClaudeTriggerComment(c) &&
-      new Date(c.created_at).getTime() >= headTime - 60000
-  );
-  return finalsAfterHead.length === 0;
-}
-
 function conflictRebaseQuiescent(comments, headPushedAt) {
   const conflictTriggers = comments.filter(isConflictRebaseTriggerComment);
   if (conflictTriggers.length === 0) return true;
@@ -281,9 +245,6 @@ function shouldSkipStaleFinalRecovery(comments, headPushedAt, headPusherLogin =
   if (headPusherLogin && isClaudeAutomationLogin(headPusherLogin)) {
     return { skip: true, reason: 'head pushed by Claude automation' };
   }
-  if (needsFinalReReviewAfterConflictRebase(comments, headPushedAt)) {
-    return { skip: false, reason: '' };
-  }
   if (isPushSoonAfterLatestFinal(comments, headPushedAt)) {
     return {
       skip: true,
@@ -955,7 +916,6 @@ module.exports = {
   hasRecentConflictComment,
   isConflictRebaseTriggerComment,
   isConflictRebaseCompletionComment,
-  needsFinalReReviewAfterConflictRebase,
   conflictRebaseQuiescent,
   hasHumanChangesRequested,
   hasAnyChangesRequested,

.github/workflows/sync-secrets-to-aiui.yml

@@ -24,7 +24,6 @@ jobs:
           CLAUDE_APP_PRIVATE_KEY: ${{ secrets.CLAUDE_APP_PRIVATE_KEY }}
           CLAUDE_CODE_OAUTH_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
           GH_TOKEN_VALUE: ${{ secrets.GH_TOKEN }}
-          DOCS_GITHUB_TOKEN: ${{ secrets.SECRETS_ADMIN_PAT }}
         run: |
           set -euo pipefail
           if [ -z "${GH_TOKEN:-}" ]; then
@@ -35,7 +34,4 @@ jobs:
           echo -n "$CLAUDE_APP_PRIVATE_KEY" | gh secret set CLAUDE_APP_PRIVATE_KEY --repo "$TARGET"
           echo -n "$CLAUDE_CODE_OAUTH_TOKEN" | gh secret set CLAUDE_CODE_OAUTH_TOKEN --repo "$TARGET"
           echo -n "$GH_TOKEN_VALUE" | gh secret set GH_TOKEN --repo "$TARGET"
-          if [ -n "${DOCS_GITHUB_TOKEN:-}" ]; then
-            echo -n "$DOCS_GITHUB_TOKEN" | gh secret set DOCS_GITHUB_TOKEN --repo "$TARGET"
-          fi
           echo "Synced CLAUDE_APP_ID, CLAUDE_APP_PRIVATE_KEY, CLAUDE_CODE_OAUTH_TOKEN, GH_TOKEN → $TARGET"

.github/workflows/test-optimized.yml

@@ -98,20 +98,6 @@ jobs:
           --ignore=tests/unit/cli/test_message_queue.py \
           --maxfail=5
 
-    - name: Run praisonai-agents subscription-auth smoke tests
-      env:
-        PRAISONAI_TEST_TIER: smoke
-        PRAISONAI_ALLOW_NETWORK: '0'
-        OPENAI_MODEL_NAME: gpt-4o-mini
-        OPENAI_API_KEY: 'test-key'
-      shell: bash
-      run: |
-        set -euo pipefail
-        cd src/praisonai-agents
-        python -m pytest tests/smoke/test_subscription_auth.py \
-          tests/unit/auth/test_agent_auth_wiring.py \
-          -q --tb=line --timeout=60 --maxfail=5
-
     - name: Standalone praisonai-code import smoke
       shell: bash
       run: |

README.md

@@ -130,7 +130,7 @@ Each layer wraps the one inside it. When an agent misbehaves, the layer tells yo
 | **3 · Harness** | Can it act, and be checked? | `tools=`, `MCP()`, `guardrails=`, `approval=`, `hooks=`, `sandbox=` |
 | **4 · Loop** | When do we stop? | `execution=ExecutionConfig(...)`, `reflection=`, `autonomy=`, doom-loop detection |
 | **5 · Graph** | Who runs when, and who checks whom? | `AgentFlow`, `route()`, `parallel()`, `loop()`, `repeat()` |
-| **⬡ Managed** | *Where does it actually run?* | `tools_run_on="docker"` — one shared sandbox for the tools, or `run_on="anthropic"` for the whole agent |
+| **⬡ Managed** | *Where does it actually run?* | `backend=ManagedAgent(compute="e2b")` — remote sandbox, or a fully hosted loop |
 
 ### Layer 1 · Prompt — *Did I say it clearly?*
 
@@ -195,6 +195,7 @@ from praisonaiagents import Agent, ExecutionConfig
 agent = Agent(
     instructions="Fix the failing tests.",
     execution=ExecutionConfig(max_iter=30, max_budget=0.50, on_budget_exceeded="stop"),
+    reflection=True,               # completion check — the agent grades its own answer
     autonomy=True,                 # required to drive the loop with run_autonomous()
 )
 result = agent.run_autonomous("Refactor the auth module", max_iterations=5)
@@ -235,85 +236,22 @@ The harness is commoditising; **where** the agent executes is the next multiplie
 pip install praisonai
 ```
 
-The simplest way in is `tools_run_on=` — one whole team or workflow shares **one** sandbox, so a file written by step 1 is there for step 2. Thinking stays on your machine:
-
 ```python
-from praisonaiagents import Agent, AgentFlow
+from praisonai import Agent, ManagedAgent, LocalManagedConfig
 
-writer = Agent(name="Writer", instructions="You write files.")
-reader = Agent(name="Reader", instructions="You read files.")
+# A. Tools run in a remote sandbox; the agent loop stays local
+sandboxed = ManagedAgent(
+    provider="local", compute="e2b",   # or modal | daytona | flyio | docker | tenki
+    config=LocalManagedConfig(model="gpt-4o-mini", name="RemoteTools"),
+)
+agent = Agent(name="builder", backend=sandboxed)
 
-flow = AgentFlow(tools_run_on="docker", steps=[writer, reader])  # or e2b | modal | daytona | flyio
-flow.run("Write 'hello' to /workspace/note.txt, then read it back")
-```
-
-Same thing with no Python at all:
-
-```yaml
-name: remote-demo
-tools_run_on: docker      # every step shares one sandbox
-agents:
-  writer: {role: Writer, goal: Write files}
-  reader: {role: Reader, goal: Read files}
-steps:
-  - agent: writer
-    action: "Write 'hello' to /workspace/note.txt"
-  - agent: reader
-    action: "Read /workspace/note.txt"
-```
-
-For a single agent, two words cover it — and they answer different questions:
-
-```python
-from praisonaiagents import Agent
-
-# A. Only the TOOLS move. Thinking stays on your machine.
-agent = Agent(name="builder", instructions="You build things.",
-              tools_run_on="docker")   # docker | e2b | modal | daytona | flyio
-                                       # tenki | sandlock | ssh | novita | subprocess
-
-# B. The WHOLE agent moves — model calls, loop and tools
-agent = Agent(name="teacher", instructions="You teach.", run_on="anthropic")  # hosted
-agent = Agent(name="builder", instructions="You build.", run_on="docker")     # self-hosted
+# B. The entire agent loop runs in the cloud (needs ANTHROPIC_API_KEY;
+#    with no key set, ManagedAgent() falls back to a local loop)
+agent = Agent(name="teacher", backend=ManagedAgent())
 agent.start("Write a Python script that prints the first 10 primes, then run it")
 ```
 
-Ask any object where it runs, and it will tell you:
-
-```python
->>> Agent(name="builder", instructions="x", tools_run_on="docker")
-Agent(name='builder', thinks_on='this machine', tools_run_on='a Docker container')
-
->>> agent.where_does_it_run()
-Thinking (the AI model calls) happens on this machine.
-Tools run on a Docker container.
-Your own tools (check_db) still run on this machine -- only shell, file and
-code tools move. They read and write this machine's files.
-```
-
-Naming a place that cannot do the job is a typo, not a preference, so it says so:
-
-```python
->>> Agent(name="x", instructions="i", run_on="e2b")
-TypeError: Agent(run_on='e2b') is not valid: run_on= places the whole agent
--- model calls, loop and tools -- on a managed runtime, and 'e2b' runs
-commands but cannot host an agent loop.
-  To run only the tools there:  Agent(tools_run_on='e2b')
-```
-
-To run one block of code somewhere else, name the place on that call:
-
-```python
-agent.execute_code_sync("print(6 * 7)", run_in="sandlock")   # kernel-enforced
-```
-
-See what is running and reclaim strays:
-
-```bash
-praisonai managed ps          # list running sandboxes
-praisonai managed stop --all  # reclaim them
-```
-
 Sandboxes shut themselves down when idle (`auto_shutdown`, `idle_timeout_s`), and a post-setup snapshot is reused so the next run skips the image pull and dependency install. Commit a `.praisonai/environment.yaml` and the environment travels with the repo.
 
 > 📖 [20 runnable examples](examples/python/managed-agents/) · manage sessions with `praisonai managed sessions list <agent-id>` or `praisonai managed sessions resume <session-id> "<prompt>"`

SECURITY.md

@@ -8,18 +8,11 @@ PraisonAI takes security seriously. We appreciate responsible disclosure from re
 |---------|----------|-------------|
 | `praisonaiagents` | [PyPI](https://pypi.org/project/praisonaiagents/) | `src/praisonai-agents/` |
 | `praisonai` | [PyPI](https://pypi.org/project/praisonai/) | `src/praisonai/` |
+| `praisonai-platform` | [PyPI](https://pypi.org/project/praisonai-platform/) | `src/praisonai-platform/` |
 | `praisonai` | [npm](https://www.npmjs.com/package/praisonai) | `src/praisonai-ts/` |
 
 Report issues against the **specific package** where the vulnerability exists. A platform-only issue does not necessarily affect the core SDK, and vice versa.
 
-### Packages maintained in their own repositories
-
-`praisonai-platform` now lives at
-[MervinPraison/PraisonAI-Platform](https://github.com/MervinPraison/PraisonAI-Platform).
-Report platform vulnerabilities through
-[that repository's advisories](https://github.com/MervinPraison/PraisonAI-Platform/security/advisories/new),
-not here — it is versioned and released independently of the SDK.
-
 ## In scope
 
 - Authentication, authorisation, and multi-tenant isolation (e.g. workspace boundaries)

api.md

@@ -7,7 +7,7 @@ Regenerate with: `praisonai docs api-md --write`
 
 Types:
 ```python
-from praisonaiagents import ContextPolicy, GuardrailResult, HandoffConfig, HandoffCycleError, HandoffDepthError, HandoffError, HandoffInputData, HandoffResult, HandoffTimeoutError, ReflectionOutput, StepResult, ToolResult, ToolValidationError, WorkflowContext
+from praisonaiagents import ContextPolicy, GuardrailResult, HandoffConfig, HandoffCycleError, HandoffDepthError, HandoffError, HandoffInputData, HandoffResult, HandoffTimeoutError, ReflectionOutput, StepResult, TaskOutput, ToolResult, ToolValidationError, WorkflowContext
 ```
 
 Methods:
@@ -16,6 +16,8 @@ Methods:
 * <code title="class HandoffConfig">HandoffConfig.<a href="./src/praisonai-agents/praisonaiagents/agent/handoff.py">from_dict</a>(data: Dict[str, Any]) -> 'HandoffConfig'</code>
 * <code title="class HandoffConfig">HandoffConfig.<a href="./src/praisonai-agents/praisonaiagents/agent/handoff.py">to_dict</a>() -> Dict[str, Any]</code>
 * <code title="class HandoffResult">HandoffResult.<a href="./src/praisonai-agents/praisonaiagents/agent/handoff.py">from_outcome</a>(outcome: AgentRunOutcome, target_agent: Optional[str] = None, source_agent: Optional[str] = None, handoff_depth: int = 0) -> 'HandoffResult'</code>
+* <code title="class TaskOutput">TaskOutput.<a href="./src/praisonai-agents/praisonaiagents/main.py">json</a>() -> Optional[str]</code>
+* <code title="class TaskOutput">TaskOutput.<a href="./src/praisonai-agents/praisonaiagents/main.py">to_dict</a>() -> dict</code>
 * <code title="class ToolResult">ToolResult.<a href="./src/praisonai-agents/praisonaiagents/tools/base.py">is_multimodal</a>() -> bool</code>
 * <code title="class ToolResult">ToolResult.<a href="./src/praisonai-agents/praisonaiagents/tools/base.py">to_dict</a>() -> Dict[str, Any]</code>
 
@@ -30,7 +32,6 @@ Methods:
 
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">aclose</a>() -> None</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">add_mcp_server</a>(name: str, mcp: Any) -> Any</code>
-* <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">add_verification</a>(hook: Any) -> None</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">agent_id</a>() -> str</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">analyze_prompt</a>(prompt: str) -> set</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">auto_memory</a>() -> Optional[bool]</code>
@@ -71,7 +72,6 @@ Methods:
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">redo</a>() -> bool</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">refresh_tools</a>() -> List[Any]</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">remove_mcp_server</a>(name: str) -> bool</code>
-* <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">remove_verification</a>(name: str) -> bool</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">retrieval_config</a>() -> Optional[Any]</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">retrieve</a>(query: str, **kwargs) -> 'ContextPack'</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">rules_manager</a>() -> Optional[Any]</code>
@@ -88,7 +88,6 @@ Methods:
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">thinking_budget</a>(value: Optional[int]) -> None</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">total_cost</a>() -> float</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">undo</a>() -> bool</code>
-* <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">where_does_it_run</a>() -> str</code>
 * <code title="class AutoAgents">AutoAgents.<a href="./src/praisonai-agents/praisonaiagents/agents/autoagents.py">astart</a>()</code>
 * <code title="class AutoAgents">AutoAgents.<a href="./src/praisonai-agents/praisonaiagents/agents/autoagents.py">start</a>()</code>
 * <code title="class AutoRagAgent">AutoRagAgent.<a href="./src/praisonai-agents/praisonaiagents/agents/auto_rag_agent.py">achat</a>(message: str, **kwargs) -> str</code>
@@ -240,12 +239,10 @@ from praisonaiagents import Memory, MemoryBackend, MemoryConfig
 
 Methods:
 
-* <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">acommit_memory_batch</a>(writes: List[tuple]) -> None</code>
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">build_cache_optimized_context</a>(task_descr: str, user_id: Optional[str] = None, additional: str = '', max_items: int = 3, include_cache_boundary: bool = True, include_in_output: Optional[bool] = None) -> Dict[str, str]</code>
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">build_context_for_task</a>(task_descr: str, user_id: Optional[str] = None, additional: str = '', max_items: int = 3, include_in_output: Optional[bool] = None) -> str</code>
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">calculate_quality_metrics</a>(output: str, expected_output: str, llm: Optional[str] = None, custom_prompt: Optional[str] = None) -> Dict[str, float]</code>
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">close_connections</a>()</code>
-* <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">commit_memory_batch</a>(writes: List[tuple]) -> None</code>
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">compute_quality_score</a>(completeness: float, relevance: float, clarity: float, accuracy: float, weights: Dict[str, float] = None) -> float</code>
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">delete_long_term</a>(memory_id: str) -> bool</code>
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">delete_memories</a>(memory_ids: List[str]) -> int</code>
@@ -255,7 +252,6 @@ Methods:
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">finalize_task_output</a>(content: str, agent_name: str, quality_score: float, threshold: float = 0.7, metrics: Dict[str, Any] = None, task_id: str = None)</code>
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">forget</a>(**kwargs) -> int</code>
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">get_all_memories</a>() -> List[Dict[str, Any]]</code>
-* <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">get_context</a>(query: Optional[str] = None, **kwargs) -> str</code>
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">get_learn_context</a>() -> str</code>
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">learn</a>()</code>
 * <code title="class Memory">Memory.<a href="./src/praisonai-agents/praisonaiagents/memory/memory.py">recall</a>(query: str, **kwargs) -> List[Dict[str, Any]]</code>
@@ -468,7 +464,7 @@ Methods:
 
 Types:
 ```python
-from praisonaiagents import SkillLoader, SkillsConfig
+from praisonaiagents import SkillLoader, SkillManager, SkillMetadata, SkillProperties, SkillsConfig
 ```
 
 Methods:
@@ -480,6 +476,55 @@ Methods:
 * <code title="class SkillLoader">SkillLoader.<a href="./src/praisonai-agents/praisonaiagents/skills/loader.py">load_metadata</a>(skill_path: str) -> Optional[LoadedSkill]</code>
 * <code title="class SkillLoader">SkillLoader.<a href="./src/praisonai-agents/praisonaiagents/skills/loader.py">load_references</a>(skill: LoadedSkill) -> dict</code>
 * <code title="class SkillLoader">SkillLoader.<a href="./src/praisonai-agents/praisonaiagents/skills/loader.py">load_scripts</a>(skill: LoadedSkill) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">activate</a>(skill: LoadedSkill) -> bool</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">activate_by_name</a>(name: str) -> bool</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">add_bundle</a>(manifest: 'BundleManifest') -> None</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">add_skill</a>(skill_path: str) -> Optional[LoadedSkill]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">add_skill_by_name</a>(name: str, skill_dirs: Optional[List[str]] = None, include_defaults: bool = True) -> Optional[LoadedSkill]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">approve</a>(identifier: str) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">archive_skill</a>(name: str) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">bundle_names</a>() -> List[str]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">bundles</a>() -> List['BundleManifest']</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">clear</a>() -> None</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">create</a>(name: str, content: str, category: Optional[str] = None, propose: Optional[bool] = None) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">create_skill</a>(name: str, content: str, category: str = None, agent_created: bool = True, propose: Optional[bool] = None, base_dir: Optional[str] = None) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">delete</a>(name: str, propose: Optional[bool] = None) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">delete_skill</a>(name: str, hard: bool = False, propose: Optional[bool] = None) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">discover</a>(skill_dirs: Optional[List[str]] = None, include_defaults: bool = True) -> int</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">discover_bundles</a>(skill_dirs: Optional[List[str]] = None, include_defaults: bool = True) -> int</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">edit</a>(name: str, content: str, propose: Optional[bool] = None) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">edit_skill</a>(name: str, content: str, propose: Optional[bool] = None) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">get_allowed_tools</a>(name: str) -> List[str]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">get_available_skills</a>() -> List[SkillMetadata]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">get_available_skills_by_state</a>(state: SkillState) -> List[LoadedSkill]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">get_bundle</a>(name: str) -> Optional['BundleManifest']</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">get_bundle_instructions</a>() -> List[str]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">get_instructions</a>(name: str) -> Optional[str]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">get_skill</a>(name: str) -> Optional[LoadedSkill]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">get_skills_diagnostics</a>() -> Dict[str, ValidationResult]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">get_user_invocable_skills</a>() -> List[LoadedSkill]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">invoke</a>(name: str, raw_args: str = '', session_id: Optional[str] = None, shell_exec: bool = False) -> Optional[str]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">list_archived_skills</a>() -> List[str]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">list_pending</a>() -> List[dict]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">load_resources</a>(name: str) -> bool</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">patch</a>(name: str, old_string: str, new_string: str, file_path: Optional[str] = None, replace_all: bool = False, propose: Optional[bool] = None) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">patch_skill</a>(name: str, old_string: str, new_string: str, file_path: str = None, replace_all: bool = False, propose: Optional[bool] = None) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">reject</a>(identifier: str) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">reload</a>() -> Dict[str, List[str]]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">remove_file</a>(name: str, file_path: str, propose: Optional[bool] = None) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">remove_skill_file</a>(name: str, file_path: str, propose: Optional[bool] = None) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">resolve</a>(selectors: List[str]) -> List[str]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">restore_skill</a>(name: str, skill_dir: Optional[str] = None) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">rollback_skill</a>(name: str) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">skill_names</a>() -> List[str]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">skills</a>() -> List[LoadedSkill]</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">to_prompt</a>() -> str</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">validate_skill_capabilities</a>(skill_name: str, force_refresh: bool = False) -> ValidationResult</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">write_file</a>(name: str, file_path: str, file_content: str, propose: Optional[bool] = None) -> dict</code>
+* <code title="class SkillManager">SkillManager.<a href="./src/praisonai-agents/praisonaiagents/skills/manager.py">write_skill_file</a>(name: str, file_path: str, file_content: str, propose: Optional[bool] = None) -> dict</code>
+* <code title="class SkillMetadata">SkillMetadata.<a href="./src/praisonai-agents/praisonaiagents/skills/models.py">from_properties</a>(props: SkillProperties) -> 'SkillMetadata'</code>
+* <code title="class SkillProperties">SkillProperties.<a href="./src/praisonai-agents/praisonaiagents/skills/models.py">idle_days</a>() -> Optional[float]</code>
+* <code title="class SkillProperties">SkillProperties.<a href="./src/praisonai-agents/praisonaiagents/skills/models.py">to_dict</a>() -> dict</code>
 * <code title="class SkillsConfig">SkillsConfig.<a href="./src/praisonai-agents/praisonaiagents/config/feature_configs.py">to_dict</a>() -> Dict[str, Any]</code>
 
 # Session
@@ -712,7 +757,6 @@ Methods:
 * <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">to_dict</a>() -> Dict[str, Any]</code>
 * <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">verbose</a>() -> bool</code>
 * <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">verbose</a>(value: bool)</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">where_does_it_run</a>() -> str</code>
 * <code title="class AgentOSProtocol">AgentOSProtocol.<a href="./src/praisonai-agents/praisonaiagents/app/protocols.py">get_app</a>() -> Any</code>
 * <code title="class AgentOSProtocol">AgentOSProtocol.<a href="./src/praisonai-agents/praisonaiagents/app/protocols.py">serve</a>(host: Optional[str] = None, port: Optional[int] = None, reload: bool = False, **kwargs: Any) -> None</code>
 * <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">aannounce_completion</a>(agent_id: str, task_id: str, result: Any, success: bool = True, error: Optional[str] = None, metadata: Optional[Dict[str, Any]] = None) -> None</code>
@@ -749,7 +793,7 @@ Methods:
 * <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_token_usage_summary</a>() -> Dict[str, Any]</code>
 * <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">has_state</a>(key: str) -> bool</code>
 * <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">increment_state</a>(key: str, amount: float = 1, default: float = 0) -> float</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">launch</a>(path: str = '/agents', port: int = 8000, host: str = '127.0.0.1', debug: bool = False, protocol: str = 'http')</code>
+* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">launch</a>(path: str = '/agents', port: int = 8000, host: str = '0.0.0.0', debug: bool = False, protocol: str = 'http')</code>
 * <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">restore_session_state</a>(session_id: str) -> bool</code>
 * <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">run</a>(content = None, return_dict = False, **kwargs)</code>
 * <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">run_all_tasks</a>()</code>
@@ -765,7 +809,6 @@ Methods:
 * <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">update_plan_step_status</a>(step_id: str, status: str) -> bool</code>
 * <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">update_state</a>(updates: Dict) -> None</code>
 * <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">wait_for_completions</a>(timeout: Optional[float] = None, agent_ids: Optional[List[str]] = None) -> List[SubAgentCompletionEvent]</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">where_does_it_run</a>() -> str</code>
 * <code title="class AutoApproveBackend">AutoApproveBackend.<a href="./src/praisonai-agents/praisonaiagents/approval/backends.py">request_approval</a>(request: ApprovalRequest) -> ApprovalDecision</code>
 * <code title="class AutoApproveBackend">AutoApproveBackend.<a href="./src/praisonai-agents/praisonaiagents/approval/backends.py">request_approval_sync</a>(request: ApprovalRequest) -> ApprovalDecision</code>
 * <code title="class RunOutcome">RunOutcome.<a href="./src/praisonai-agents/praisonaiagents/agent/run_outcome.py">completed</a>(output: Optional[str] = None) -> 'RunOutcome'</code>
@@ -847,13 +890,11 @@ Methods:
 * <code title="cli">praisonai managed list <a href="./src/praisonai/praisonai/cli/commands/managed.py">--help</a></code>
 * <code title="cli">praisonai managed managed-callback <a href="./src/praisonai/praisonai/cli/commands/managed.py">--help</a></code>
 * <code title="cli">praisonai managed multi <a href="./src/praisonai/praisonai/cli/commands/managed.py">--help</a></code>
-* <code title="cli">praisonai managed ps <a href="./src/praisonai/praisonai/cli/commands/managed.py">--help</a></code>
 * <code title="cli">praisonai managed restore <a href="./src/praisonai/praisonai/cli/commands/managed.py">--help</a></code>
 * <code title="cli">praisonai managed resume <a href="./src/praisonai/praisonai/cli/commands/managed.py">--help</a></code>
 * <code title="cli">praisonai managed run <a href="./src/praisonai/praisonai/cli/commands/managed.py">--help</a></code>
 * <code title="cli">praisonai managed save <a href="./src/praisonai/praisonai/cli/commands/managed.py">--help</a></code>
 * <code title="cli">praisonai managed show <a href="./src/praisonai/praisonai/cli/commands/managed.py">--help</a></code>
-* <code title="cli">praisonai managed stop <a href="./src/praisonai/praisonai/cli/commands/managed.py">--help</a></code>
 * <code title="cli">praisonai managed update <a href="./src/praisonai/praisonai/cli/commands/managed.py">--help</a></code>
 * <code title="cli">praisonai n8n export <a href="./src/praisonai/praisonai/cli/commands/n8n.py">--help</a></code>
 * <code title="cli">praisonai n8n import <a href="./src/praisonai/praisonai/cli/commands/n8n.py">--help</a></code>
@@ -883,7 +924,6 @@ Methods:
 * <code title="cli">praisonai recipe list <a href="./src/praisonai/praisonai/cli/commands/recipe.py">--help</a></code>
 * <code title="cli">praisonai recipe optimize <a href="./src/praisonai/praisonai/cli/commands/recipe.py">--help</a></code>
 * <code title="cli">praisonai recipe run <a href="./src/praisonai/praisonai/cli/commands/recipe.py">--help</a></code>
-* <code title="cli">praisonai recipe runs <a href="./src/praisonai/praisonai/cli/commands/recipe.py">--help</a></code>
 * <code title="cli">praisonai recipe serve <a href="./src/praisonai/praisonai/cli/commands/recipe.py">--help</a></code>
 * <code title="cli">praisonai replay cleanup <a href="./src/praisonai/praisonai/cli/commands/replay.py">--help</a></code>
 * <code title="cli">praisonai replay context <a href="./src/praisonai/praisonai/cli/commands/replay.py">--help</a></code>
@@ -900,11 +940,7 @@ Methods:
 * <code title="cli">praisonai schedule describe <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
 * <code title="cli">praisonai schedule list <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
 * <code title="cli">praisonai schedule logs <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
-* <code title="cli">praisonai schedule pause <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
-* <code title="cli">praisonai schedule remove <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
 * <code title="cli">praisonai schedule restart <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
-* <code title="cli">praisonai schedule resume <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
-* <code title="cli">praisonai schedule runs <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
 * <code title="cli">praisonai schedule schedule-callback <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
 * <code title="cli">praisonai schedule start <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
 * <code title="cli">praisonai schedule stats <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
@@ -913,7 +949,6 @@ Methods:
 * <code title="cli">praisonai schedule suggestion-dismiss <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
 * <code title="cli">praisonai schedule suggestion-propose <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
 * <code title="cli">praisonai schedule suggestions <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
-* <code title="cli">praisonai schedule update <a href="./src/praisonai/praisonai/cli/commands/schedule.py">--help</a></code>
 * <code title="cli">praisonai validate check <a href="./src/praisonai/praisonai/cli/commands/validate.py">--help</a></code>
 * <code title="cli">praisonai validate schema <a href="./src/praisonai/praisonai/cli/commands/validate.py">--help</a></code>
 * <code title="cli">praisonai validate validate <a href="./src/praisonai/praisonai/cli/commands/validate.py">--help</a></code>

docker/Dockerfile.chat

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=4.7.1" \
+    "praisonai>=4.6.162" \
     "praisonai[chat]" \
     "embedchain[github,youtube]"
 

docker/Dockerfile.dev

@@ -20,7 +20,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=4.7.1" \
+    "praisonai>=4.6.162" \
     "praisonai[ui]" \
     "praisonai[chat]" \
     "praisonai[realtime]" \

docker/Dockerfile.ui

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=4.7.1" \
+    "praisonai>=4.6.162" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

examples/middleware/hol_guard_tool_policy.py

@@ -1,110 +0,0 @@
-"""
-HOL Guard Tool Policy Example - PraisonAI Agents
-
-Demonstrates using HOL Guard (an optional, external runtime security engine)
-at the existing `wrap_tool_call` middleware boundary to inspect command-bearing
-tool calls *before* they execute.
-
-HOL Guard is installed and versioned separately. Its side-effect-free CLI can
-classify a shell command before execution:
-
-    hol-guard command test '<command>' --json
-
-Fail-closed policy: the wrapped tool only runs when Guard returns an explicit
-allow/benign classification. Review/block/unknown verdicts, malformed output,
-timeouts, or CLI failures all short-circuit the call so the tool never runs.
-
-    pip install hol-guard   # optional, external dependency
-"""
-
-import json
-import shutil
-import subprocess
-
-from praisonaiagents import Agent, tool
-from praisonaiagents.hooks import wrap_tool_call, ToolRequest, ToolResponse
-
-
-COMMAND_BEARING_TOOLS = {"run_shell"}
-GUARD_TIMEOUT_SECONDS = 10
-
-
-@tool
-def run_shell(command: str) -> str:
-    """Run a shell command and return its output."""
-    result = subprocess.run(
-        command, shell=True, capture_output=True, text=True
-    )
-    return result.stdout or result.stderr
-
-
-def _inspect_with_hol_guard(command: str) -> bool:
-    """Return True only if HOL Guard explicitly allows the command.
-
-    Fails closed (returns False) on any ambiguity: missing CLI, non-zero exit,
-    timeout, malformed JSON, or a non-allow verdict.
-    """
-    if not shutil.which("hol-guard"):
-        return False
-
-    try:
-        completed = subprocess.run(
-            ["hol-guard", "command", "test", command, "--json"],
-            capture_output=True,
-            text=True,
-            timeout=GUARD_TIMEOUT_SECONDS,
-        )
-    except (subprocess.TimeoutExpired, OSError):
-        return False
-
-    if completed.returncode != 0:
-        return False
-
-    try:
-        verdict = json.loads(completed.stdout)
-    except (json.JSONDecodeError, ValueError):
-        return False
-
-    if not isinstance(verdict, dict):
-        return False
-
-    decision = str(verdict.get("decision", "")).lower()
-    return decision in ("allow", "benign")
-
-
-@wrap_tool_call
-def hol_guard_tool_policy(request: ToolRequest, call_next):
-    """Gate command-bearing tools through HOL Guard before execution."""
-    if request.tool_name not in COMMAND_BEARING_TOOLS:
-        return call_next(request)
-
-    command = request.arguments.get("command", "")
-
-    if _inspect_with_hol_guard(command):
-        return call_next(request)
-
-    blocked_message = "Blocked by HOL Guard: command was not explicitly allowed."
-    # Surface the denial in `result` too: the agent tool executor returns
-    # `ToolResponse.result` to the model and discards `error`, so a denial with
-    # only `error` set would reach the model as a null result. Keeping `error`
-    # populated preserves the signal for after_tool hooks and logging.
-    return ToolResponse(
-        tool_name=request.tool_name,
-        result=blocked_message,
-        error=blocked_message,
-        context=request.context,
-    )
-
-
-agent = Agent(
-    name="GuardedShellBot",
-    instructions="You run shell commands only when they are safe.",
-    tools=[run_shell],
-    hooks=[hol_guard_tool_policy],
-)
-
-
-if __name__ == "__main__":
-    print("HOL Guard tool policy registered on 'run_shell'.")
-    print("Commands are only executed when Guard returns an explicit allow.")
-    print("\n✓ HOL Guard example complete")

examples/persistence/state_redis.py

@@ -14,7 +14,7 @@ Expected Output:
     Agent responds with state persisted to Redis
 """
 
-from praisonaiagents import Agent, MemoryConfig
+from praisonaiagents import Agent
 from praisonaiagents.db import db
 
 print("=== Redis State Store (Agent-First) ===")
@@ -28,7 +28,8 @@ my_db = db(
 agent = Agent(
     name="Assistant",
     instructions="You are a helpful assistant.",
-    memory=MemoryConfig(db=my_db, session_id="redis-state-example"),
+    memory=my_db,
+    session_id="redis-state-example"
 )
 
 # Chat - state is automatically managed via Redis

examples/python/autonomy/03_verification_hooks.py

@@ -23,7 +23,6 @@ from praisonaiagents.hooks.verification import (
     VerificationResult,
     BaseVerificationHook,
     CommandVerificationHook,
-    FileCheckHook,
 )
 
 
@@ -101,19 +100,7 @@ def main():
     print(f"   Name: {cmd_hook.name}")
     print(f"   Command: {cmd_hook.command}")
     print(f"   Timeout: {cmd_hook.timeout_seconds}s")
-
-    # 6. FileCheckHook: declarative, no-shell completion gate
-    print("\n6. FileCheckHook (declarative completion gate):")
-    file_hook = FileCheckHook(
-        name="changelog", path="CHANGELOG.md", non_empty=True
-    )
-    file_result = file_hook.run()
-    print(f"   {file_hook.name}: success={file_result.success} — {file_result.output}")
-    print(
-        "   Gate wiring: when verification_hooks are configured, the autonomous "
-        "loop cannot finalise with a success outcome while a blocking hook fails."
-    )
-
+    
     print("\n" + "=" * 60)
     print("✓ Verification hooks example completed successfully!")
     print("=" * 60)

examples/python/mcp/filesystem-mcp.py

@@ -7,12 +7,12 @@ allowed_dirs = [
     "/path/to/other/allowed/dir"
 ]
 
-# Pass the executable as the first token and the allowed directories as args
+# Use a single string command with allowed directories
 filesystem_agent = Agent(
     instructions="""You are a helpful assistant that can interact with the filesystem.
     Use the available tools when relevant to manage files and directories.""",
     llm="gpt-4o-mini",
-    tools=MCP("npx", args=["-y", "@modelcontextprotocol/server-filesystem", *allowed_dirs])
+    tools=MCP("npx -y @modelcontextprotocol/server-filesystem", args=allowed_dirs)
 )
 
 filesystem_agent.start("List files in the allowed directories") 

examples/serve/README.md

@@ -24,7 +24,7 @@ Examples for all PraisonAI server types and the unified endpoints CLI.
 | `praisonai serve unified --port 8765` | Start unified server |
 | `praisonai serve agents --file agents.yaml --port 8000` | Start agents API |
 | `praisonai serve recipe --port 8765` | Start recipe server |
-| `praisonai mcp serve --transport http-stream --port 8080` | Start MCP server |
+| `praisonai serve mcp --transport http --port 8080` | Start MCP server |
 | `praisonai serve tools --port 8081` | Start tools MCP server |
 | `praisonai serve a2a --port 8082` | Start A2A server |
 | `praisonai serve a2u --port 8083` | Start A2U server |

examples/serve/mcp_http_server.py

@@ -13,7 +13,7 @@ Usage:
     python mcp_http_server.py
     
     # Or use CLI:
-    praisonai mcp serve --transport http-stream --port 8080
+    praisonai serve mcp --transport http --port 8080
     
     # Test with curl:
     curl http://localhost:8080/mcp/tools

examples/terminal_bench/job_code_smoke.yaml

@@ -14,9 +14,9 @@ datasets:
     # A small verified subset for a cheap smoke run. Verify against the registry
     # with `harbor datasets list` before editing.
     task_names:
-      - terminal-bench/build-pmars
-      - terminal-bench/bn-fit-modify
-      - terminal-bench/break-filter-js-from-html
+      - hello-world
+      - fix-permissions
+      - csv-to-parquet
 
 agents:
   - import_path: examples.terminal_bench.praisonai_code_agent:PraisonAICodeAgent

examples/terminal_bench/praisonai_code_agent.py

@@ -81,19 +81,21 @@ class PraisonAICodeAgent(BaseInstalledAgent):
         model = self.model_name or "openai/gpt-4o-mini"
 
         command = (
-            "log_file=$(mktemp /tmp/praisonai_code.XXXXXX); "
-            "chmod 600 \"$log_file\"; "
+            # Private per-run log (mktemp, 0600) instead of a predictable
+            # /tmp/praisonai_code.log path another process could pre-create as a
+            # symlink to redirect/clobber a file writable by the agent user.
+            "log=$(mktemp /tmp/praisonai_code.XXXXXX.log); "
             f"praisonai code -p --output json {shlex.quote(instruction)} "
             f"--dangerously-skip-approval "
             f"--model {shlex.quote(model)} "
-            "> \"$log_file\" 2>&1; "
+            '> "$log" 2>&1; '
             # Capture the real exit status so install/auth/startup failures still
             # surface instead of being silently masked (Harbor otherwise records a
             # completed attempt for a crashed agent).
             "status=$?; "
-            # Echo the envelope so Harbor captures it for post-run accounting.
-            "cat \"$log_file\"; "
-            "rm -f \"$log_file\"; "
+            # Echo the envelope so Harbor captures it for post-run accounting,
+            # then remove the private log.
+            'cat "$log"; rm -f "$log"; '
             # `praisonai code` normally exits 0 (Harbor grades by task
             # verification), so a genuine benchmark miss won't fail here — but a
             # nonzero status means the assistant itself failed to run.

examples/terminal_bench/praisonai_external_agent.py

@@ -34,7 +34,6 @@ except ImportError as e:
 try:
     from praisonaiagents import Agent
     from praisonaiagents.approval import get_approval_registry, AutoApproveBackend
-    from praisonaiagents.config.feature_configs import ExecutionConfig
 except ImportError as e:
     raise ImportError(
         f"PraisonAI not installed: {e}\n"
@@ -42,13 +41,6 @@ except ImportError as e:
     ) from e
 
 
-TB_EXECUTION = ExecutionConfig(
-    max_tool_calls_per_turn=80,
-    max_iter=40,
-    max_steps=80,
-)
-
-
 class PraisonAIExternalAgent(BaseAgent):
     """External PraisonAI agent that drives a Harbor container environment."""
 
@@ -150,14 +142,26 @@ class PraisonAIExternalAgent(BaseAgent):
                 ),
                 tools=[bash_tool],
                 llm=self.model_name or "openai/gpt-4o-mini",
-                execution=TB_EXECUTION,
             )
 
-            # Execute one deliberately long coding turn. Harbor's hidden verifier
-            # is the only completion authority; model or pytest text is not.
+            # Execute the agent with outer loop to handle premature stopping
             print(f"🚀 PraisonAI Agent starting task: {instruction[:100]}...")
             result = await agent.achat(instruction)
-            print("✅ PraisonAI Agent completed task")
+            for _iter in range(19):
+                result_str = str(result)
+                # Stop if test passed
+                if any(sig in result_str.lower() for sig in [
+                    " passed", "passed ", "test passed", "all tests pass", "1 passed"
+                ]):
+                    break
+                result = await agent.achat(
+                    "The task is NOT complete yet — keep working. Run bash_tool commands now. "
+                    "If you haven't already: (1) read all files in /app/, "
+                    "(2) run the test to see the exact failure, "
+                    "(3) implement a fix, (4) run the test again. "
+                    "Repeat until the test passes. What is your next bash_tool command?"
+                )
+            print(f"✅ PraisonAI Agent completed task")
             
             # Populate Harbor context with metadata
             self._populate_context(agent, context, result)
@@ -199,10 +203,6 @@ class PraisonAIExternalAgent(BaseAgent):
                 "tools_used": ["bash_tool"],
                 "framework": "praisonai",
                 "version": self.version(),
-                "stop_reason": getattr(agent, "last_stop_reason", None),
-                "max_tool_calls_per_turn": TB_EXECUTION.max_tool_calls_per_turn,
-                "max_iter": TB_EXECUTION.max_iter,
-                "max_steps": TB_EXECUTION.max_steps,
             }
             
         except Exception as e:
@@ -218,4 +218,4 @@ if __name__ == "__main__":
     print("  --model openai/gpt-4o-mini")
     print()
     print("Dependencies:")
-    print("  pip install harbor praisonaiagents")
+    print("  pip install harbor praisonaiagents")

examples/terminal_bench/test_adapter_config.py

@@ -1,39 +0,0 @@
-"""Static regression checks for the in-tree Harbor adapter configuration."""
-
-from pathlib import Path
-
-import yaml
-
-
-EXAMPLES = Path(__file__).parent
-
-
-def test_external_adapter_sets_coding_execution_budget():
-    source = (EXAMPLES / "praisonai_external_agent.py").read_text(encoding="utf-8")
-
-    assert "ExecutionConfig" in source
-    assert "max_tool_calls_per_turn=80" in source
-    assert "max_iter=40" in source
-    assert "max_steps=80" in source
-
-
-def test_external_adapter_does_not_guess_completion_from_pytest_text():
-    source = (EXAMPLES / "praisonai_external_agent.py").read_text(encoding="utf-8")
-
-    assert '"1 passed"' not in source
-    assert '"test passed"' not in source
-
-
-def test_smoke_yaml_uses_terminal_bench_21_registry_ids():
-    job = yaml.safe_load(
-        (EXAMPLES / "job_code_smoke.yaml").read_text(encoding="utf-8")
-    )
-    names = job["datasets"][0]["task_names"]
-
-    assert names
-    assert all(name.startswith("terminal-bench/") for name in names)
-    assert names == [
-        "terminal-bench/build-pmars",
-        "terminal-bench/bn-fit-modify",
-        "terminal-bench/break-filter-js-from-html",
-    ]

examples/yaml/workflows/remote_sandbox_workflow.yaml

@@ -1,45 +0,0 @@
-# Run a whole workflow's shell/file tools inside ONE shared remote sandbox.
-#
-#   praisonai examples/yaml/workflows/remote_sandbox_workflow.yaml
-#
-# `tools_run_on:` is the only line that differs from a normal local workflow.
-# Every step shares the same sandbox and working directory, so the file the
-# writer creates is there for the reader. Thinking and orchestration still run
-# on your machine, and the sandbox is torn down when the run finishes.
-#
-# Places: docker | e2b | modal | daytona | flyio | tenki | local
-#         subprocess | sandlock | ssh | novita
-#   - docker needs a local Docker daemon and nothing else
-#   - e2b / modal / daytona / flyio need that provider's API key
-#   - sandlock is a kernel-enforced local boundary (Linux 6.12+)
-#   - subprocess is process separation only, NOT a security boundary
-#
-# `run_on:` is still accepted here as the old spelling for this key.
-#
-# See what is still running:  praisonai managed ps
-# Reclaim strays:             praisonai managed stop --all
-
-name: remote-sandbox-demo
-tools_run_on: docker
-
-agents:
-  writer:
-    role: File Writer
-    goal: Write files into the shared workspace
-    instructions: >
-      You have write_file and execute_command running on a remote Linux
-      sandbox. Use them; never say you cannot run commands.
-
-  reader:
-    role: File Reader
-    goal: Read files back out of the shared workspace
-    instructions: >
-      You have read_file and execute_command running on the same remote
-      sandbox the writer used. Use them.
-
-steps:
-  - agent: writer
-    action: "Use write_file to put exactly 'hello from step 1' in /workspace/note.txt"
-
-  - agent: reader
-    action: "Use read_file on /workspace/note.txt and report its exact contents"

src/praisonai-agents/.agent/workflows/security-audit.md

@@ -99,12 +99,13 @@ pip index versions praisonaiagents | head -1
 pip index versions praisonai | head -1
 ```
 
-13. **praisonai-platform** advisories are handled in a different repository:
-[MervinPraison/PraisonAI-Platform](https://github.com/MervinPraison/PraisonAI-Platform).
-It is not part of this monorepo and is not published from here. Triage, patch,
-release and advisory publication all happen in that repo, on its own semver line.
-Nothing in this repository imports it, so a platform advisory never requires an
-SDK release.
+13. Publish **praisonai-platform** (only when the advisory targets platform code):
+```bash
+cd /Users/praison/praisonai-package/src/praisonai-platform
+praisonai publish pypi
+# or: uv lock && uv build && uv publish --token $PYPI_TOKEN
+```
+Platform releases are **independent** of `praisonai` / `praisonaiagents` version numbers. A platform-only fix (e.g. `0.1.8`) does **not** require bumping the main SDK.
 
 14. Publish **praisonai (npm / TypeScript)** (only when the advisory targets `src/praisonai-ts`):
 ```bash
@@ -112,8 +113,9 @@ cd /Users/praison/praisonai-package/src/praisonai-ts
 npm version patch && npm publish
 ```
 
-15. Verify npm when applicable:
+15. Verify platform / npm when applicable:
 ```bash
+pip index versions praisonai-platform | head -1
 npm view praisonai version
 ```
 
@@ -137,7 +139,7 @@ gh api repos/MervinPraison/PraisonAI/security-advisories/<GHSA_ID> \
 }
 EOF
 ```
-- `<PACKAGE_NAME>`: `praisonaiagents` (core SDK), `praisonai` (Python wrapper), or `praisonai` (npm ecosystem for TypeScript)
+- `<PACKAGE_NAME>`: `praisonaiagents` (core SDK), `praisonai` (Python wrapper), `praisonai-platform` (platform layer), or `praisonai` (npm ecosystem for TypeScript)
 - `<LAST_VULNERABLE_VERSION>`: version before the fix
 - `<FIRST_PATCHED_VERSION>`: the version just published with the fix
 - Always include credits for the reporter
@@ -188,8 +190,8 @@ After validating each advisory in source code, assign **one** label:
 | Package | Version line | Notes |
 |---|---|---|
 | `praisonaiagents` + `praisonai` | Aligned patch (e.g. `1.6.62` / `4.6.62`) | Main SDK + wrapper; bump together via `bump_and_release.py` |
+| `praisonai-platform` | Independent semver (e.g. `0.1.8`) | Platform-only fixes; users need **not** upgrade the main SDK |
 | `praisonai` (npm) | Independent semver (e.g. `1.7.2`) | TypeScript SDK; publish from `src/praisonai-ts` |
-| `praisonai-platform` | Independent semver, **separate repository** | Not released from this repo — see [PraisonAI-Platform](https://github.com/MervinPraison/PraisonAI-Platform) |
 
 Always set the advisory `patched_versions` to the **package that actually contains the fix**. Do not imply users must upgrade all packages when only one changed.
 
@@ -215,11 +217,9 @@ Close (or publish advisory with no code change only if already mitigated) when:
 |---|---|---|---|
 | praisonaiagents | pip | src/praisonai-agents/praisonaiagents/ | tools/, mcp/, memory/, agent/, sandbox/ |
 | praisonai | pip | src/praisonai/praisonai/ | cli/, capabilities/, mcp_server/, sandbox/, recipe/ |
+| praisonai-platform | pip | src/praisonai-platform/praisonai_platform/ | api/routes/, services/, auth |
 | praisonai | npm | src/praisonai-ts/src/ | agent/, mcp/, tools/, code-mode/ |
 
-`praisonai-platform` is **not audited from this repository** — it lives in
-[MervinPraison/PraisonAI-Platform](https://github.com/MervinPraison/PraisonAI-Platform).
-
 ## RESOURCES & DOCUMENTATION
 
 - **Official Repository**: https://github.com/MervinPraison/PraisonAI — Source code, issue tracking, and contribution guidelines
@@ -234,7 +234,7 @@ Close (or publish advisory with no code change only if already mitigated) when:
 - ALWAYS set patched_versions before publishing advisory
 - ALWAYS publish to PyPI/npm BEFORE publishing advisories (so Dependabot can point users to a fix)
 - Python SDK: `praisonai publish pypi` from `src/praisonai-agents`, then `bump_and_release.py` for the wrapper
-- Platform-only: released from the separate [PraisonAI-Platform](https://github.com/MervinPraison/PraisonAI-Platform) repo, never from here
+- Platform-only: `praisonai publish pypi` from `src/praisonai-platform` — no SDK bump required
 - npm: `npm publish` from `src/praisonai-ts` when the TypeScript SDK is affected
 - ALWAYS request CVE AFTER publishing advisory
 - Use generic commit messages: "refactor: harden X" not "fix: SQL injection in Y"

src/praisonai-agents/AGENTS.md

@@ -1074,7 +1074,7 @@ PraisonAI's reliability engineering rests on three pillars — **C**ontext, **H*
 > **Evaluator status.** The `ContextEvaluator` / `HarnessEvaluator` / `LoopEvaluator` classes named in the rubric are **planned follow-ups** (PA-CHL-001–004), not yet in the repo. Until they land, the equivalent checks are covered by existing modules:
 >
 > - **Context** — `context/tokens.py` and `eval/tokens.py` (`estimate_tokens` / `count_tokens`) for budget; `compaction/compactor.py` (`ContextCompactor`) for compaction/retention.
-> - **Harness** — `runtime/turn_context.py` for turn-context parity; `examples/runtime/example_harness.py` and `tests/` for harness/artifact checks.
+> - **Harness** — `runtime/turn_context.py` for turn-context parity; `runtime/example_harness.py` and `tests/` for harness/artifact checks.
 > - **Loop** — `eval/loop.py` (`EvaluationLoop`) and `agent/autonomy.py` for convergence and doom-loop guards.
 >
 > Keep terminology consistent with the `agent/context_agent.py` (`ContextAgent`) PRP methodology.

src/praisonai-agents/DOCS_PARITY.md

@@ -18,76 +18,76 @@ This report compares **Python SDK feature categories** against **Python document
 | Category | Features | Docs | Lines |
 |----------|----------|------|-------|
 | ✅ AGUI | 1 | 2 | 420 |
-| ✅ Agent | 22 | 53 | 17053 |
+| ✅ Agent | 22 | 50 | 15809 |
 | ✅ Agent-to-Agent (A2A) | 1 | 7 | 2996 |
 | ✅ Agent-to-User (A2U) | 1 | 3 | 689 |
-| ✅ Approval | 1 | 5 | 2658 |
+| ✅ Approval | 1 | 5 | 2537 |
 | ✅ Audio | 2 | 12 | 1000 |
-| ✅ Auto Generation | 5 | 11 | 3542 |
-| ✅ Autonomy | 3 | 7 | 2790 |
-| ✅ Bots | 7 | 31 | 13411 |
+| ✅ Auto Generation | 5 | 10 | 3049 |
+| ✅ Autonomy | 3 | 7 | 2744 |
+| ✅ Bots | 7 | 31 | 13314 |
 | ✅ Budget | 1 | 1 | 287 |
-| ✅ CLI | 5 | 122 | 36734 |
-| ✅ Chunking | 2 | 2 | 420 |
+| ✅ CLI | 5 | 121 | 36021 |
+| ✅ Chunking | 2 | 2 | 385 |
 | ✅ Citations | 2 | 1 | 202 |
-| ✅ Code Execution | 2 | 14 | 4855 |
-| ✅ Conditions | 1 | 3 | 1347 |
-| ✅ Configuration | 3 | 8 | 3139 |
-| ✅ Context Management | 16 | 36 | 13988 |
+| ✅ Code Execution | 2 | 14 | 4583 |
+| ✅ Conditions | 1 | 3 | 1179 |
+| ✅ Configuration | 3 | 8 | 3047 |
+| ✅ Context Management | 16 | 34 | 13396 |
 | ✅ Deep Research | 8 | 2 | 587 |
 | ✅ Display | 6 | 3 | 741 |
 | ✅ Embeddings | 6 | 23 | 2049 |
-| ✅ Evaluation | 1 | 7 | 2920 |
+| ✅ Evaluation | 1 | 7 | 2905 |
 | ✅ Events | 1 | 2 | 749 |
-| ✅ Execution | 3 | 4 | 1606 |
-| ✅ Failover | 2 | 1 | 452 |
-| ✅ Files | 2 | 7 | 2275 |
+| ✅ Execution | 3 | 4 | 1562 |
+| ✅ Failover | 2 | 1 | 432 |
+| ✅ Files | 2 | 7 | 2273 |
 | ✅ Flow | 1 | 3 | 788 |
-| ✅ Gateway | 7 | 81 | 29955 |
-| ✅ Guardrails | 4 | 4 | 2205 |
-| ✅ Handoffs | 11 | 6 | 2626 |
-| ✅ Hooks | 2 | 9 | 4509 |
+| ✅ Gateway | 7 | 72 | 26391 |
+| ✅ Guardrails | 4 | 4 | 2017 |
+| ✅ Handoffs | 11 | 6 | 2563 |
+| ✅ Hooks | 2 | 9 | 4317 |
 | ✅ Image | 1 | 11 | 1255 |
-| ✅ Knowledge | 4 | 16 | 4942 |
-| ✅ LLM | 3 | 15 | 5372 |
-| ✅ Loops | 4 | 5 | 1475 |
-| ✅ MCP | 1 | 61 | 14135 |
-| ✅ Memory | 6 | 18 | 7187 |
+| ✅ Knowledge | 4 | 13 | 4333 |
+| ✅ LLM | 3 | 15 | 5192 |
+| ✅ Loops | 4 | 5 | 1422 |
+| ✅ MCP | 1 | 61 | 13847 |
+| ✅ Memory | 6 | 18 | 7070 |
 | ✅ OCR | 2 | 1 | 237 |
-| ✅ Observability | 2 | 23 | 2811 |
+| ✅ Observability | 2 | 23 | 2814 |
 | ✅ Optimizer | 1 | 2 | 792 |
-| ✅ Output | 3 | 5 | 1265 |
+| ✅ Output | 3 | 5 | 1201 |
 | ✅ Parallel Execution | 3 | 2 | 497 |
-| ✅ Planning | 6 | 6 | 1605 |
-| ✅ Plugins | 8 | 5 | 3120 |
-| ✅ Prompts | 2 | 9 | 1971 |
-| ✅ Providers | 1 | 56 | 7781 |
+| ✅ Planning | 6 | 6 | 1549 |
+| ✅ Plugins | 8 | 4 | 2850 |
+| ✅ Prompts | 2 | 9 | 1965 |
+| ✅ Providers | 1 | 56 | 7735 |
 | ✅ Query | 1 | 2 | 736 |
-| ✅ RAG | 5 | 15 | 3118 |
+| ✅ RAG | 5 | 15 | 3003 |
 | ✅ Realtime | 2 | 5 | 668 |
-| ✅ Reflection | 3 | 3 | 730 |
+| ✅ Reflection | 3 | 3 | 680 |
 | ✅ Retrieval | 2 | 5 | 1054 |
 | ✅ Routing | 1 | 2 | 430 |
-| ✅ Sandbox | 5 | 7 | 3483 |
-| ✅ Security | 1 | 3 | 3482 |
-| ✅ Sessions | 4 | 19 | 7631 |
+| ✅ Sandbox | 5 | 6 | 2918 |
+| ✅ Security | 1 | 3 | 3206 |
+| ✅ Sessions | 4 | 17 | 6963 |
 | ✅ Skills | 6 | 15 | 5638 |
-| ✅ Tasks | 2 | 6 | 2897 |
-| ✅ Telemetry | 1 | 2 | 648 |
+| ✅ Tasks | 2 | 6 | 2819 |
+| ✅ Telemetry | 1 | 2 | 604 |
 | ✅ Templates | 1 | 8 | 1663 |
-| ✅ Tools | 12 | 144 | 43113 |
+| ✅ Tools | 12 | 141 | 41242 |
 | ✅ Tracing | 3 | 2 | 139 |
-| ✅ Vector Store | 1 | 12 | 1215 |
+| ✅ Vector Store | 1 | 12 | 1211 |
 | ✅ Video | 2 | 6 | 649 |
 | ✅ Vision | 2 | 1 | 329 |
-| ✅ Web | 3 | 9 | 2487 |
-| ✅ Workflows | 5 | 18 | 7406 |
+| ✅ Web | 3 | 9 | 2467 |
+| ✅ Workflows | 5 | 16 | 6589 |
 
 ## Documentation Without Features
 
 These docs exist but don't match any implemented feature category:
 
-- ℹ️ Database (42 docs, 6959 lines)
+- ℹ️ Database (42 docs, 6713 lines)
 - ℹ️ Documents (1 docs, 787 lines)
 
 ---

src/praisonai-agents/praisonaiagents/__init__.py

@@ -92,6 +92,20 @@ from ._lazy import lazy_import, create_lazy_getattr_with_fallback
 # Thread-safe cache for lazy-loaded values
 _lazy_cache = {}
 
+# Backward compatibility: _get_lazy_cache function for tests
+import threading
+_lazy_cache_local = threading.local()
+
+def _get_lazy_cache():
+    """Get thread-local lazy cache dict. Thread-safe for concurrent access.
+    
+    Note: This is kept for backward compatibility with tests.
+    The main lazy loading now uses the centralized _lazy.py utility.
+    """
+    if not hasattr(_lazy_cache_local, 'cache'):
+        _lazy_cache_local.cache = {}
+    return _lazy_cache_local.cache
+
 # ============================================================================
 # LAZY IMPORT MAPPING
 # ============================================================================

src/praisonai-agents/praisonaiagents/_warning_patch.py

@@ -27,7 +27,7 @@ SUPPRESSED_PATTERNS = [
     "The `dict` method is deprecated; use `model_dump` instead",
     "Pydantic serializer warnings",
     "PydanticSerializationUnexpectedValue",
-    "fields but got",  # litellm/pydantic "Expected N fields but got M"
+    "Expected",  # Catches all "Expected N fields but got M" patterns
     "Expected `StreamingChoices` but got `Choices`",
     "serialized value may not be as expected",
     "Mixing V1 models and V2 models",

src/praisonai-agents/praisonaiagents/agent/async_safety.py

@@ -110,32 +110,14 @@ class AsyncSafeState:
     def __init__(self, initial_value: Any = None):
         self.value = initial_value
         self._lock = DualLock()
-        self._activity_lock = threading.Lock()
-        self._async_holders = 0
-        self._copying = False
 
     def __deepcopy__(self, memo):
-        """Copy protected state, rejecting overlap with asynchronous access."""
+        """Copy the protected value while replacing all lock state."""
         result = type(self).__new__(type(self))
         memo[id(self)] = result
-        with self._activity_lock:
-            if self._async_holders:
-                raise RuntimeError(
-                    "Cannot deepcopy AsyncSafeState during asynchronous access"
-                )
-            if self._copying:
-                raise RuntimeError("AsyncSafeState deepcopy is already in progress")
-            self._copying = True
-        try:
-            with self.lock():
-                result.value = copy.deepcopy(self.value, memo)
-        finally:
-            with self._activity_lock:
-                self._copying = False
+        with self.lock():
+            result.value = copy.deepcopy(self.value, memo)
         result._lock = DualLock()
-        result._activity_lock = threading.Lock()
-        result._async_holders = 0
-        result._copying = False
         return result
         
     @contextmanager 
@@ -148,25 +130,7 @@ class AsyncSafeState:
     async def async_lock(self):
         """Acquire lock in async context."""
         async with self._lock.async_lock():
-            self._begin_async_access()
-            try:
-                yield self.value
-            finally:
-                self._end_async_access()
-
-    def _begin_async_access(self) -> None:
-        """Register async access unless a synchronous copy is in progress."""
-        with self._activity_lock:
-            if self._copying:
-                raise RuntimeError(
-                    "Cannot access AsyncSafeState during synchronous deepcopy"
-                )
-            self._async_holders += 1
-
-    def _end_async_access(self) -> None:
-        """Unregister one active asynchronous accessor."""
-        with self._activity_lock:
-            self._async_holders -= 1
+            yield self.value
             
     def __enter__(self):
         """Support for synchronous context manager protocol (backward compatibility)."""
@@ -182,20 +146,12 @@ class AsyncSafeState:
         """Support for asynchronous context manager protocol."""
         async_lock = self._lock._get_async_lock()
         await async_lock.acquire()
-        try:
-            self._begin_async_access()
-        except Exception:
-            async_lock.release()
-            raise
         return self.value
         
     async def __aexit__(self, exc_type, exc_val, exc_tb):
         """Support for asynchronous context manager protocol."""
         async_lock = self._lock._get_async_lock()
-        try:
-            self._end_async_access()
-        finally:
-            async_lock.release()
+        async_lock.release()
         return None
             
     def get(self) -> Any:

src/praisonai-agents/praisonaiagents/agent/audio_agent.py

@@ -136,8 +136,9 @@ class AudioAgent:
                 - AudioConfig: Full configuration object
             verbose: Verbosity level for output
         """
-        from ..utils.model_alias import resolve_model_name
-        llm = resolve_model_name(llm, model, "AudioAgent")
+        # Handle model= alias
+        if llm is None and model is not None:
+            llm = model
         
         self.name = name or "AudioAgent"
         self.instructions = instructions

src/praisonai-agents/praisonaiagents/agent/autonomy.py

@@ -106,11 +106,8 @@ class AutonomyConfig:
         track_changes: Whether to track filesystem changes via shadow git.
             Defaults to True when level="full_auto", False otherwise.
             When enabled, agent.undo()/redo()/diff() become available.
-        sandbox: Optional SandboxConfig, carried for forward compatibility.
-            NOT IMPLEMENTED: nothing currently reads this field, and no sandbox
-            is auto-enabled at any autonomy level. To isolate execution, set it
-            on the agent itself -- Agent(sandbox=...) -- or run the whole
-            workflow remotely with AgentFlow(run_on="docker").
+        sandbox: Optional SandboxConfig for execution isolation.
+            When level="full_auto" and sandbox is None, subprocess sandbox is auto-enabled.
         snapshot_dir: Directory for snapshot storage. Defaults to ~/.praisonai/snapshots.
     
     Usage::
@@ -217,13 +214,6 @@ class AutonomyConfig:
                 f"Invalid autonomy level: {level!r}. "
                 f"Must be one of {sorted(VALID_AUTONOMY_LEVELS)}"
             )
-        verification_hooks = data.get("verification_hooks")
-        # Config parity: accept declarative `verification:` entries and map
-        # `command:`/`file:` shapes onto the two hook classes.
-        declarative = data.get("verification")
-        if declarative:
-            built = _build_verification_hooks(declarative)
-            verification_hooks = (verification_hooks or []) + built
         return cls(
             enabled=data.get("enabled", True),
             level=level,
@@ -234,7 +224,7 @@ class AutonomyConfig:
             observe=data.get("observe", False),
             completion_promise=data.get("completion_promise"),
             clear_context=data.get("clear_context", False),
-            verification_hooks=verification_hooks,
+            verification_hooks=data.get("verification_hooks"),
             track_changes=data.get("track_changes"),
             sandbox=data.get("sandbox"),
             snapshot_dir=data.get("snapshot_dir"),
@@ -244,49 +234,6 @@ class AutonomyConfig:
             budget_action=data.get("budget_action", "pause"),
         )
 
-
-def _build_verification_hooks(entries: List[Any]) -> List[Any]:
-    """Map declarative ``verification:`` config entries onto hook instances.
-
-    Each entry is a dict with either a ``command`` key (→
-    :class:`CommandVerificationHook`) or a ``file`` key (→
-    :class:`FileCheckHook`). Unknown shapes are skipped.
-
-    Example::
-
-        verification:
-          - {name: tests, command: "python -m pytest -q"}
-          - {name: changelog, file: CHANGELOG.md, non_empty: true}
-    """
-    from ..hooks.verification import CommandVerificationHook, FileCheckHook
-
-    hooks: List[Any] = []
-    for entry in entries or []:
-        if not isinstance(entry, dict):
-            continue
-        blocking = entry.get("blocking", True)
-        if "command" in entry:
-            hooks.append(CommandVerificationHook(
-                name=entry.get("name", "command"),
-                command=entry["command"],
-                cwd=entry.get("cwd"),
-                timeout=entry.get("timeout", 60.0),
-                blocking=blocking,
-            ))
-        elif "file" in entry:
-            hooks.append(FileCheckHook(
-                name=entry.get("name", "file"),
-                path=entry["file"],
-                exists=entry.get("exists", True),
-                non_empty=entry.get("non_empty", False),
-                contains=entry.get("contains"),
-                json_field=entry.get("json_field"),
-                equals=entry.get("equals"),
-                blocking=blocking,
-            ))
-    return hooks
-
-
 class AutonomySignal(str, Enum):
     """Signals detected from prompts for autonomy decisions.
     

src/praisonai-agents/praisonaiagents/agent/chat_mixin.py

@@ -1211,15 +1211,7 @@ Your Goal: {self.goal}"""
         return content
 
     def _extract_llm_response_content(self, response) -> Optional[str]:
-        """Return assistant message text, or a tool-call summary.
-
-        A well-formed response that simply carries no content -- a content filter,
-        a refusal, or ``finish_reason="length"`` with zero output tokens -- yields
-        the empty string.  ``str(response)`` is reserved for responses this method
-        could not parse at all, where the repr is a diagnostic rather than an
-        answer; returning it for a merely empty message put the raw SDK object's
-        repr in front of the user and into ``chat_history``.
-        """
+        """Return assistant message text, a tool-call summary, or str(response) as fallback."""
         if not response:
             return None
         try:
@@ -1234,17 +1226,6 @@ Your Goal: {self.goal}"""
                     if tool_calls:
                         names = [getattr(tc.function, "name", "?") for tc in tool_calls]
                         return f"[tool_calls: {', '.join(names)}]"
-                    # Parsed cleanly; the model returned no content.  A refusal
-                    # (safety) is carried in ``message.refusal`` independently of
-                    # ``finish_reason`` -- surface it so an empty answer isn't silent.
-                    finish_reason = getattr(choice, "finish_reason", None)
-                    refusal = getattr(msg, "refusal", None)
-                    if refusal or finish_reason not in (None, "stop"):
-                        logging.warning(
-                            f"Agent {self.name}: model returned no content "
-                            f"(finish_reason={finish_reason!r}, refused={bool(refusal)})"
-                        )
-                    return ""
         except (AttributeError, IndexError, TypeError) as e:
             logging.warning(
                 f"Failed to extract LLM response content (falling back to str): {e}"
@@ -1744,7 +1725,7 @@ Your Goal: {self.goal}"""
             return max_retries
         return 2
 
-    def _chat_completion(self, messages, temperature=None, tools=None, stream=None, reasoning_steps=False, task_name=None, task_description=None, task_id=None, response_format=None, _retry_depth=0, _fallback_index=0):
+    def _chat_completion(self, messages, temperature=1.0, tools=None, stream=None, reasoning_steps=False, task_name=None, task_description=None, task_id=None, response_format=None, _retry_depth=0, _fallback_index=0):
         start_time = time.time()
 
         # --- Proactive Context Budget Management (default-on) ---
@@ -1868,11 +1849,6 @@ Your Goal: {self.goal}"""
                     stream = False  # Set for the main execution below
                 else:
                     raise  # Re-raise if it's a different ValueError
-            except ToolExecutionError:
-                # A tool failed during the streaming attempt. Re-raise so it is
-                # not relabelled as an LLM error and so the tool is not executed
-                # a second time by the non-streaming fallback below.
-                raise
             except Exception as e:
                 from ..errors import LLMError
                 # Don't retry if it's an LLMError that has exhausted retries
@@ -1977,8 +1953,6 @@ Your Goal: {self.goal}"""
 
         except BudgetExceededError:
             raise
-        except ToolExecutionError:
-            raise
         except Exception as e:
             from ..errors import LLMError
             
@@ -2145,7 +2119,7 @@ Your Goal: {self.goal}"""
         self, 
         exc: Exception, 
         messages, 
-        temperature=None, 
+        temperature=1.0, 
         tools=None, 
         stream=True,
         reasoning_steps=False,
@@ -2335,7 +2309,7 @@ Your Goal: {self.goal}"""
     def _execute_unified_chat_completion(
         self, 
         messages, 
-        temperature=None, 
+        temperature=1.0, 
         tools=None, 
         stream=None,
         reasoning_steps=False,
@@ -2397,11 +2371,7 @@ Your Goal: {self.goal}"""
                     task_name=task_name,
                     task_description=task_description,
                     task_id=task_id,
-                    agent_name=getattr(self, 'name', 'assistant'),
-                    # Durable re-injection target for deferred tool results:
-                    # background jobs completing after this call must land in the
-                    # persistent history a later turn replays, not the loop copy.
-                    deferred_history_sink=getattr(self, 'chat_history', None),
+                    agent_name=getattr(self, 'name', 'assistant')
                 )
                 return final_response
             except ValueError as e:
@@ -2457,8 +2427,6 @@ Your Goal: {self.goal}"""
                     ]
                     or None
                 ),
-                # Durable re-injection target for deferred tool results (see above).
-                deferred_history_sink=getattr(self, 'chat_history', None),
             )
             return final_response
             
@@ -2469,7 +2437,7 @@ Your Goal: {self.goal}"""
     async def _execute_unified_achat_completion(
         self, 
         messages, 
-        temperature=None, 
+        temperature=1.0, 
         tools=None, 
         stream=True,  # Async methods keep stream=True default (async adapters support streaming vs sync smart fallback)
         reasoning_steps=False,
@@ -2807,11 +2775,7 @@ Your Goal: {self.goal}"""
                 
                 model_name = self.llm if isinstance(self.llm, str) else "gpt-4o-mini"
                 model_limit = get_model_limit(model_name)
-                # Count the whole request (history + system prompt + tool schemas),
-                # otherwise a large prompt/tool block can push the call over the
-                # window while the history alone stays under the threshold.
-                overhead = self._estimate_request_overhead_tokens(system_prompt, tools)
-                current_tokens = estimate_messages_tokens(optimized) + overhead
+                current_tokens = estimate_messages_tokens(optimized)
                 
                 # If over 95% of limit, apply emergency truncation
                 if current_tokens > model_limit * 0.95:
@@ -2819,67 +2783,20 @@ Your Goal: {self.goal}"""
                         f"[{self.name}] Context at {current_tokens} tokens (limit: {model_limit}), "
                         f"applying emergency truncation"
                     )
-                    # Leave room for the fixed overhead so the full request lands
-                    # near 80% of the window rather than the history alone.
-                    target = max(1, int(model_limit * 0.8) - overhead)
+                    target = int(model_limit * 0.8)  # Target 80% of limit
                     optimized = self.context_manager.emergency_truncate(optimized, target)
                     result["emergency_truncated"] = True
-                    result["tokens_after"] = estimate_messages_tokens(optimized) + overhead
+                    result["tokens_after"] = estimate_messages_tokens(optimized)
             except Exception as e:
                 logging.debug(f"Hard limit check skipped: {e}")
             
             return optimized, result
             
         except Exception as e:
-            # Context management should never break the chat flow, but silently
-            # returning the unchanged history disables the hard-limit truncation
-            # too and sends an over-budget request. Fall back to emergency
-            # truncation so we still fit within the model window.
-            logging.error(f"Context management failed: {e}")
-            try:
-                from ..context.budgeter import get_model_limit
-                from ..context.tokens import estimate_messages_tokens
-
-                model_name = self.llm if isinstance(self.llm, str) else "gpt-4o-mini"
-                model_limit = get_model_limit(model_name)
-                # Include the system prompt and tool schemas in the budget: the
-                # request can exceed the window on those alone even when the
-                # history is under the threshold.
-                overhead = self._estimate_request_overhead_tokens(system_prompt, tools)
-                if estimate_messages_tokens(messages) + overhead > model_limit * 0.95:
-                    target = max(1, int(model_limit * 0.8) - overhead)
-                    truncated = self.context_manager.emergency_truncate(messages, target)
-                    return truncated, {"emergency_truncated": True}
-            except Exception as inner:
-                logging.debug(f"Emergency truncation fallback skipped: {inner}")
+            # Context management should never break the chat flow
+            logging.warning(f"Context management error (continuing without): {e}")
             return messages, None
 
-    def _estimate_request_overhead_tokens(
-        self,
-        system_prompt: str = "",
-        tools: Optional[list] = None,
-    ) -> int:
-        """Estimate non-history request tokens (system prompt + tool schemas).
-
-        Emergency-truncation thresholds must budget the full request, not just
-        the message history, or a large system prompt / tool block can push the
-        call over the model window undetected.
-        """
-        try:
-            from ..context.tokens import (
-                estimate_tokens_heuristic,
-                estimate_tool_schema_tokens,
-            )
-        except Exception:
-            return 0
-
-        overhead = 0
-        if system_prompt:
-            overhead += estimate_tokens_heuristic(system_prompt)
-        if tools:
-            overhead += estimate_tool_schema_tokens(tools)
-        return overhead
-
     def _truncate_tool_output(self, tool_name: str, output: str, tool_call_id: str | None = None) -> str:
         """
         Truncate tool output according to configured budget.
@@ -2965,7 +2882,7 @@ Your Goal: {self.goal}"""
             )
         return rendered
 
-    def chat(self, prompt: str, temperature: Optional[float] = None, tools: Optional[List[Any]] = None, output_json: Optional[Any] = None, output_pydantic: Optional[Any] = None, reasoning_steps: bool = False, stream: Optional[bool] = None, task_name: Optional[str] = None, task_description: Optional[str] = None, task_id: Optional[str] = None, config: Optional[Dict[str, Any]] = None, force_retrieval: bool = False, skip_retrieval: bool = False, attachments: Optional[List[str]] = None, tool_choice: Optional[str] = None, seed: Optional[int] = None, cancel_token: Optional[Any] = None) -> Optional[str]:
+    def chat(self, prompt: str, temperature: float = 1.0, tools: Optional[List[Any]] = None, output_json: Optional[Any] = None, output_pydantic: Optional[Any] = None, reasoning_steps: bool = False, stream: Optional[bool] = None, task_name: Optional[str] = None, task_description: Optional[str] = None, task_id: Optional[str] = None, config: Optional[Dict[str, Any]] = None, force_retrieval: bool = False, skip_retrieval: bool = False, attachments: Optional[List[str]] = None, tool_choice: Optional[str] = None, seed: Optional[int] = None, cancel_token: Optional[Any] = None) -> Optional[str]:
         """
         Chat with the agent.
         
@@ -2978,14 +2895,6 @@ Your Goal: {self.goal}"""
                         'required' forces the LLM to call a tool before responding.
             ...other args...
         """
-        # Tools go to their sandbox before the first model call, once per
-        # agent. Placed on chat/achat/_start_stream rather than run/start
-        # because AgentTeam and AgentFlow call these three directly -- an
-        # agent used inside a team would otherwise run its tools locally.
-        if getattr(self, 'tools_run_on', None) is not None:
-            from .tools_placement import ensure_tools_placed
-            ensure_tools_placed(self)
-
         # Slash-command invocation: /skill-name [args] renders the skill
         # body before any backend/LLM call.
         prompt = self._resolve_skill_invocation(prompt)
@@ -3575,14 +3484,11 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                                 reflection_output = _get_display_functions()['ReflectionOutput'](**reflection_data)
                             else:
                                 # Use OpenAI's structured output for OpenAI models
-                                _reflection_kwargs = {}
-                                if temperature is not None:
-                                    _reflection_kwargs['temperature'] = temperature
                                 reflection_response = self._openai_client.sync_client.beta.chat.completions.parse(
                                     model=self.reflect_llm if self.reflect_llm else self.llm,
                                     messages=messages,
-                                    response_format=_get_display_functions()['ReflectionOutput'],
-                                    **_reflection_kwargs
+                                    temperature=temperature,
+                                    response_format=_get_display_functions()['ReflectionOutput']
                                 )
 
                                 reflection_output = reflection_response.choices[0].message.parsed
@@ -3647,22 +3553,6 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                                 logging.error("Reflection parsing failed.", exc_info=True)
                                 messages.append({"role": "assistant", "content": "Self Reflection failed."})
                                 reflection_count += 1
-                                if reflection_count >= self.max_reflect:
-                                    # Bound the retry, as the async path does. Without this
-                                    # a persistently unparseable reflection (e.g. a
-                                    # structured-output refusal, where message.parsed is
-                                    # None) loops forever, two LLM calls at a time.
-                                    if self.verbose:
-                                        _get_display_functions()['display_self_reflection']("Maximum reflection count reached after repeated parse errors, returning current response", console=self.console)
-                                    self._append_to_chat_history({"role": "assistant", "content": response_text})
-                                    try:
-                                        validated_response = self._apply_guardrail_with_retry(response_text, original_prompt, temperature, tools, task_name, task_description, task_id)
-                                        self._execute_callback_and_display(original_prompt, validated_response, time.time() - start_time, task_name, task_description, task_id)
-                                        return self._trigger_after_agent_hook(original_prompt, validated_response, start_time)
-                                    except Exception as guard_e:
-                                        logging.error(f"Agent {self.name}: Guardrail validation failed after reflection error: {guard_e}")
-                                        self._rollback_chat_history_to(chat_history_length)
-                                        return None
                                 continue  # Continue even after error to try again
                     except Exception:
                         # Catch any exception from the inner try block and re-raise to outer handler
@@ -3682,7 +3572,7 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
 
         return clean_triple_backticks(output)
 
-    async def achat(self, prompt: str, temperature: Optional[float] = None, tools: Optional[List[Any]] = None, output_json: Optional[Any] = None, output_pydantic: Optional[Any] = None, reasoning_steps: bool = False, stream: Optional[bool] = None, task_name: Optional[str] = None, task_description: Optional[str] = None, task_id: Optional[str] = None, config: Optional[Dict[str, Any]] = None, force_retrieval: bool = False, skip_retrieval: bool = False, attachments: Optional[List[str]] = None, tool_choice: Optional[str] = None, seed: Optional[int] = None, cancel_token: Optional[Any] = None):
+    async def achat(self, prompt: str, temperature: float = 1.0, tools: Optional[List[Any]] = None, output_json: Optional[Any] = None, output_pydantic: Optional[Any] = None, reasoning_steps: bool = False, stream: Optional[bool] = None, task_name: Optional[str] = None, task_description: Optional[str] = None, task_id: Optional[str] = None, config: Optional[Dict[str, Any]] = None, force_retrieval: bool = False, skip_retrieval: bool = False, attachments: Optional[List[str]] = None, tool_choice: Optional[str] = None, seed: Optional[int] = None, cancel_token: Optional[Any] = None):
         """Async version of chat method with self-reflection support.
         
         Args:
@@ -3690,14 +3580,6 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
             attachments: Optional list of image/file paths that are ephemeral
                         (used for THIS turn only, NEVER stored in history).
         """
-        # Tools go to their sandbox before the first model call, once per
-        # agent. Placed on chat/achat/_start_stream rather than run/start
-        # because AgentTeam and AgentFlow call these three directly -- an
-        # agent used inside a team would otherwise run its tools locally.
-        if getattr(self, 'tools_run_on', None) is not None:
-            from .tools_placement import ensure_tools_placed
-            ensure_tools_placed(self)
-
         # Slash-command invocation: /skill-name [args] renders the skill body.
         prompt = self._resolve_skill_invocation(prompt)
 
@@ -4243,14 +4125,11 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                                             self._rollback_chat_history_to(chat_history_length)
                                             return None
                                     
-                                    _areflection_kwargs = {}
-                                    if temperature is not None:
-                                        _areflection_kwargs['temperature'] = temperature
                                     reflection_response = await self._openai_client.async_client.beta.chat.completions.parse(
                                         model=self.reflect_llm if self.reflect_llm else self.llm,
                                         messages=reflection_messages,
-                                        response_format=_get_display_functions()['ReflectionOutput'],
-                                        **_areflection_kwargs
+                                        temperature=temperature,
+                                        response_format=_get_display_functions()['ReflectionOutput']
                                     )
                                     
                                     reflection_output = reflection_response.choices[0].message.parsed
@@ -4364,10 +4243,9 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                             tool_call_kwargs = dict(
                                 model=self.llm,
                                 messages=messages,
+                                temperature=temperature,
                                 tools=formatted_tools,
                             )
-                            if temperature is not None:
-                                tool_call_kwargs['temperature'] = temperature
                             if effective_tool_choice:
                                 tool_call_kwargs['tool_choice'] = effective_tool_choice
                             response = await self._openai_client.async_client.chat.completions.create(
@@ -4381,14 +4259,11 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                             self._execute_callback_and_display(original_prompt, result, time.time() - start_time, task_name, task_description, task_id)
                             return await self._atrigger_after_agent_hook(original_prompt, result, start_time)
                         elif output_json or output_pydantic:
-                            _json_kwargs = {}
-                            if temperature is not None:
-                                _json_kwargs['temperature'] = temperature
                             response = await self._openai_client.async_client.chat.completions.create(
                                 model=self.llm,
                                 messages=messages,
-                                response_format={"type": "json_object"},
-                                **_json_kwargs
+                                temperature=temperature,
+                                response_format={"type": "json_object"}
                             )
                             response_text = response.choices[0].message.content
                             if get_logger().getEffectiveLevel() == logging.DEBUG:
@@ -4398,13 +4273,10 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                             self._execute_callback_and_display(original_prompt, response_text, time.time() - start_time, task_name, task_description, task_id)
                             return await self._atrigger_after_agent_hook(original_prompt, response_text, start_time)
                         else:
-                            _plain_kwargs = {}
-                            if temperature is not None:
-                                _plain_kwargs['temperature'] = temperature
                             response = await self._openai_client.async_client.chat.completions.create(
                                 model=self.llm,
                                 messages=messages,
-                                **_plain_kwargs
+                                temperature=temperature
                             )
                         
                         response_text = response.choices[0].message.content
@@ -4441,14 +4313,11 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                                             logging.debug(f"Agent.achat completed in {total_time:.2f} seconds")
                                         return await self._atrigger_after_agent_hook(original_prompt, response_text, start_time)
                                     
-                                    _areflection_kwargs = {}
-                                    if temperature is not None:
-                                        _areflection_kwargs['temperature'] = temperature
                                     reflection_response = await self._openai_client.async_client.beta.chat.completions.parse(
                                         model=self.reflect_llm if self.reflect_llm else self.llm,
                                         messages=reflection_messages,
-                                        response_format=_get_display_functions()['ReflectionOutput'],
-                                        **_areflection_kwargs
+                                        temperature=temperature,
+                                        response_format=_get_display_functions()['ReflectionOutput']
                                     )
                                     
                                     reflection_output = reflection_response.choices[0].message.parsed
@@ -4474,13 +4343,10 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                                         {"role": "user", "content": "Now regenerate your response using the reflection you made"}
                                     ]
                                     
-                                    _regen_kwargs = {}
-                                    if temperature is not None:
-                                        _regen_kwargs['temperature'] = temperature
                                     new_response = await self._openai_client.async_client.chat.completions.create(
                                         model=self.llm,
                                         messages=regenerate_messages,
-                                        **_regen_kwargs
+                                        temperature=temperature
                                     )
                                     response_text = new_response.choices[0].message.content
                                     reflection_count += 1
@@ -4567,12 +4433,7 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                     # after-context aggregation) are fired once, guarded, inside
                     # execute_tool_async — no inline duplicate dispatch here.
                     # Pass the tools list to honor task-scoped tools
-                    result = await self.execute_tool_async(
-                        function_name,
-                        arguments,
-                        tool_call_id=getattr(tool_call, "id", None),
-                        tools_override=tools,
-                    )
+                    result = await self.execute_tool_async(function_name, arguments, tools_override=tools)
 
                     results.append(result)
                 except Exception as e:
@@ -4673,14 +4534,6 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
 
     def _start_stream(self, prompt: str, **kwargs) -> Generator[str, None, None]:
         """Own the durable context for the complete streaming generator."""
-        # Tools go to their sandbox before the first model call, once per
-        # agent. Placed on chat/achat/_start_stream rather than run/start
-        # because AgentTeam and AgentFlow call these three directly -- an
-        # agent used inside a team would otherwise run its tools locally.
-        if getattr(self, 'tools_run_on', None) is not None:
-            from .tools_placement import ensure_tools_placed
-            ensure_tools_placed(self)
-
         durable_context = None
         durable_token = None
         try:
@@ -5368,7 +5221,7 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
             agent_id=getattr(self, 'name', None),
         )
 
-    def _chat_completion_with_retry(self, messages, temperature=None, tools=None, stream=None, reasoning_steps=False, task_name=None, task_description=None, task_id=None, response_format=None, stream_callback=None, emit_events=True):
+    def _chat_completion_with_retry(self, messages, temperature=1.0, tools=None, stream=None, reasoning_steps=False, task_name=None, task_description=None, task_id=None, response_format=None, stream_callback=None, emit_events=True):
         """
         Wrapper for _execute_unified_chat_completion that adds jittered exponential backoff retry logic.
         
@@ -5455,7 +5308,7 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
         # This should never be reached, but just in case
         raise RuntimeError("Retry loop completed without returning or raising an exception")
 
-    async def _achat_completion_with_retry(self, messages, temperature=None, tools=None, stream=None, reasoning_steps=False, task_name=None, task_description=None, task_id=None, response_format=None, stream_callback=None, emit_events=True):
+    async def _achat_completion_with_retry(self, messages, temperature=1.0, tools=None, stream=None, reasoning_steps=False, task_name=None, task_description=None, task_id=None, response_format=None, stream_callback=None, emit_events=True):
         """
         Async wrapper for _execute_unified_achat_completion that adds jittered exponential backoff retry logic.
         

src/praisonai-agents/praisonaiagents/agent/code_agent.py

@@ -59,8 +59,7 @@ class CodeAgent:
     def __init__(
         self,
         name: str = "CodeAgent",
-        llm: Optional[str] = None,  # Deprecated alias for model=
-        model: Optional[str] = None,
+        llm: Optional[str] = None,
         code: Optional[Union[bool, Dict, CodeConfig]] = None,
         instructions: Optional[str] = None,
         verbose: bool = True,
@@ -70,16 +69,14 @@ class CodeAgent:
         
         Args:
             name: Agent name
-            llm: Deprecated alias for model=. Passing both raises TypeError.
-            model: Model to use (default: gpt-4o-mini)
+            llm: LLM model (default: gpt-4o-mini)
             code: Code configuration (bool, dict, or CodeConfig)
             instructions: System instructions
             verbose: Enable verbose output
             **kwargs: Additional arguments
         """
-        from ..utils.model_alias import resolve_model_name
         self.name = name
-        self.llm = resolve_model_name(llm, model, "CodeAgent") or "gpt-4o-mini"
+        self.llm = llm or "gpt-4o-mini"
         self.instructions = instructions
         self.verbose = verbose
         

src/praisonai-agents/praisonaiagents/agent/durable.py

@@ -17,7 +17,6 @@ from ..runtime.journal import (
     KIND_MODEL_DECISION,
     KIND_TOOL_CALL,
     KIND_TOOL_RESULT,
-    KIND_VERIFICATION,
     RunJournal,
 )
 
@@ -59,85 +58,6 @@ def _accepts_idempotency_key(execute_tool_fn: Callable) -> bool:
     )
 
 
-def _normalize_restart_safe(value: Any) -> Optional[bool]:
-    """Accept only genuine booleans as a restart-safety declaration.
-
-    ``None`` means undeclared. Any other type (e.g. the string ``"False"``) is a
-    malformed declaration and is treated as unsafe so we fail closed rather than
-    coercing a truthy value into an unintended replay.
-    """
-    if value is None:
-        return None
-    if isinstance(value, bool):
-        return value
-    return False
-
-
-def _canonical_tool_name(name: Any) -> str:
-    """Normalise a tool name for tolerant comparison across repair variants.
-
-    ``execute_tool`` may repair case/separator variants (e.g. ``Send-Email`` →
-    ``send_email``); the declaration lookup mirrors that so an explicit
-    ``restart_safe`` declaration is not missed for a repaired name.
-    """
-    return "".join(ch for ch in str(name).lower() if ch.isalnum())
-
-
-def _declared_restart_safe(
-    function_name: str, executor: Optional[Callable]
-) -> Optional[bool]:
-    """Return an explicit ``restart_safe`` declaration for ``function_name``.
-
-    Resolves the tool object first from the executor's owning agent (its live
-    ``tools``), then from the global tool registry, and reads its
-    ``restart_safe`` attribute. Returns ``None`` when the tool is undeclared or
-    cannot be resolved.
-    """
-    if not function_name:
-        return False
-    target = _canonical_tool_name(function_name)
-    agent = getattr(executor, "__self__", None)
-    tools = getattr(agent, "tools", None)
-    if isinstance(tools, (list, tuple)):
-        for tool in tools:
-            name = getattr(tool, "name", None) or getattr(tool, "__name__", None)
-            if (
-                name is not None
-                and _canonical_tool_name(name) == target
-                and getattr(tool, "restart_safe", None) is not None
-            ):
-                return _normalize_restart_safe(tool.restart_safe)
-    try:
-        from ..tools import get_registry as _get_tool_registry
-
-        tool = _get_tool_registry().get(function_name)
-    except Exception:  # pragma: no cover - registry lookup is best-effort
-        tool = None
-    declared = getattr(tool, "restart_safe", None) if tool is not None else None
-    return _normalize_restart_safe(declared)
-
-
-def _is_restart_safe(function_name: str, executor: Optional[Callable] = None) -> bool:
-    """Resolve whether a tool is safe to re-run for an in-flight durable resume.
-
-    An explicit ``restart_safe`` declaration on the tool contract wins. When the
-    tool is undeclared (or cannot be resolved), fall back to the read-only name
-    heuristic and, ultimately, fail closed — an effectful/unknown tool is *not*
-    replayed so a missing declaration never causes a duplicated side effect.
-    """
-    if not function_name:
-        return False
-    declared = _declared_restart_safe(function_name, executor)
-    if declared is not None:
-        return declared
-    try:
-        from .tool_execution import ToolExecutionMixin
-
-        return bool(ToolExecutionMixin._is_read_only_tool(function_name))
-    except Exception:  # pragma: no cover - heuristic import is best-effort
-        return False
-
-
 class DurableRunContext:
     """Per-turn journal state; safe for parallel tool-call wrappers."""
 
@@ -160,10 +80,6 @@ class DurableRunContext:
         self._results_by_tool_call_id: Dict[str, Any] = {}
         self._pending_by_call_id: Dict[str, Tuple[int, str, Dict[str, Any], str]] = {}
         self._pending_by_fingerprint: Dict[str, Tuple[int, str, Dict[str, Any], str]] = {}
-        # Names of in-flight tool calls (journalled tool_call with no tool_result
-        # at the crash). Used only when replaying to gate replay by restart-safety.
-        self._inflight_names_by_call_id: Dict[str, str] = {}
-        self._inflight_names_by_fingerprint: Dict[str, str] = {}
         self._recorded_iterations = set()
         for event in events:
             if event.kind == KIND_TOOL_RESULT:
@@ -190,11 +106,8 @@ class DurableRunContext:
                 or f"{self.run_id}:{event.seq}:{name}"
             )
             pending = (event.seq, call_id, args, key)
-            fingerprint = self._fingerprint(name, args)
             self._pending_by_call_id[call_id] = pending
-            self._pending_by_fingerprint[fingerprint] = pending
-            self._inflight_names_by_call_id[call_id] = name
-            self._inflight_names_by_fingerprint[fingerprint] = name
+            self._pending_by_fingerprint[self._fingerprint(name, args)] = pending
 
         self._resume_completed_steps = len(self._recorded_iterations)
 
@@ -206,44 +119,6 @@ class DurableRunContext:
     def _fingerprint(function_name: str, arguments: Dict[str, Any]) -> str:
         return f"{function_name}:{json.dumps(_json_safe(arguments), sort_keys=True)}"
 
-    def _is_inflight_call(
-        self,
-        function_name: str,
-        arguments: Dict[str, Any],
-        tool_call_id: Optional[str],
-    ) -> bool:
-        """Whether this call was in-flight (journalled, no result) at the crash.
-
-        Only meaningful while replaying: such calls have a recorded ``tool_call``
-        but no ``tool_result``, so re-driving the loop would re-execute their
-        side effect. Completed calls (already have a result) are replayed
-        upstream and never reach this check.
-        """
-        if not self.replaying:
-            return False
-        call_id = str(tool_call_id) if tool_call_id is not None else None
-        if call_id and call_id in self._inflight_names_by_call_id:
-            return True
-        return self._fingerprint(function_name, arguments) in (
-            self._inflight_names_by_fingerprint
-        )
-
-    @staticmethod
-    def _not_safely_resumable_result(function_name: str) -> Dict[str, Any]:
-        """Typed, operator-visible outcome for a gated in-flight effectful tool."""
-        return {
-            "error": (
-                f"Tool '{function_name}' was in-flight when the durable run "
-                "crashed and is not declared restart_safe; its outcome could not "
-                "be confirmed. It was not re-executed on resume to avoid a "
-                "duplicate side effect. Reconcile the external action manually "
-                "or mark the tool @tool(restart_safe=True) if it is idempotent."
-            ),
-            "error_type": "NotSafelyResumable",
-            "not_safely_resumable": True,
-            "restart_safe": False,
-        }
-
     def restore_messages(self, messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
         """Append completed decision/result pairs once, before the next model call."""
         if not self.replaying or self._restored:
@@ -402,26 +277,6 @@ class DurableRunContext:
         )
         self.finalize("failed")
 
-    def record_verification(self, payloads: List[Dict[str, Any]]) -> None:
-        """Append verification-gate results as durable ``verification`` events.
-
-        Each payload gets its own fresh ``seq`` so the events append cleanly
-        alongside the tool-call cursor without colliding on ``(run_id, seq,
-        kind)``. Best-effort: journalling never raises into the gate.
-        """
-        if self._closed:
-            return
-        with self._lock:
-            for payload in payloads:
-                seq = self._next_seq
-                self._next_seq += 1
-                try:
-                    self.journal.append(
-                        JournalEvent(self.run_id, seq, KIND_VERIFICATION, payload)
-                    )
-                except Exception:  # pragma: no cover - journalling is best-effort
-                    pass
-
     def wrap_sync(self, execute_tool_fn: Optional[Callable]) -> Optional[Callable]:
         if execute_tool_fn is None:
             return None
@@ -431,19 +286,9 @@ class DurableRunContext:
             call_id = str(tool_call_id) if tool_call_id is not None else None
             if call_id and call_id in self._results_by_tool_call_id:
                 return self._results_by_tool_call_id[call_id]
-            gate_inflight = self._is_inflight_call(
-                function_name, arguments, tool_call_id
-            ) and not _is_restart_safe(function_name, execute_tool_fn)
             seq, call_id, idempotency_key = self._allocate_step(
                 function_name, arguments, tool_call_id
             )
-            if gate_inflight:
-                return self._record_result(
-                    seq,
-                    call_id,
-                    self._not_safely_resumable_result(function_name),
-                    iteration_index,
-                )
             token = _active_idempotency_key.set(idempotency_key)
             try:
                 call_kwargs = dict(kwargs)
@@ -474,20 +319,9 @@ class DurableRunContext:
             call_id = str(tool_call_id) if tool_call_id is not None else None
             if call_id and call_id in self._results_by_tool_call_id:
                 return self._results_by_tool_call_id[call_id]
-            gate_inflight = self._is_inflight_call(
-                function_name, arguments, tool_call_id
-            ) and not _is_restart_safe(function_name, execute_tool_fn)
             seq, call_id, idempotency_key = await asyncio.to_thread(
                 self._allocate_step, function_name, arguments, tool_call_id
             )
-            if gate_inflight:
-                return await asyncio.to_thread(
-                    self._record_result,
-                    seq,
-                    call_id,
-                    self._not_safely_resumable_result(function_name),
-                    iteration_index,
-                )
             token = _active_idempotency_key.set(idempotency_key)
             try:
                 call_kwargs = dict(kwargs)

src/praisonai-agents/praisonaiagents/agent/embedding_agent.py

@@ -110,8 +110,8 @@ class EmbeddingAgent:
                 - EmbeddingConfig: Full configuration object
             verbose: Verbosity level for output
         """
-        from ..utils.model_alias import resolve_model_name
-        llm = resolve_model_name(llm, model, "EmbeddingAgent")
+        if llm is None and model is not None:
+            llm = model
         
         self.name = name or "EmbeddingAgent"
         self.instructions = instructions

src/praisonai-agents/praisonaiagents/agent/execution_location.py

@@ -1,276 +0,0 @@
-"""Describe, in plain English, where an agent's work actually happens.
-
-PraisonAI can run the thinking (LLM calls) and the tools in different places:
-this machine, a container, or a provider's cloud. Which one you get depends on
-``run_on=``, ``backend=`` and ``sandbox=``, and until now none of that was
-visible from the object -- ``repr(agent)`` was the bare default.
-
-This module is the single source of that answer, shared by ``Agent``,
-``AgentTeam`` and ``AgentFlow`` so all three describe themselves identically.
-
-Vocabulary note: the fields are ``thinks_on`` / ``tools_run_on``, never
-``loop``. "Loop" is already a public workflow primitive here
-(``praisonaiagents.workflows.loop()``), asyncio's event loop, and agent-loop
-jargon a beginner would not know -- three meanings for one word is exactly the
-problem this module exists to fix.
-"""
-
-from __future__ import annotations
-
-from typing import Any, Dict, Optional
-
-# Provider name -> how a human would say it out loud.
-_PLACE_WORDS = {
-    "local": "this machine",
-    "subprocess": "a separate process on this machine",
-    "sandlock": "a locked-down process on this machine",
-    "docker": "a Docker container",
-    "e2b": "an E2B cloud sandbox",
-    "modal": "a Modal cloud sandbox",
-    "daytona": "a Daytona cloud sandbox",
-    "flyio": "a Fly.io machine",
-    "tenki": "a Tenki cloud sandbox",
-    "novita": "a Novita cloud sandbox",
-    "ssh": "a remote machine over SSH",
-    "anthropic": "Anthropic's cloud",
-}
-
-HERE = "this machine"
-
-# Public sandbox aliases the SandboxManager collapses before it picks a backend
-# (see praisonaiagents/sandbox/manager.py). We must describe the backend that
-# actually runs, not the alias the user typed, or "native"/"local" would report
-# a place that never executes.
-_ALIASES = {"native": "sandlock", "local": "subprocess"}
-
-# ...but only for the SANDBOX registry. "local" resolves to two different
-# backends depending on which parameter carried it:
-#   run_in="local"        -> SandboxManager collapses it to subprocess:
-#                            scrubbed environment, blocked commands and paths
-#   tools_run_on="local"  -> the wrapper's LocalCompute: a plain shell in the
-#                            current directory, full environment inherited,
-#                            no security policy at all
-# Describing the second in the first's words overstates it, which is the exact
-# failure this module exists to prevent. One word, two backends -- so the
-# phrase has to depend on where the word came from.
-_COMPUTE_ONLY_WORDS = {"local": "a plain shell on this machine (no policy applied)"}
-
-# Tiers that separate a process but do NOT contain it. Verified: under the
-# subprocess backend, outbound network still works and ~/.ssh is readable even
-# though SecurityPolicy declares them blocked.
-# `native` is deliberately absent: it aliases sandlock, which applies Landlock,
-# seccomp, a scrubbed environment and deny-all networking. Listing it here made
-# tools_run_on="native" and tools_run_on="sandlock" -- the same backend --
-# disagree about whether they contain anything.
-_NOT_A_BOUNDARY = {"subprocess", "local"}
-
-
-def say_place(name: Any, *, via: str = "sandbox") -> str:
-    """Turn a place name into a phrase a non-developer can read.
-
-    ``via`` says which registry resolved the name -- ``"compute"`` for
-    ``tools_run_on=``, ``"sandbox"`` for ``run_in=``. It only matters for names
-    that mean different backends in each (see ``_COMPUTE_ONLY_WORDS``).
-    """
-    if name is None:
-        return HERE
-    if name is True:
-        return _PLACE_WORDS["subprocess"]
-    if not isinstance(name, str):
-        # A configured provider instance: use its own declared name if it has
-        # one. Normalise BEFORE the compute-only check, or a backend holding a
-        # LocalCompute object (provider_name="local") skips the branch and gets
-        # described in the subprocess backend's stronger words -- the exact
-        # overstatement this module exists to prevent.
-        name = getattr(name, "provider_name", None) or type(name).__name__
-    if via == "compute" and name.lower() in _COMPUTE_ONLY_WORDS:
-        return _COMPUTE_ONLY_WORDS[name.lower()]
-    key = str(name).lower()
-    key = _ALIASES.get(key, key)
-
-    known = _PLACE_WORDS.get(key)
-    if known:
-        return known
-
-    # A place contributed by another package can name itself; the bare name is
-    # the last resort rather than the only option, because the phrase table is
-    # a literal that cannot know about packages installed later.
-    try:
-        from ..managed._compute_bridge import contributed_display_name
-
-        declared = contributed_display_name(key)
-        if declared:
-            return declared
-    except Exception:
-        pass
-    return str(name)
-
-
-def _backend_places(backend: Any) -> Optional[Dict[str, str]]:
-    """Where does a managed ``backend=`` put the thinking and the tools?"""
-    if backend is None:
-        return None
-
-    # Ask the backend what it is, rather than guessing from its class name.
-    # Name-matching missed any backend that did not happen to contain "Hosted"
-    # or "Anthropic" -- a self-hosted docker backend reported that it was
-    # thinking on this machine while the whole loop ran in a container.
-    declared = getattr(backend, "provider_name", None)
-    if isinstance(declared, str):
-        try:
-            from .placement import managed_runtimes
-
-            if declared.lower() in managed_runtimes():
-                where = say_place(declared)
-                return {"thinks_on": where, "tools_run_on": where}
-        except Exception:
-            pass
-
-    cls = type(backend).__name__
-    # Hosted runtimes move the entire turn off this machine.
-    if "Hosted" in cls or "Anthropic" in cls:
-        provider = getattr(backend, "provider", None) or "anthropic"
-        where = say_place(provider)
-        return {"thinks_on": where, "tools_run_on": where}
-
-    # Local/sandboxed agents keep the loop here and may push tools out. A
-    # backend's compute object is a COMPUTE-registry provider, so it is read
-    # with the compute vocabulary: a LocalCompute here is the unrestricted
-    # shell, not the subprocess backend "local" collapses to under run_in=.
-    compute = getattr(backend, "_compute", None) or getattr(backend, "compute", None)
-    if compute is not None:
-        return {"thinks_on": HERE, "tools_run_on": say_place(compute, via="compute")}
-    return {"thinks_on": HERE, "tools_run_on": HERE}
-
-
-def describe(obj: Any, *, shared: bool = False) -> Dict[str, str]:
-    """Return ``{thinks_on, tools_run_on, code_runs_on?}`` for an object.
-
-    Never raises: a description of where things run must not be able to break
-    the thing it describes.
-    """
-    places: Dict[str, str] = {"thinks_on": HERE, "tools_run_on": HERE}
-    try:
-        from_backend = _backend_places(getattr(obj, "backend", None))
-        if from_backend:
-            places.update(from_backend)
-
-        where_tools = getattr(obj, "tools_run_on", None)
-        if where_tools is not None:
-            where = say_place(where_tools, via="compute")
-            places["tools_run_on"] = f"{where} (shared)" if shared else where
-
-        # run_on= puts the WHOLE agent on a managed runtime, so it moves the
-        # thinking as well. _backend_places() already reports that (run_on= is
-        # turned into a backend at construction); this only covers an object
-        # that carries the name without a built backend.
-        whole = getattr(obj, "run_on", None)
-        if whole is not None and not from_backend:
-            everywhere = say_place(whole)
-            places["thinks_on"] = everywhere
-            places["tools_run_on"] = everywhere
-
-        sandbox_config = getattr(obj, "sandbox_config", None)
-        if sandbox_config is not None:
-            places["code_runs_on"] = say_place(
-                getattr(sandbox_config, "sandbox_type", None)
-            )
-    except Exception:  # pragma: no cover - description must never break callers
-        pass
-    return places
-
-
-def _tools_staying_here(obj: Any) -> list:
-    """Names of the object's own tools, which do NOT move to the sandbox.
-
-    Only four tool names are bridged (``execute_command``, ``read_file``,
-    ``write_file``, ``list_files``); everything else the user passed keeps
-    running in this process, against this filesystem. The capability prompt
-    tells the model the sandbox is where things happen, so anything staying
-    behind has to be said out loud.
-
-    Reads the pre-attach tool list when a sandbox is already attached: by then
-    ``agent.tools`` has been rewritten and the originals live in the sandbox's
-    restore record.
-    """
-    try:
-        from ..managed.shared_compute import BRIDGED_TOOL_NAMES
-    except Exception:
-        BRIDGED_TOOL_NAMES = ("execute_command", "read_file", "write_file", "list_files")
-
-    tools = None
-    shared = getattr(obj, "_tools_sandbox", None)
-    if shared is not None:
-        for patched, original_tools, _ in getattr(shared, "_patched", []):
-            if patched is obj:
-                tools = original_tools
-                break
-    if tools is None:
-        tools = getattr(obj, "tools", None) or []
-
-    names = []
-    for tool in tools:
-        name = getattr(tool, "__name__", None) or getattr(tool, "name", None)
-        if isinstance(name, str) and name not in BRIDGED_TOOL_NAMES:
-            names.append(name)
-    return names
-
-
-def repr_fields(obj: Any, *, shared: bool = False) -> str:
-    """Render the places as ``key='value'`` pairs for a ``__repr__``."""
-    return ", ".join(f"{k}={v!r}" for k, v in describe(obj, shared=shared).items())
-
-
-def explain(obj: Any, *, shared: bool = False) -> str:
-    """Plain-sentence answer to "where does this actually run?".
-
-    Deliberately uses only words a non-engineer already knows -- no "loop",
-    "harness", "provision" or "runtime".
-    """
-    places = describe(obj, shared=shared)
-    lines = [
-        f"Thinking (the AI model calls) happens on {places['thinks_on']}.",
-        f"Tools run on {places['tools_run_on']}.",
-    ]
-
-    if shared and getattr(obj, "tools_run_on", None) is not None:
-        lines.append(
-            "Every step shares that same sandbox, so a file written by one step "
-            "is visible to the next."
-        )
-
-    staying = _tools_staying_here(obj)
-    if staying and places["tools_run_on"] != places["thinks_on"]:
-        listed = ", ".join(staying[:6]) + ("..." if len(staying) > 6 else "")
-        lines.append(
-            f"Your own tools ({listed}) still run on {HERE} -- only shell, file "
-            f"and code tools move. They read and write this machine's files."
-        )
-
-    if "code_runs_on" in places:
-        lines.append(
-            f"Code you run yourself with execute_code() runs on {places['code_runs_on']}."
-        )
-
-    # Say plainly when the chosen tier is not a security boundary.
-    raw = [
-        getattr(obj, "tools_run_on", None),
-        getattr(obj, "run_on", None),
-        getattr(getattr(obj, "sandbox_config", None), "sandbox_type", None),
-    ]
-    if any(isinstance(v, str) and v.lower() in _NOT_A_BOUNDARY for v in raw) or any(
-        v is True for v in raw
-    ):
-        lines.append(
-            "Note: a separate process is not a security boundary -- it can still "
-            "reach the network and read your files, and its blocked-command "
-            "list can be worked around by ordinary shell syntax. Use docker or a cloud "
-            "provider for untrusted code."
-        )
-
-    if places["thinks_on"] == HERE and places["tools_run_on"] == HERE:
-        lines.append(
-            "Nothing is isolated: tools you pass run in this program, with your "
-            "permissions."
-        )
-    return "\n".join(lines)

src/praisonai-agents/praisonaiagents/agent/execution_mixin.py

@@ -1456,18 +1456,6 @@ Write the complete compiled report:"""
                 after_results = await hook_runner.execute(
                     HookEvent.AFTER_TOOL, after_tool_input, target=function_name
                 )
-                # Honour a post-tool block so a redacted/denied result never
-                # reaches the model (mirrors the BEFORE_TOOL block path above).
-                if hook_runner.is_blocked(after_results):
-                    reason = hook_runner.get_blocking_reason(after_results)
-                    logging.warning(f"Tool {function_name} result blocked by AFTER_TOOL hook")
-                    return _record_async_loop_outcome(
-                        reason or f"Result of {function_name} was blocked by security policy."
-                    )
-                # Read back any rewritten/redacted tool_output so a plugin can
-                # scrub secrets before the result reaches the model.
-                if getattr(after_tool_input, "tool_output", result) is not result:
-                    result = after_tool_input.tool_output
                 extra_context = hook_runner.aggregate_context(after_results)
                 if extra_context:
                     if isinstance(result, str):
@@ -1519,7 +1507,6 @@ Write the complete compiled report:"""
                 run_id=getattr(self, '_current_run_id', 'unknown'),
                 session_id=getattr(self, '_session_id', None) or 'default',
                 tool_name=function_name,
-                metadata={"tool_call_id": tool_call_id},
             ),
         )
 
@@ -1541,7 +1528,6 @@ Write the complete compiled report:"""
 
     async def _execute_tool_async_with_retry(self, function_name: str, arguments: Dict[str, Any], tool_call_id: Optional[str] = None, tools_override: Optional[List] = None) -> Any:
         """Async tool execution with retry policy (middleware-agnostic core)."""
-        from ..errors import ToolExecutionError
 
         # Get retry policy (tool-level > agent-level > default)
         retry_policy = self._get_tool_retry_policy(function_name)
@@ -1558,39 +1544,22 @@ Write the complete compiled report:"""
                     # Skip retry for non-retryable errors (approval, permission, etc.).
                     # `retryable is False` covers async tool timeouts, whose executor
                     # work cannot be cancelled — retrying would duplicate side effects.
-                    # `loop_blocked` is a terminal loop-guard decision — retrying would
-                    # defeat the doom-loop protection this stop is meant to add.
                     if (result.get("approval_denied") or 
                         result.get("permission_denied") or 
                         result.get("approval_error") or
                         result.get("circuit_open") or
-                        result.get("loop_blocked") or
-                        result.get("_praison_retryable") is False):
-                        result.pop("_praison_retryable", None)
+                        result.get("retryable") is False):
                         return result
                     
                     # Determine error type for retry policy
                     error_type = self._classify_error_type(result, last_exception)
                     
-                    # Check if we should retry. A tool that *raised* is flattened
-                    # into an error dict before it can be classified, so it always
-                    # arrives here as "unknown" — which no default retry_on
-                    # contains. The sync path escalates exactly those error types
-                    # to its own retry loop (tool_execution.py:853-866); honouring
-                    # the impl's explicit `retryable` flag is how the async path
-                    # reaches the same decision instead of never retrying at all.
-                    # `_praison_retryable` is a private control-plane key (see
-                    # _execute_tool_async_impl): a tool's own result may legitimately
-                    # contain "retryable" (common for HTTP-API wrappers) and must
-                    # never steer our retry loop.
-                    if (not retry_policy.should_retry(error_type, attempt)
-                            and result.get("_praison_retryable") is not True):
-                        result.pop("_praison_retryable", None)
+                    # Check if we should retry
+                    if not retry_policy.should_retry(error_type, attempt):
                         return result
                     
                     # Don't retry on last attempt
                     if attempt == retry_policy.max_attempts - 1:
-                        result.pop("_praison_retryable", None)
                         return result
                     
                     # Emit retry hook event  
@@ -1604,11 +1573,6 @@ Write the complete compiled report:"""
                     # Success - return result
                     return result
                     
-            except ToolExecutionError:
-                # A loop-guard HALT (raised in _execute_tool_async_impl) is a
-                # terminal, non-retryable decision — let it propagate to stop the
-                # run instead of retrying or swallowing it into an error dict.
-                raise
             except Exception as e:
                 last_exception = e
                 # Determine if retryable
@@ -1640,7 +1604,6 @@ Write the complete compiled report:"""
 
     async def _execute_tool_async_impl(self, function_name: str, arguments: Dict[str, Any], tool_call_id: Optional[str] = None, tools_override: Optional[List] = None) -> Any:
         """Internal async tool execution implementation"""
-        from ..errors import ToolExecutionError
         try:
             logging.info(f"Executing async tool: {function_name} with arguments: {arguments}")
             
@@ -1688,29 +1651,6 @@ Write the complete compiled report:"""
                 logging.error(f"Function {function_name} not found in tools")
                 return {"error": f"Function {function_name} not found in tools"}
 
-            # Loop guard (pre-execution) — parity with the sync path in
-            # tool_execution.py. The async path previously had no loop-guard or
-            # doom-loop protection, so a repeatedly-failing tool could be hammered
-            # every turn via achat()/async workflows. check() is pure/sync, so it
-            # is safe to call here without awaiting.
-            loop_guard = None
-            if hasattr(self, '_ensure_loop_guard'):
-                loop_guard = self._ensure_loop_guard()
-                from ..escalation.loop_guard import GuardAction
-                decision = loop_guard.check(function_name, arguments, is_pre_execution=True)
-                if decision.action == GuardAction.BLOCK:
-                    logging.warning(f"Loop guard blocked {function_name}: {decision.message}")
-                    return {"error": f"[loop-guard] {decision.message}", "loop_blocked": True}
-                elif decision.action == GuardAction.HALT:
-                    raise ToolExecutionError(
-                        f"[loop-guard] {decision.message}",
-                        tool_name=function_name,
-                        agent_id=self.name,
-                        is_retryable=False,
-                    )
-                elif decision.action == GuardAction.WARN:
-                    logging.warning(f"Loop guard warning for {function_name}: {decision.message}")
-
             # Activate the tool-progress channel so tools running under the async
             # path can stream incremental output (emit_tool_progress) and the
             # built-in todo tool can publish live updates (emit_todo_update),
@@ -1783,33 +1723,14 @@ Write the complete compiled report:"""
                         # a duplicate invocation while the original keeps executing —
                         # duplicating DB writes / API calls / file mutations. Surface the
                         # timeout once instead of re-running an uncancellable side effect.
-                        # Fall through (not return) so the loop guard records this
-                        # timeout as a failure — repeated timeouts must accumulate
-                        # toward the BLOCK/HALT thresholds like any other failure.
-                        result = {
+                        return {
                             "error": f"Tool timed out after {tool_timeout}s",
                             "timeout": True,
-                            "_praison_retryable": False,
+                            "retryable": False,
                         }
                 else:
                     result = await _invoke()
-
-                # Loop guard (post-execution) — record the outcome and surface a
-                # block/halt decision back to the model on this same turn, mirroring
-                # the sync path in tool_execution.py so repeated failures accumulate
-                # toward the BLOCK/HALT thresholds instead of retrying unbounded.
-                if loop_guard is not None:
-                    is_success = result is not None and not (isinstance(result, dict) and result.get('error'))
-                    loop_guard.record(function_name, arguments, is_success, result=result)
-                    decision = loop_guard.check(function_name, arguments, is_pre_execution=False)
-                    if decision.action.value in ("warn", "block", "halt"):
-                        if isinstance(result, str):
-                            result = f"{result}\n\n[loop-guard] {decision.message}"
-                        elif isinstance(result, dict):
-                            result["_loop_guard"] = {"message": decision.message, "action": decision.action.value}
-                        else:
-                            result = {"value": result, "_loop_guard": {"message": decision.message, "action": decision.action.value}}
-
+                
                 # Ensure result is JSON serializable
                 logging.debug(f"Raw result from tool: {result}")
                 if result is None:
@@ -1823,61 +1744,24 @@ Write the complete compiled report:"""
 
             except Exception as e:
                 logging.error(f"Error executing {function_name}: {str(e)}", exc_info=True)
-                # Record the failed invocation so repeated identical failures
-                # accumulate toward the loop-guard BLOCK/HALT thresholds — a raised
-                # tool exception is a failure just like an error-dict result on the
-                # sync path. The next pre-execution check will then BLOCK/HALT.
-                if loop_guard is not None:
-                    loop_guard.record(function_name, arguments, False, result=None)
-                # Carry the retry verdict with the flattened exception. Without it
-                # the caller only sees an opaque error string, classifies it as
-                # "unknown" (never in RetryPolicy.retry_on) and gives up — while
-                # the sync path, which still has the exception object, retries.
-                # Mirror the sync path exactly: a ToolExecutionError already
-                # carries an explicit is_retryable verdict (e.g. a terminal
-                # non-retryable failure) and must be honoured verbatim; for any
-                # other exception apply the same terminal rule — programming
-                # errors are terminal, everything else may be retried.
-                if isinstance(e, ToolExecutionError):
-                    retryable = e.is_retryable
-                else:
-                    retryable = not isinstance(e, (ValueError, TypeError, AttributeError))
-                # Private control-plane key: a tool's own result may legitimately
-                # contain "retryable" (common for HTTP-API wrappers) and must not
-                # collide with the framework's verdict nor leak to the model.
-                return {
-                    "error": f"Error executing {function_name}: {str(e)}",
-                    "_praison_retryable": retryable,
-                }
+                return {"error": f"Error executing {function_name}: {str(e)}"}
 
-        except ToolExecutionError:
-            # A loop-guard HALT must propagate to stop the run, mirroring the sync
-            # path; do not swallow it into an error dict.
-            raise
         except Exception as e:
             logging.error(f"Error in execute_tool_async: {str(e)}", exc_info=True)
             return {"error": f"Error in execute_tool_async: {str(e)}"}
 
-    def launch(self, path: str = '/', port: int = 8000, host: str = '127.0.0.1', debug: bool = False, protocol: str = "http"):
+    def launch(self, path: str = '/', port: int = 8000, host: str = '0.0.0.0', debug: bool = False, protocol: str = "http"):
         """
         Launch the agent as an HTTP API endpoint or MCP server.
         
         This method now delegates to protocol-based launchers to follow
         the protocol-driven architecture. Heavy implementations (FastAPI/uvicorn)
         are only imported when needed through lazy loading.
-
-        Request authorisation matches ``PraisonAIAgents.launch``: when
-        ``PRAISONAI_LAUNCH_AUTH_TOKEN`` is set, every HTTP route requires that
-        bearer token (401 otherwise). When it is unset and ``host`` is
-        non-loopback, a one-time token is generated and printed rather than
-        serving an unauthenticated endpoint on all interfaces.
-
+        
         Args:
             path: API endpoint path (default: '/') for HTTP, or base path for MCP.
             port: Server port (default: 8000)
-            host: Server host (default: '127.0.0.1'; changed from '0.0.0.0' to
-                avoid binding all interfaces by default — pass '0.0.0.0'
-                explicitly to expose externally).
+            host: Server host (default: '0.0.0.0')
             debug: Enable debug mode (default: False)
             protocol: "http" to launch as FastAPI, "mcp" to launch as MCP server.
             
@@ -1901,8 +1785,6 @@ Write the complete compiled report:"""
         """
         global _server_started, _registered_agents, _shared_apps, _server_lock
 
-        from .launch_security import authorise_launch_request, resolve_launch_host
-
         # Try to import FastAPI dependencies - lazy loading
         try:
             import uvicorn
@@ -1927,15 +1809,7 @@ Write the complete compiled report:"""
             print("\nOr install all API dependencies with:")
             print("pip install 'praisonaiagents[api]'")
             return None
-
-        # Fail-closed bind guard: refuse to serve keyless on a non-loopback host
-        # (auto-generates and prints a one-time token instead). Matches the
-        # serve/jobs precedent and keeps this path in lock-step with
-        # PraisonAIAgents.launch. Applied only after the dependency guard above
-        # so a launch that bails out (missing deps) cannot mutate the
-        # process-wide launch token and retroactively 401 a running endpoint.
-        host = resolve_launch_host(host)
-
+                
         should_start = False
         with _server_lock:
             # Initialize port-specific collections if needed (once per port)
@@ -1988,8 +1862,6 @@ Write the complete compiled report:"""
             # Define the endpoint handler
             @_shared_apps[port].post(path)
             async def handle_agent_query(request: Request, query_data: Optional[AgentQuery] = None):
-                if not authorise_launch_request(request):
-                    raise HTTPException(status_code=401, detail="Unauthorized")
                 # Handle both direct JSON with query field and form data
                 if query_data is None:
                     try:

src/praisonai-agents/praisonaiagents/agent/handoff.py

@@ -14,7 +14,6 @@ from typing import Optional, Any, Callable, Dict, List, Union, TYPE_CHECKING, Li
 from dataclasses import dataclass, field
 from enum import Enum
 import inspect
-from contextlib import contextmanager
 from praisonaiagents._logging import get_logger
 import asyncio
 import contextvars
@@ -470,46 +469,12 @@ class Handoff:
                     return value
         return 'gpt-4o-mini'
 
-    @contextmanager
-    def _seed_target_history(self, prior_messages: Optional[List[Any]]):
-        """Temporarily seed the filtered handoff context onto the target agent.
-
-        The configured ``context_policy``/``input_filter`` produce the messages the
-        target should see; without seeding them the target only ever received the
-        literal handoff prompt string and the configured policy had no effect.
-
-        The seeding is *invocation-scoped*: the prior messages are prepended for the
-        duration of this handoff and the target's original ``chat_history`` is
-        restored on exit. This keeps handoff context from leaking into later
-        handoffs or ordinary chats that reuse the same target agent, and stops the
-        target prompt from growing across sequential handoffs.
-        No shared mutable state is retained between agents.
-        """
-        existing = getattr(self.agent, 'chat_history', None)
-        if not prior_messages or not isinstance(existing, list):
-            yield
-            return
-        try:
-            prior = list(prior_messages)
-        except TypeError:
-            yield
-            return
-        original = existing
-        try:
-            # Avoid re-seeding if the context is already at the head.
-            if existing[:len(prior)] != prior:
-                self.agent.chat_history = prior + existing
-            yield
-        finally:
-            self.agent.chat_history = original
-
     def _execute_with_runtime_resolution(
         self, 
         source_agent: 'Agent', 
         prompt: str, 
         effective_tools: Optional[List[Any]], 
-        context: Dict[str, Any],
-        prior_messages: Optional[List[Any]] = None,
+        context: Dict[str, Any]
     ) -> str:
         """Execute handoff through the target agent's full chat pipeline."""
         target_model_ref = self._extract_model_ref(self.agent)
@@ -519,16 +484,14 @@ class Handoff:
             target_model_ref,
             _get_handoff_depth(),
         )
-        with self._seed_target_history(prior_messages):
-            return self.agent.chat(prompt, tools=effective_tools)
+        return self.agent.chat(prompt, tools=effective_tools)
     
     async def _execute_with_runtime_resolution_async(
         self, 
         source_agent: 'Agent', 
         prompt: str, 
         effective_tools: Optional[List[Any]], 
-        context: Dict[str, Any],
-        prior_messages: Optional[List[Any]] = None,
+        context: Dict[str, Any]
     ) -> str:
         """Execute handoff through the target agent's full async chat pipeline."""
         target_model_ref = self._extract_model_ref(self.agent)
@@ -538,14 +501,13 @@ class Handoff:
             target_model_ref,
             _get_handoff_depth(),
         )
-        with self._seed_target_history(prior_messages):
-            async_chat = getattr(self.agent, 'achat', None)
-            if callable(async_chat) and inspect.iscoroutinefunction(async_chat):
-                return await async_chat(prompt, tools=effective_tools)
-            loop = asyncio.get_running_loop()
-            return await loop.run_in_executor(
-                None, lambda: self.agent.chat(prompt, tools=effective_tools)
-            )
+        async_chat = getattr(self.agent, 'achat', None)
+        if callable(async_chat) and inspect.iscoroutinefunction(async_chat):
+            return await async_chat(prompt, tools=effective_tools)
+        loop = asyncio.get_running_loop()
+        return await loop.run_in_executor(
+            None, lambda: self.agent.chat(prompt, tools=effective_tools)
+        )
     
     def _check_safety(self, source_agent: 'Agent') -> None:
         """
@@ -699,9 +661,8 @@ class Handoff:
             # Execute on_handoff callback
             self._execute_callback(self.config.on_handoff or self.on_handoff, source_agent, kwargs)
             
-            # Prepare context per the configured context_policy/input_filter and
-            # thread the filtered history through to the target agent.
-            handoff_data = self._prepare_context(source_agent, kwargs)
+            # Prepare context (for future extensibility - context data available for hooks)
+            _ = self._prepare_context(source_agent, kwargs)
             
             # Build prompt with context
             context_prefix = f"[Handoff from {source_agent.name}] "
@@ -716,8 +677,7 @@ class Handoff:
             
             # Resolve runtime at turn-time instead of using construction-time pin
             response = self._execute_with_runtime_resolution(
-                source_agent, full_prompt, effective_tools, kwargs,
-                prior_messages=handoff_data.messages,
+                source_agent, full_prompt, effective_tools, kwargs
             )
             
             result = HandoffResult(
@@ -809,9 +769,8 @@ class Handoff:
                 # Execute callback
                 self._execute_callback(self.config.on_handoff or self.on_handoff, source_agent, kwargs)
                 
-                # Prepare context per the configured context_policy/input_filter
-                # and thread the filtered history through to the target agent.
-                handoff_data = self._prepare_context(source_agent, kwargs)
+                # Prepare context (for future extensibility)
+                _ = self._prepare_context(source_agent, kwargs)
                 
                 # Build prompt
                 context_prefix = f"[Handoff from {source_agent.name}] "
@@ -826,8 +785,7 @@ class Handoff:
                 
                 # Resolve runtime at turn-time for async execution
                 response = await self._execute_with_runtime_resolution_async(
-                    source_agent, full_prompt, effective_tools, kwargs,
-                    prior_messages=handoff_data.messages,
+                    source_agent, full_prompt, effective_tools, kwargs
                 )
                 
                 result = HandoffResult(
@@ -940,39 +898,20 @@ class Handoff:
                 # Prepare handoff data with context policy
                 handoff_data = self._prepare_context(source_agent, kwargs)
                 
-                # Get the last user message or context to pass to target agent.
-                # Track the index of the message chosen for ``prompt`` so exactly
-                # that item is excluded from the seeded history (it may not be the
-                # final list item if an assistant/tool message follows it).
+                # Get the last user message or context to pass to target agent
                 last_message = None
-                selected_index = None
-                for i in range(len(handoff_data.messages) - 1, -1, -1):
-                    msg = handoff_data.messages[i]
+                for msg in reversed(handoff_data.messages):
                     if isinstance(msg, dict) and msg.get('role') == 'user':
                         last_message = msg.get('content', '')
-                        selected_index = i
                         break
                 
                 if not last_message and handoff_data.messages:
-                    selected_index = len(handoff_data.messages) - 1
-                    last_msg = handoff_data.messages[selected_index]
+                    last_msg = handoff_data.messages[-1]
                     if isinstance(last_msg, dict):
                         last_message = last_msg.get('content', '')
                     else:
                         last_message = str(last_msg)
-
-                # Tool-style handoff (as_tool): ContextPolicy.NONE discards the
-                # history, so the prompt must come from the generated ``task``/
-                # ``prompt`` argument instead. Without this the sub-agent would
-                # never run and the tool would report a hollow "completed". The
-                # task is the sub-agent's whole instruction, so it is passed
-                # verbatim rather than wrapped in a ``[Handoff from …]`` prefix.
-                task_prompt = None
-                if not last_message and not self.input_type:
-                    task_prompt = kwargs.get('task') or kwargs.get('prompt')
-                    if task_prompt:
-                        last_message = str(task_prompt)
-
+                
                 # Prepare context information
                 context_info = f"[Handoff from {source_agent.name}] "
                 if kwargs and self.input_type:
@@ -980,26 +919,15 @@ class Handoff:
                 
                 # Execute the target agent with tool boundary enforcement
                 if last_message:
-                    prompt = last_message if task_prompt else context_info + last_message
+                    prompt = context_info + last_message
                     logger.info(f"Handing off to {self.agent.name} with prompt: {prompt}")
                     
                     # Compute effective tools based on tool policy
                     effective_tools = self._compute_effective_tools(source_agent)
                     
-                    # Resolve runtime at turn-time for tool function execution.
-                    # The selected message is already folded into ``prompt`` above,
-                    # so exclude exactly that item from the seeded history to avoid
-                    # duplicating it while preserving any messages that follow it.
-                    if selected_index is None:
-                        prior_messages = list(handoff_data.messages)
-                    else:
-                        prior_messages = (
-                            handoff_data.messages[:selected_index]
-                            + handoff_data.messages[selected_index + 1:]
-                        )
+                    # Resolve runtime at turn-time for tool function execution
                     response = self._execute_with_runtime_resolution(
-                        source_agent, prompt, effective_tools, kwargs,
-                        prior_messages=prior_messages,
+                        source_agent, prompt, effective_tools, kwargs
                     )
                     
                     result = HandoffResult(
@@ -1067,17 +995,6 @@ class Handoff:
                     )
                 )
             handoff_tool.__signature__ = inspect.Signature(sig_params)
-        elif self.config.context_policy == ContextPolicy.NONE:
-            # Tool-style handoff (as_tool): no conversation context is passed, so
-            # advertise an explicit ``task`` parameter the caller must fill. This
-            # is what ``handoff_tool`` reads as the sub-agent's prompt above.
-            handoff_tool.__signature__ = inspect.Signature([
-                inspect.Parameter(
-                    'task',
-                    inspect.Parameter.KEYWORD_ONLY,
-                    annotation=str,
-                )
-            ])
         
         return handoff_tool
 
@@ -1551,9 +1468,8 @@ class TypedHandoff(Handoff, Generic[T]):
             # Execute on_handoff callback
             self._execute_callback(self.config.on_handoff or self.on_handoff, source_agent, kwargs)
             
-            # Apply context policy / input filter; the resulting messages are
-            # seeded onto the target only for the duration of its chat below.
-            handoff_data = self._prepare_context(source_agent, kwargs)
+            # Apply input filter if provided (fixes Greptile P1 issue)
+            _ = self._prepare_context(source_agent, kwargs)
             
             # Validate payload against schema
             try:
@@ -1580,8 +1496,7 @@ class TypedHandoff(Handoff, Generic[T]):
             logger.info(f"Typed handoff to {self.agent.name} with validated payload")
             
             # Execute with timeout if sync
-            with self._seed_target_history(handoff_data.messages):
-                response = self.agent.chat(full_prompt)
+            response = self.agent.chat(full_prompt)
             
             result = HandoffResult(
                 success=True,
@@ -1666,9 +1581,8 @@ class TypedHandoff(Handoff, Generic[T]):
                 # Execute callback
                 self._execute_callback(self.config.on_handoff or self.on_handoff, source_agent, kwargs)
                 
-                # Apply context policy / input filter; the resulting messages are
-                # seeded onto the target only for the duration of its chat below.
-                handoff_data = self._prepare_context(source_agent, kwargs)
+                # Apply input filter if provided (fixes Greptile P1 issue)
+                _ = self._prepare_context(source_agent, kwargs)
                 
                 # Validate payload against schema
                 try:
@@ -1694,13 +1608,12 @@ class TypedHandoff(Handoff, Generic[T]):
                 logger.info(f"Async typed handoff to {self.agent.name}")
                 
                 # Execute - check for async chat method
-                with self._seed_target_history(handoff_data.messages):
-                    if hasattr(self.agent, 'achat'):
-                        response = await self.agent.achat(full_prompt)
-                    else:
-                        # Run sync chat in executor
-                        loop = asyncio.get_event_loop()
-                        response = await loop.run_in_executor(None, self.agent.chat, full_prompt)
+                if hasattr(self.agent, 'achat'):
+                    response = await self.agent.achat(full_prompt)
+                else:
+                    # Run sync chat in executor
+                    loop = asyncio.get_event_loop()
+                    response = await loop.run_in_executor(None, self.agent.chat, full_prompt)
                 
                 return HandoffResult(
                     success=True,

src/praisonai-agents/praisonaiagents/agent/launch_security.py

@@ -1,88 +0,0 @@
-"""Shared authorisation + bind guard for the ``launch()`` serving paths.
-
-Both ``Agent.launch()`` (``agent/execution_mixin.py``) and
-``PraisonAIAgents.launch()`` (``agents/agents.py``) expose a prompt-execution
-HTTP endpoint. They must enforce identical request authorisation and must not
-silently bind all interfaces without a token. Factoring the two helpers here
-keeps that policy in one place so the two launch paths cannot drift apart.
-
-Stdlib only — no heavy imports, no new public params.
-"""
-
-from __future__ import annotations
-
-import os
-import secrets as _secrets
-from typing import Optional
-
-__all__ = [
-    "launch_auth_token",
-    "authorise_launch_request",
-    "resolve_launch_host",
-]
-
-# Hosts that are safe to serve keyless on: loopback only.
-_LOOPBACK_HOSTS = frozenset({"127.0.0.1", "::1", "localhost"})
-
-# One auto-generated token per process, reused across launches so a later
-# non-loopback launch cannot mint a fresh token and lock out an endpoint that
-# is already serving with the previously generated one.
-_GENERATED_TOKEN: Optional[str] = None
-
-
-def launch_auth_token() -> Optional[str]:
-    """Return the configured launch bearer token, if any."""
-    return os.environ.get("PRAISONAI_LAUNCH_AUTH_TOKEN")
-
-
-def authorise_launch_request(request) -> bool:
-    """Return True if the request carries the configured bearer token.
-
-    When no token is configured this returns True (local-dev flow preserved).
-    Accepts either ``Authorization: Bearer <token>`` or ``X-Auth-Token``.
-    """
-    token = launch_auth_token()
-    if not token:
-        return True
-    auth = request.headers.get("Authorization", "")
-    if auth.startswith("Bearer ") and _secrets.compare_digest(auth[7:], token):
-        return True
-    supplied = request.headers.get("X-Auth-Token", "")
-    return bool(supplied) and _secrets.compare_digest(supplied, token)
-
-
-def _is_loopback(host: str) -> bool:
-    return host in _LOOPBACK_HOSTS
-
-
-def resolve_launch_host(host: str) -> str:
-    """Fail-closed bind guard, mirroring the ``serve``/jobs precedent.
-
-    * Token set → bind ``host`` unchanged (auth protects the endpoint).
-    * Token unset + loopback host → bind unchanged (local dev unchanged).
-    * Token unset + non-loopback host → auto-generate a token, export it via
-      ``PRAISONAI_LAUNCH_AUTH_TOKEN`` so every route enforces it, and print it
-      once. This closes the unauthenticated-exposure hole without refusing to
-      start.
-
-    Returns the host to bind (unchanged; the guard acts on the token, not the
-    host, so an explicit ``0.0.0.0`` is still honoured — just never keyless).
-
-    A generated token is reused for the lifetime of the process: repeated
-    non-loopback launches share the one token rather than each minting a fresh
-    one, so a later launch cannot invalidate an already-running endpoint's
-    clients.
-    """
-    if launch_auth_token() or _is_loopback(host):
-        return host
-
-    global _GENERATED_TOKEN
-    if _GENERATED_TOKEN is None:
-        _GENERATED_TOKEN = _secrets.token_urlsafe(32)
-        print(
-            f"🔐 launch() bound to non-loopback host {host!r} without "
-            f"PRAISONAI_LAUNCH_AUTH_TOKEN set. Generated a one-time bearer token "
-            f"(set PRAISONAI_LAUNCH_AUTH_TOKEN to override): {_GENERATED_TOKEN}"
-        )
-    os.environ["PRAISONAI_LAUNCH_AUTH_TOKEN"] = _GENERATED_TOKEN
-    return host

src/praisonai-agents/praisonaiagents/agent/ocr_agent.py

@@ -89,8 +89,8 @@ class OCRAgent:
             ocr: OCR configuration
             verbose: Verbosity level for output
         """
-        from ..utils.model_alias import resolve_model_name
-        llm = resolve_model_name(llm, model, "OCRAgent")
+        if llm is None and model is not None:
+            llm = model
         
         self.name = name or "OCRAgent"
         self.instructions = instructions

src/praisonai-agents/praisonaiagents/agent/placement.py

@@ -1,211 +0,0 @@
-"""One vocabulary for "where does this run?", shared by Agent, AgentFlow and AgentTeam.
-
-Two questions get asked about placement and they have different answers:
-
-``run_on=``
-    Where the **whole agent** runs -- the model calls, the loop, the tools, all
-    of it on someone else's machine. Only a *managed runtime* can answer this,
-    because running the loop remotely means something has to host the loop.
-
-``tools_run_on=``
-    Where **the tools** run. Thinking stays on this machine; only the shell,
-    the file writes and the code execution move. Any sandbox or compute place
-    can answer this, because all it has to do is run a command.
-
-Keeping the two words apart is the entire point. The old surface used one word
-(``run_on=``) on ``AgentFlow``/``AgentTeam`` for the tools-only meaning, another
-(``compute=``) on ``LocalAgent`` for exactly the same meaning, and a third
-(``backend=``) for the whole-agent meaning -- so the same concept had two names
-and one name had two concepts.
-
-Because the two questions have disjoint answer sets, a wrong pairing is a typo
-worth catching rather than a preference worth honouring. ``run_on="docker"``
-cannot mean anything: Docker does not host agent loops. It gets a ``TypeError``
-naming the parameter the user actually wanted, not a silent fallback.
-"""
-
-from __future__ import annotations
-
-from typing import Any, Literal, NamedTuple, Optional, Union
-
-# Runtimes that can host an entire agent loop. Resolved from the wrapper's
-# entry-point registry when it is installed so third-party backends work with
-# `run_on=` too; the literal is the floor, not the ceiling.
-_FALLBACK_MANAGED = ("anthropic",)
-
-# Static spellings so editors can autocomplete and type-checkers can reject a
-# typo at the call site rather than at the first model turn. The runtime
-# functions below stay the authority for validation -- these exist for tooling,
-# which cannot call a function to learn a set.
-# Keep in sync with _compute_bridge._PROVIDERS | _sandbox_adapter.SANDBOX_ONLY.
-ManagedRuntime = Literal["anthropic"]
-
-ToolPlace = Literal[
-    "local", "subprocess", "sandlock", "docker", "e2b",
-    "modal", "daytona", "flyio", "tenki", "novita", "ssh",
-]
-
-
-def managed_runtimes() -> tuple:
-    """Names that ``run_on=`` accepts -- places that host a whole agent."""
-    try:
-        from praisonai.integrations.backend_registry import get_backend_registry
-
-        names = tuple(get_backend_registry().list_all_names())
-        if names:
-            return tuple(sorted(set(names) | set(_FALLBACK_MANAGED)))
-    except Exception:
-        pass
-    return _FALLBACK_MANAGED
-
-
-def tool_places() -> list:
-    """Names that ``tools_run_on=`` accepts -- places that can run a command.
-
-    Includes the resolver's aliases. Validation runs before resolution, so
-    leaving them out rejected spellings the resolver handles happily:
-    ``tools_run_on="native"`` raised "not a known place" while
-    ``resolve_compute("native")`` returned a working sandlock adapter.
-    """
-    try:
-        from ..managed._compute_bridge import _ALIASES, available_providers
-
-        return sorted(set(available_providers()) | set(_ALIASES))
-    except Exception:
-        return ["local", "docker"]
-
-
-class Placement(NamedTuple):
-    """The resolved answer to "where does this run?"."""
-
-    whole: Optional[Any] = None   # managed runtime name/object, or None
-    tools: Optional[Any] = None   # tools place name/object, or None
-
-
-def _name_of(value: Any) -> Optional[str]:
-    """The comparable name of a placement value, or None if it is an object.
-
-    Objects (a built provider, a live ``SSHSandbox``) carry their own config and
-    are never second-guessed -- only bare strings get routed by name.
-    """
-    return value.lower() if isinstance(value, str) else None
-
-
-def _quote_list(names) -> str:
-    return ", ".join(repr(n) for n in names)
-
-
-def resolve_placement(
-    owner: str,
-    *,
-    run_on: Any = None,
-    tools_run_on: Any = None,
-    backend: Any = None,
-    supports_run_on: bool = True,
-) -> Placement:
-    """Validate placement arguments and return where things should run.
-
-    ``owner`` is the class name, used only to make errors read naturally.
-    ``supports_run_on`` is False for AgentFlow/AgentTeam, which can place tools
-    but cannot (yet) hand a whole multi-agent run to a managed runtime.
-
-    Raises:
-        TypeError: on any combination that names two different places for the
-            same thing, or a place that cannot do the job asked of it.
-    """
-    managed = managed_runtimes()
-    places = tool_places()
-
-    # ── a place that cannot do the job asked of it ───────────────────────────
-    run_on_name = _name_of(run_on)
-    if run_on_name is not None and run_on_name not in managed:
-        if run_on_name in places:
-            raise TypeError(
-                f"{owner}(run_on={run_on!r}) is not valid: run_on= places the "
-                f"whole agent -- model calls, loop and tools -- on a managed "
-                f"runtime, and {run_on_name!r} runs commands but cannot host an "
-                f"agent loop.\n"
-                f"  To run only the tools there:  {owner}(tools_run_on={run_on!r})\n"
-                f"  Runtimes that host a whole agent: {_quote_list(managed)}"
-            )
-        raise TypeError(
-            f"{owner}(run_on={run_on!r}) is not a known managed runtime.\n"
-            f"  Runtimes that host a whole agent: {_quote_list(managed)}\n"
-            f"  Places that can run tools:        {_quote_list(places)} "
-            f"(pass those as tools_run_on=)"
-        )
-
-    tools_name = _name_of(tools_run_on)
-    if tools_name is not None and tools_name in managed and tools_name not in places:
-        raise TypeError(
-            f"{owner}(tools_run_on={tools_run_on!r}) is not valid: {tools_name!r} "
-            f"hosts an entire agent, not individual tools.\n"
-            f"  Did you mean:  {owner}(run_on={tools_run_on!r})"
-        )
-
-    # A typo here used to survive construction and only surface on the first
-    # model turn -- after the prompt was built and, for a real run, after the
-    # API spend. run_on= validates at the call site and YAML validates at load
-    # time; this is the same standard for the third spelling.
-    if tools_name is not None and tools_name not in places:
-        raise TypeError(
-            f"{owner}(tools_run_on={tools_run_on!r}) is not a known place.\n"
-            f"  Places that can run tools: {_quote_list(places)}\n"
-            f"  Runtimes that host a whole agent: {_quote_list(managed)} "
-            f"(pass those as run_on=)"
-        )
-
-    # Names that cannot work as a bare string, because the connection details
-    # live in the object. Catch it now rather than at first use.
-    if tools_name is not None:
-        try:
-            from ..managed._sandbox_adapter import NEEDS_INSTANCE
-        except Exception:
-            NEEDS_INSTANCE = {}
-        if tools_name in NEEDS_INSTANCE:
-            raise TypeError(
-                f"{owner}(tools_run_on={tools_run_on!r}) needs more than a name: "
-                f"{NEEDS_INSTANCE[tools_name]}"
-            )
-
-    # ── two names for the same thing ─────────────────────────────────────────
-    if run_on is not None and backend is not None:
-        raise TypeError(
-            f"{owner}(run_on=..., backend=...) sets the agent's runtime twice. "
-            f"run_on={run_on!r} is the short form of backend=HostedAgent("
-            f"provider={run_on!r}); pass one or the other.\n"
-            f"  Use backend= only when you need to configure the runtime "
-            f"(model, system prompt, tools)."
-        )
-
-    if run_on is not None and tools_run_on is not None:
-        raise TypeError(
-            f"{owner}(run_on={run_on!r}, tools_run_on={tools_run_on!r}) points "
-            f"the tools at two machines. run_on= already runs everything -- "
-            f"including tools -- on {run_on!r}.\n"
-            f"  Whole agent remote:  {owner}(run_on={run_on!r})\n"
-            f"  Only tools remote:   {owner}(tools_run_on={tools_run_on!r})"
-        )
-
-    if backend is not None and tools_run_on is not None:
-        raise TypeError(
-            f"{owner}(backend=..., tools_run_on={tools_run_on!r}) points the "
-            f"tools at two machines: backend= runs the whole agent (tools "
-            f"included) on its managed runtime, so the tools cannot also run on "
-            f"{tools_run_on!r}.\n"
-            f"  Drop tools_run_on= to keep the hosted runtime, or drop backend= "
-            f"to keep local thinking with remote tools."
-        )
-
-    # ── a class that cannot answer this question ─────────────────────────────
-    if run_on is not None and not supports_run_on:
-        raise TypeError(
-            f"{owner}(run_on={run_on!r}) is not supported: run_on= hands one "
-            f"agent's whole loop to a managed runtime, and a {owner} "
-            f"orchestrates several agents locally.\n"
-            f"  To run every step's tools in one shared sandbox:\n"
-            f"      {owner}(tools_run_on={run_on!r})\n"
-            f"  To host a single agent's loop, put run_on= on that Agent."
-        )
-
-    return Placement(whole=run_on, tools=tools_run_on)

src/praisonai-agents/praisonaiagents/agent/realtime_agent.py

@@ -57,8 +57,7 @@ class RealtimeAgent:
     def __init__(
         self,
         name: str = "RealtimeAgent",
-        llm: Optional[str] = None,  # Deprecated alias for model=
-        model: Optional[str] = None,
+        llm: Optional[str] = None,
         realtime: Optional[Union[bool, Dict, RealtimeConfig]] = None,
         instructions: Optional[str] = None,
         verbose: bool = True,
@@ -68,16 +67,14 @@ class RealtimeAgent:
         
         Args:
             name: Agent name
-            llm: Deprecated alias for model=. Passing both raises TypeError.
-            model: Model to use (default: gpt-4o-realtime-preview)
+            llm: LLM model (default: gpt-4o-realtime-preview)
             realtime: Realtime configuration (bool, dict, or RealtimeConfig)
             instructions: System instructions
             verbose: Enable verbose output
             **kwargs: Additional arguments
         """
-        from ..utils.model_alias import resolve_model_name
         self.name = name
-        self.llm = resolve_model_name(llm, model, "RealtimeAgent") or "gpt-4o-realtime-preview"
+        self.llm = llm or "gpt-4o-realtime-preview"
         self.instructions = instructions
         self.verbose = verbose
         

src/praisonai-agents/praisonaiagents/agent/sandbox_mixin.py

@@ -52,61 +52,19 @@ class SandboxMixin:
         
         return self._sandbox_manager
     
-
-    def _manager_for(self, run_in: Optional[Union[bool, str, 'SandboxConfig']]):
-        """Return the sandbox manager for a ``run_in=`` argument.
-
-        ``run_in=`` names where a single ``execute_code()`` call runs, so the
-        place lives on the call that uses it rather than on the constructor.
-        ``Agent(sandbox=...)`` still sets the default for every call.
-
-        Managers are cached per place: a fresh ``SandboxManager`` per call would
-        start and tear down a container each time, which for Docker is seconds
-        of latency and for any backend means the previous call's files are gone.
-        """
-        if run_in is None:
-            if not self.has_sandbox:
-                raise RuntimeError(
-                    "No sandbox configured. Either name a place on the call --\n"
-                    "    agent.execute_code_sync(code, run_in='docker')\n"
-                    "or set a default for every call with Agent(sandbox='docker')."
-                )
-            return self.get_sandbox_manager()
-
-        from ..sandbox import SandboxConfig, SandboxManager
-
-        if run_in is True:
-            config = SandboxConfig.subprocess()
-        elif isinstance(run_in, str):
-            config = SandboxConfig(sandbox_type=run_in)
-        else:
-            config = run_in
-
-        key = getattr(config, "sandbox_type", None) or repr(config)
-        cache = getattr(self, "_sandbox_managers", None)
-        if cache is None:
-            cache = self._sandbox_managers = {}
-        if key not in cache:
-            cache[key] = SandboxManager(config)
-        return cache[key]
-
     async def execute_code(
         self,
         code: str,
         language: str = "python",
         check_security: bool = True,
-        run_in: Optional[Union[bool, str, 'SandboxConfig']] = None,
         **kwargs
     ) -> 'SandboxResult':
-        """Execute code safely in a sandbox.
+        """Execute code safely in configured sandbox.
         
         Args:
             code: Code to execute
             language: Programming language (python, bash, etc.)
             check_security: Whether to run security pre-checks
-            run_in: Where to run this call -- "docker", "sandlock",
-                "subprocess", a SandboxConfig, or True for the default local
-                sandbox. Overrides Agent(sandbox=...) for this call only.
             **kwargs: Additional arguments passed to sandbox.execute()
             
         Returns:
@@ -115,39 +73,31 @@ class SandboxMixin:
         Raises:
             RuntimeError: If no sandbox is configured
         """
-        manager = self._manager_for(run_in)
+        if not self.has_sandbox:
+            raise RuntimeError(
+                "No sandbox configured. Set sandbox=True or provide SandboxConfig to Agent()"
+            )
         
         # Security pre-check if enabled
-        security_warnings = None
         if check_security:
             from ..sandbox import check_code_safety, format_warnings
-            security_warnings = check_code_safety(code, language)
-            if security_warnings:
-                warning_text = format_warnings(security_warnings)
+            warnings = check_code_safety(code, language)
+            if warnings:
+                warning_text = format_warnings(warnings)
                 if self.verbose:
                     logger.warning(f"Security warnings for code execution:\n{warning_text}")
-
-        result = await manager.run_code(code, language=language, **kwargs)
-
-        # Attach warnings to the result rather than forwarding a `metadata`
-        # kwarg: SandboxProtocol.execute() has no such parameter, so passing it
-        # through raised TypeError for any code that tripped a warning -- i.e.
-        # sandboxed execution failed exactly when the check mattered most.
-        if security_warnings:
-            try:
-                existing = getattr(result, "metadata", None) or {}
-                existing["security_warnings"] = security_warnings
-                result.metadata = existing
-            except Exception:  # pragma: no cover - result may be immutable
-                logger.debug("Could not attach security warnings to sandbox result")
-        return result
+                
+                # Store warnings in result metadata
+                kwargs.setdefault('metadata', {})['security_warnings'] = warnings
+        
+        manager = self.get_sandbox_manager()
+        return await manager.run_code(code, language=language, **kwargs)
     
     def execute_code_sync(
         self,
         code: str,
         language: str = "python", 
         check_security: bool = True,
-        run_in: Optional[Union[bool, str, 'SandboxConfig']] = None,
         **kwargs
     ) -> 'SandboxResult':
         """Synchronous wrapper for execute_code.
@@ -162,15 +112,12 @@ class SandboxMixin:
             SandboxResult with execution details
         """
         from ..approval.utils import run_coroutine_safely
-        return run_coroutine_safely(
-            self.execute_code(code, language, check_security, run_in=run_in, **kwargs)
-        )
+        return run_coroutine_safely(self.execute_code(code, language, check_security, **kwargs))
     
     async def run_shell_command(
         self,
         command: Union[str, list],
         check_security: bool = True,
-        run_in: Optional[Union[bool, str, 'SandboxConfig']] = None,
         **kwargs
     ) -> 'SandboxResult':
         """Run a shell command in the sandbox.
@@ -183,7 +130,8 @@ class SandboxMixin:
         Returns:
             SandboxResult with execution details
         """
-        manager = self._manager_for(run_in)
+        if not self.has_sandbox:
+            raise RuntimeError("No sandbox configured")
         
         # Convert command to string for security checking
         if isinstance(command, list):
@@ -200,7 +148,7 @@ class SandboxMixin:
                 if self.verbose:
                     logger.warning(f"Security warnings for command:\n{warning_text}")
         
-        async with manager as sandbox:
+        async with self.get_sandbox_manager() as sandbox:
             return await sandbox.run_command(command, **kwargs)
     
     def get_sandbox_status(self) -> Dict[str, Any]:
@@ -282,15 +230,5 @@ class SandboxMixin:
                 return result.stdout or result.output
             else:
                 return f"Error: {result.error or result.stderr}"
-
-        # Tag as framework-generated so clone_for_channel() can drop these
-        # source-bound wrappers and regenerate clone-owned ones. Without the
-        # tag, a clone would inherit tools closing over the *source* agent and
-        # silently share its SandboxManager.
-        generated = [execute_python_code, execute_shell_command]
-        for _t in generated:
-            try:
-                _t._praison_sandbox_tool = True
-            except Exception:  # pragma: no cover - tool object may be immutable
-                pass
-        return generated
+        
+        return [execute_python_code, execute_shell_command]

src/praisonai-agents/praisonaiagents/agent/skill_review.py

@@ -52,29 +52,14 @@ class SkillReviewMixin:
         return policy
 
     def _build_skill_review_tool(self):
-        """Return the restricted toolset for the review turn.
-
-        Always exposes the single skill-mutation tool (``skill_manage``). When
-        the agent has memory enabled, ``store_memory`` is added so the same
-        guarded pass can also persist a durable fact / user-model detail
-        (issue #4030) — closing the learning loop for memory, not just skills,
-        without a second review turn or a parallel knob. The set stays
-        restricted: never the agent's full toolset.
-        """
-        tools = []
+        """Return the restricted toolset for the review turn (skill_manage only)."""
         try:
             from ..tools.skill_tools import create_skill_tools
             skill_tools = create_skill_tools()
-            tools.append(skill_tools.skill_manage)
+            return [skill_tools.skill_manage]
         except Exception as e:  # pragma: no cover - defensive
             logger.debug("Could not build skill review tool: %s", e, exc_info=True)
-        if getattr(self, "memory", None):
-            try:
-                from ..tools.memory import store_memory
-                tools.append(store_memory)
-            except Exception as e:  # pragma: no cover - defensive
-                logger.debug("Could not build memory review tool: %s", e, exc_info=True)
-        return tools
+            return []
 
     def _skill_review_log_context(self):
         """Return (agent_name, session_id) for swallowed-failure warnings."""

src/praisonai-agents/praisonaiagents/agent/tool_execution.py

@@ -22,13 +22,6 @@ from ..config.feature_configs import DEFAULT_TOOL_OUTPUT_LIMIT
 
 logger = logging.getLogger(__name__)
 
-# Upper bound on how many timed-out (still-blocked) tool executors a single
-# agent may retire before it stops recycling and falls back to reusing the
-# existing bounded pool. This keeps the "fresh worker after a timeout"
-# throughput win while capping leaked threads from pathological repeated
-# timeouts so they cannot exhaust process resources.
-_MAX_ORPHANED_TOOL_EXECUTORS = 4
-
 if TYPE_CHECKING:
     pass
 
@@ -374,12 +367,6 @@ class ToolExecutionMixin:
 
         return resolve_tool_names(tool_names)
 
-    def _resolve_tools_list(self, tools):
-        """Resolve any tool-name strings inside a mixed ``tools=`` list."""
-        from ..tools.resolver import resolve_tools_list
-
-        return resolve_tools_list(tools)
-
     def _cast_arguments(self, func, arguments):
         """Cast arguments to their expected types based on function signature."""
         if not callable(func) or not arguments:
@@ -495,7 +482,6 @@ class ToolExecutionMixin:
                 run_id=getattr(self, '_current_run_id', 'unknown'),
                 session_id=getattr(self, '_session_id', None) or 'default',
                 tool_name=function_name,
-                metadata={"tool_call_id": tool_call_id},
             ),
         )
 
@@ -753,21 +739,26 @@ class ToolExecutionMixin:
             if blocked_result is not None:
                 result = blocked_result
             else:
-                # Apply tool retry logic with exponential backoff.
-                # ONE vocabulary: the effective RetryPolicy caps how many times
-                # the tool body may run, whichever of the two loops does the
-                # retrying, and owns the backoff. ExecutionConfig.max_retry_limit
-                # / retry_* are translated into it (see
-                # _effective_tool_retry_policy) rather than run as a second,
-                # independent budget in different units.
-                retry_policy = self._effective_tool_retry_policy(function_name)
-                max_attempts = retry_policy.max_attempts
-
+                # Apply tool retry logic with exponential backoff
+                execution_config = getattr(self, '_execution_config', None)
+                if execution_config is None:
+                    # Fall back to reading individual config attributes for backward compatibility
+                    max_retry_limit = getattr(self, 'max_retry_limit', 2)
+                    retry_initial_delay = 1.0
+                    retry_backoff_factor = 2.0
+                    retry_jitter = 0.1
+                else:
+                    max_retry_limit = execution_config.max_retry_limit
+                    retry_initial_delay = execution_config.retry_initial_delay
+                    retry_backoff_factor = execution_config.retry_backoff_factor
+                    retry_jitter = execution_config.retry_jitter
+                
                 result = None
                 last_exception = None
-
-                # max_attempts is the total number of tool-body runs.
-                for attempt in range(1, max_attempts + 1):
+                
+                # max_retry_limit is the number of retries (not total attempts)
+                # So total attempts = 1 (initial) + max_retry_limit (retries)
+                for attempt in range(1, max_retry_limit + 2):
                     try:
                         # P8/G11: Apply tool timeout if configured
                         tool_timeout = getattr(self, '_tool_timeout', None)
@@ -796,7 +787,7 @@ class ToolExecutionMixin:
                                         return self._execute_tool_with_circuit_breaker(function_name, arguments)
 
                                 # Use reusable executor to prevent resource leaks
-                                if not hasattr(self, '_tool_executor') or self._tool_executor is None:
+                                if not hasattr(self, '_tool_executor'):
                                     self._tool_executor = concurrent.futures.ThreadPoolExecutor(
                                         max_workers=2, thread_name_prefix=f"tool-{self.name}"
                                     )
@@ -809,104 +800,66 @@ class ToolExecutionMixin:
                                         _progress_active.clear()
                                     future.cancel()
                                     logging.warning(f"Tool {function_name} timed out after {tool_timeout}s")
-                                    # Tag as an OUTER wall-clock timeout: unlike an
-                                    # inner-loop timeout (already retried to
-                                    # exhaustion), the body ran once here and the
-                                    # inner budget never saw it, so this one still
-                                    # earns an outer retry pass under the single budget.
-                                    result = {"error": f"Tool timed out after {tool_timeout}s", "timeout": True, "_outer_timeout": True}
-                                    # The timed-out thread cannot be reclaimed. Retire this
-                                    # executor so the next call gets a fresh worker instead of
-                                    # queuing behind a permanently stuck one — but bound how many
-                                    # orphaned (still-blocked) threads we allow to accumulate:
-                                    # once the cap is reached we stop recycling and keep reusing
-                                    # the existing pool so repeated timeouts can't exhaust process
-                                    # resources with an unbounded number of leaked threads.
-                                    orphaned = getattr(self, '_tool_executor_orphaned', 0)
-                                    if orphaned < _MAX_ORPHANED_TOOL_EXECUTORS:
-                                        self._tool_executor.shutdown(wait=False)
-                                        self._tool_executor = None
-                                        self._tool_executor_orphaned = orphaned + 1
+                                    result = {"error": f"Tool timed out after {tool_timeout}s", "timeout": True}
                         else:
                             with tool_progress_channel(_progress_sink), with_injection_context(state):
                                 result = self._execute_tool_with_circuit_breaker(function_name, arguments)
                         
                         # Check if the result indicates a retryable error
                         if isinstance(result, dict) and result.get("error"):
-                            # Approval/permission/policy/guardrail denials are
-                            # legitimate non-retryable outcomes: stop immediately.
-                            if result.get("approval_denied") or result.get("permission_denied") or result.get("approval_error") or result.get("policy_denied") or result.get("guardrail_denied"):
+                            # Check if this is a circuit breaker error (always retryable)
+                            if result.get("circuit_open"):
+                                raise ToolExecutionError(
+                                    result["error"],
+                                    tool_name=function_name,
+                                    agent_id=self.name,
+                                    is_retryable=True,
+                                )
+                            # Check if this is a timeout error (retryable)
+                            elif result.get("timeout"):
+                                raise ToolExecutionError(
+                                    result["error"],
+                                    tool_name=function_name,
+                                    agent_id=self.name,
+                                    is_retryable=True,
+                                )
+                            # For other error dicts: approval/permission denials are legitimate
+                            # non-retryable outcomes; everything else represents a tool failure
+                            # that should engage the outer retry/backoff loop.
+                            elif result.get("approval_denied") or result.get("permission_denied") or result.get("approval_error") or result.get("policy_denied") or result.get("guardrail_denied"):
                                 break
-                            # ONE budget: the inner loop
-                            # (_execute_tool_with_circuit_breaker) already retries
-                            # its retry_on error types (timeout/rate_limit/
-                            # connection_error) to exhaustion before returning here,
-                            # so re-escalating them as retryable would restart the
-                            # whole inner budget on every outer attempt and run the
-                            # tool up to max_attempts² times.
-                            error_type = self._classify_error_type(result, None)
-                            inner_policy = self._get_tool_retry_policy(function_name)
-                            # Only escalate to an outer retry pass when the failure is
-                            # a transient the inner loop did NOT already re-drive:
-                            #   • _outer_timeout — this loop's own wall-clock guard
-                            #     tripped; the body ran once and the inner budget
-                            #     never saw it. BUT the timed-out body is still
-                            #     running in an orphaned thread (future.cancel() is
-                            #     a no-op once started), so retrying a mutating tool
-                            #     would duplicate its side effects. Only re-drive it
-                            #     when the tool is known idempotent/read-only.
-                            #   • circuit_open — returned by the inner loop WITHOUT a
-                            #     body run, so retrying costs no duplicate side effect.
-                            #   • _praison_retryable — a raised exception was flattened
-                            #     into this error dict (see _execute_tool_impl); honour
-                            #     that verdict, but ONLY for error types the inner loop
-                            #     does not itself retry, or inner×outer would run the
-                            #     body max_attempts² times.
-                            # A plain error dict the tool body *returned* carries no tag
-                            # — it is the tool's own reported outcome, not a transient
-                            # the framework must re-drive. The body already ran to
-                            # completion, so re-running it would duplicate its side
-                            # effects (charge money, send a message, write a row) for a
-                            # decision the tool already made. If a user genuinely wants
-                            # such an outcome retried, its error type belongs in the
-                            # RetryPolicy.retry_on the inner loop honours — not a word
-                            # in the tool's own payload. Surface it once.
-                            is_retryable = bool(
-                                (result.get("_outer_timeout")
-                                    and self._is_tool_idempotent(function_name))
-                                or result.get("circuit_open")
-                                or (result.get("_praison_retryable") is True
-                                    and error_type not in inner_policy.retry_on
-                                    # The body already ran and may have completed
-                                    # its side effect before raising. Honour an
-                                    # explicit non-idempotent declaration here, as
-                                    # the _outer_timeout clause above already does.
-                                    and not self._tool_declares_not_idempotent(function_name))
-                            )
-                            # Strip the private control-plane tag before it can reach
-                            # the model or be re-surfaced as the tool's payload.
-                            result.pop("_praison_retryable", None)
-                            raise ToolExecutionError(
-                                result.get("error", f"Tool '{function_name}' failed"),
-                                tool_name=function_name,
-                                agent_id=self.name,
-                                is_retryable=is_retryable,
-                            )
+                            else:
+                                # Avoid compounding with the inner retry loop in
+                                # _execute_tool_with_circuit_breaker: error types it already
+                                # retries (e.g. timeout/rate_limit/connection_error) are
+                                # exhausted by the time they reach here, so escalating them as
+                                # retryable would re-run the entire inner loop from scratch on
+                                # every outer attempt. Only escalate error types the inner loop
+                                # does NOT retry (e.g. "unknown") so they get one outer pass.
+                                error_type = self._classify_error_type(result, None)
+                                inner_policy = self._get_tool_retry_policy(function_name)
+                                is_retryable = error_type not in inner_policy.retry_on
+                                raise ToolExecutionError(
+                                    result.get("error", f"Tool '{function_name}' failed"),
+                                    tool_name=function_name,
+                                    agent_id=self.name,
+                                    is_retryable=is_retryable,
+                                )
                         else:
                             # Success path - return the result
                             break
                             
                     except ToolExecutionError as e:
                         last_exception = e
-                        # Only retry if the error is marked as retryable and the
-                        # policy still has attempts left.
-                        if not e.is_retryable or attempt >= max_attempts:
+                        # Only retry if the error is marked as retryable and we have retries left
+                        # attempt starts at 1, so (attempt - 1) gives us the retry count
+                        if not e.is_retryable or (attempt - 1) >= max_retry_limit:
                             raise e
-
-                        # Calculate delay for exponential backoff (policy owns it)
-                        delay = retry_policy.get_delay_ms(attempt - 1) / 1000.0
+                        
+                        # Calculate delay for exponential backoff
+                        delay = BackoffPolicy.delay(attempt, retry_initial_delay, retry_backoff_factor, retry_jitter)
                         logging.warning(
-                            f"Tool {function_name} failed (attempt {attempt}/{max_attempts}): {e}. "
+                            f"Tool {function_name} failed (attempt {attempt}/{max_retry_limit + 1}): {e}. "
                             f"Retrying in {delay:.2f}s..."
                         )
                         time.sleep(delay)
@@ -922,14 +875,15 @@ class ToolExecutionMixin:
                             is_retryable=is_retryable,
                         )
                         last_exception = tool_error
-
-                        if not is_retryable or attempt >= max_attempts:
+                        
+                        # attempt starts at 1, so (attempt - 1) gives us the retry count
+                        if not is_retryable or (attempt - 1) >= max_retry_limit:
                             raise tool_error from e
-
-                        # Calculate delay for exponential backoff (policy owns it)
-                        delay = retry_policy.get_delay_ms(attempt - 1) / 1000.0
+                        
+                        # Calculate delay for exponential backoff
+                        delay = BackoffPolicy.delay(attempt, retry_initial_delay, retry_backoff_factor, retry_jitter)
                         logging.warning(
-                            f"Tool {function_name} failed (attempt {attempt}/{max_attempts}): {e}. "
+                            f"Tool {function_name} failed (attempt {attempt}/{max_retry_limit + 1}): {e}. "
                             f"Retrying in {delay:.2f}s..."
                         )
                         time.sleep(delay)
@@ -1176,20 +1130,6 @@ class ToolExecutionMixin:
                 )
                 after_tool_results = self._hook_runner.execute_sync(HookEvent.AFTER_TOOL, after_tool_input, target=function_name)
 
-                # Honour a post-tool block: a plugin/hook can deny the result
-                # (e.g. secret/PII detected) so the original output never
-                # reaches the model. Mirrors the BEFORE_TOOL block path above.
-                if self._hook_runner.is_blocked(after_tool_results):
-                    reason = self._hook_runner.get_blocking_reason(after_tool_results)
-                    logging.warning(f"Tool {function_name} result blocked by AFTER_TOOL hook")
-                    return reason or f"Result of {function_name} was blocked by security policy."
-
-                # Read back any rewritten/redacted tool_output so a plugin can
-                # scrub secrets before the result reaches the model. The bridge
-                # mutates ``after_tool_input.tool_output`` in place.
-                if getattr(after_tool_input, "tool_output", result) is not result:
-                    result = after_tool_input.tool_output
-
                 # Surface any additional_context returned by AFTER_TOOL hooks
                 # back to the model by appending it to the tool result (mirrors
                 # the loop-guard injection pattern below). Without this the
@@ -2021,12 +1961,6 @@ class ToolExecutionMixin:
         if not decision.approved:
             error_msg = f"Tool execution denied: {decision.reason}"
             logging.warning(error_msg)
-            feedback = getattr(decision, "feedback", None)
-            if feedback:
-                error_msg = (
-                    f"Tool '{function_name}' was denied by the user. "
-                    f"Do not retry it as-is. User guidance: {feedback}"
-                )
             return {"error": error_msg, "approval_denied": True}
         
         if decision.modified_args:
@@ -2060,12 +1994,6 @@ class ToolExecutionMixin:
         if not decision.approved:
             error_msg = f"Tool execution denied: {decision.reason}"
             logging.warning(error_msg)
-            feedback = getattr(decision, "feedback", None)
-            if feedback:
-                error_msg = (
-                    f"Tool '{function_name}' was denied by the user. "
-                    f"Do not retry it as-is. User guidance: {feedback}"
-                )
             return {"error": error_msg, "approval_denied": True}
         
         if decision.modified_args:
@@ -2108,13 +2036,7 @@ class ToolExecutionMixin:
                         result.get("guardrail_denied") or
                         result.get("circuit_open")):
                         return result
-
-                    # The body already ran and may have completed its side effect
-                    # before failing. Honour an explicit non-idempotent declaration
-                    # rather than re-driving it (send a second email, charge twice).
-                    if self._tool_declares_not_idempotent(function_name):
-                        return result
-
+                    
                     # Determine error type for retry policy
                     error_type = self._classify_error_type(result, last_exception)
                     
@@ -2596,20 +2518,8 @@ class ToolExecutionMixin:
                             f"{error_msg} Expected parameters for '{function_name}' — "
                             f"required: {schema['required']}, optional: {schema['optional']}."
                         )
-                        # An argument-binding error is a programming error — the same
-                        # call will always fail — so mark it terminal and never retry.
-                        return {"error": error_msg, "expected_parameters": schema, "_praison_retryable": False}
-                # A tool that *raised* is flattened into an error dict here, which
-                # erases the exception type the retry policy needs. Carry the same
-                # verdict the exception paths use so the outer loop can retry a
-                # transient failure without re-running a tool that merely *returned*
-                # an error dict of its own. Programming errors are terminal;
-                # everything else may be retried. Private key: never leaks to the
-                # model and cannot collide with a tool's own "retryable" field.
-                return {
-                    "error": error_msg,
-                    "_praison_retryable": not isinstance(e, (ValueError, TypeError, AttributeError)),
-                }
+                        return {"error": error_msg, "expected_parameters": schema}
+                return {"error": error_msg}
 
         # Unresolved: return a corrective, model-readable message so the model can
         # retry with a valid name instead of repeating the same mistake.
@@ -2996,124 +2906,17 @@ class ToolExecutionMixin:
         else:
             return f"Unknown bridge tool: {function_name}"
 
-    def _tool_declares_not_idempotent(self, tool_name):
-        """True only when the tool *explicitly* declares itself unsafe to re-run.
-
-        Deliberately narrower than ``_is_tool_idempotent``, which answers False
-        for unknown tools as a safe default: gating a retry on that would stop
-        retrying every unregistered user tool.
-
-        This keys on an explicit declaration and nothing else. In particular it
-        must NOT consult the shared ``MUTATING_TOOLS`` name registry -- that is a
-        73-name list maintained for the escalation loop guard, and using it here
-        silently removed the retry from any *undeclared* tool that happened to
-        share a name with an entry (``write_file``, ``store_memory``, ``mkdir``...).
-        """
-        tools = getattr(self, 'tools', [])
-        if not isinstance(tools, (list, tuple)):
-            tools = []
-        for tool in tools:
-            name_attr = getattr(tool, '__name__', None) or getattr(tool, 'name', None)
-            if name_attr == tool_name:
-                explicit = getattr(tool, 'idempotent', None)
-                if not isinstance(explicit, bool):
-                    # ``restart_safe`` is the public replay-safety contract on
-                    # ``@tool`` (FunctionTool) and ``BaseTool``: ``False`` marks an
-                    # effectful tool that must never be silently re-executed.
-                    explicit = getattr(tool, 'restart_safe', None)
-                if isinstance(explicit, bool):
-                    return not explicit
-                return False
-        # A tool from the process-global registry (only reachable under
-        # ToolConfig(allow_global_tools=True)) can carry its own declaration;
-        # ``_is_tool_idempotent`` consults it, so this must too.
-        if getattr(self, '_allow_global_tools', False):
-            try:
-                from ..tools.registry import get_registry
-                global_tool = get_registry().get(tool_name)
-                for attr in ('idempotent', 'restart_safe'):
-                    explicit = getattr(global_tool, attr, None)
-                    if isinstance(explicit, bool):
-                        return not explicit
-            except Exception:
-                pass
-        return False
-
-    def _is_tool_idempotent(self, tool_name):
-        """Whether re-running ``tool_name`` is safe (no duplicated side effects).
-
-        Used to decide if an OUTER wall-clock timeout may be retried: the timed-out
-        tool body is still running in an orphaned thread (``future.cancel()`` is a
-        no-op once started), so auto-retrying a mutating tool would duplicate its
-        side effects (send a second email, charge twice). Only tools classified as
-        read-only/idempotent are safe to re-drive.
-
-        Precedence: explicit ``idempotent`` attribute on the tool > the shared
-        read-only/mutating name registry (reused from the escalation loop guard).
-        Unknown tools default to NOT idempotent (safe: surface the timeout once).
-        """
-        tools = getattr(self, 'tools', [])
-        if not isinstance(tools, (list, tuple)):
-            tools = []
-        for tool in tools:
-            tool_name_attr = getattr(tool, '__name__', None) or getattr(tool, 'name', None)
-            if tool_name_attr == tool_name:
-                explicit = getattr(tool, 'idempotent', None)
-                if isinstance(explicit, bool):
-                    return explicit
-                break
-        # A tool from the process-global registry (only reachable when
-        # ToolConfig(allow_global_tools=True)) can carry its own explicit
-        # ``idempotent`` flag even when its name is absent from the shared
-        # read-only/mutating registries below.
-        if getattr(self, '_allow_global_tools', False):
-            try:
-                from ..tools.registry import get_registry
-                global_tool = get_registry().get(tool_name)
-                explicit = getattr(global_tool, 'idempotent', None)
-                if isinstance(explicit, bool):
-                    return explicit
-            except Exception:
-                pass
-        try:
-            from ..escalation.loop_guard import IDEMPOTENT_TOOLS, MUTATING_TOOLS
-        except Exception:
-            return False
-        if tool_name in IDEMPOTENT_TOOLS:
-            return True
-        if tool_name in MUTATING_TOOLS:
-            return False
-        return False
-
     def _get_tool_retry_policy(self, tool_name):
         """Get retry policy for a tool (tool-level > agent-level > default).
-
-        Kept as the historical name; both retry loops now go through
-        ``_effective_tool_retry_policy`` so they share one policy object.
-
+        
         Args:
             tool_name: Name of the tool to get retry policy for
             
         Returns:
             RetryPolicy instance
         """
-        return self._effective_tool_retry_policy(tool_name)
-
-    def _effective_tool_retry_policy(self, tool_name):
-        """The one RetryPolicy that governs every retry of ``tool_name``.
-
-        Precedence: per-tool ``.retry_policy`` > agent-level
-        ``ToolConfig(retry_policy=...)`` > a policy translated from the
-        ExecutionConfig spelling of the same knobs.
-
-        ``ExecutionConfig`` speaks a second vocabulary for the same thing --
-        ``max_retry_limit`` counts *retries* (so total runs = limit + 1),
-        ``retry_initial_delay`` is in *seconds*, and ``retry_jitter`` is a
-        *fraction*. Translating it here, once, is what keeps the two retry loops
-        from running two independent budgets in two different units.
-        """
         from ..tools.retry import RetryPolicy
-
+        
         # Check for tool-level retry policy first
         tools = getattr(self, 'tools', [])
         # Handle non-iterable tools (e.g., single MCP instance)
@@ -3124,43 +2927,16 @@ class ToolExecutionMixin:
             tool_policy = getattr(tool, 'retry_policy', None) if hasattr(tool, 'retry_policy') else None
             if tool_name_attr == tool_name and tool_policy is not None:
                 return tool_policy
-
+        
         # Check for agent-level retry policy
         agent_policy = getattr(self, '_tool_retry_policy', None)
         if agent_policy is not None:
             return agent_policy
-
-        # Translate the ExecutionConfig spelling into the RetryPolicy vocabulary.
-        execution_config = getattr(self, '_execution_config', None)
-        if execution_config is None:
-            max_retry_limit = getattr(self, 'max_retry_limit', 2)
-            initial_delay_s, backoff_factor, jitter_fraction = 1.0, 2.0, 0.1
-        else:
-            max_retry_limit = execution_config.max_retry_limit
-            initial_delay_s = execution_config.retry_initial_delay
-            backoff_factor = execution_config.retry_backoff_factor
-            jitter_fraction = execution_config.retry_jitter
-
-        cached = getattr(self, '_translated_retry_policy', None)
-        key = (max_retry_limit, initial_delay_s, backoff_factor, jitter_fraction)
-        if cached is not None and cached[0] == key:
-            return cached[1]
-        # Reproduce BackoffPolicy.delay's 60s base cap so ExecutionConfig users
-        # keep the exact same delay ceiling they had before this consolidation
-        # (RetryPolicy defaults to a 30s cap). initial_delay_ms must not exceed
-        # max_delay_ms per RetryPolicy validation, so lift the cap to whichever
-        # is larger.
-        initial_delay_ms = int(initial_delay_s * 1000)
-        policy = RetryPolicy(
-            max_attempts=max(1, max_retry_limit + 1),
-            backoff_factor=max(1.0, backoff_factor),
-            initial_delay_ms=initial_delay_ms,
-            max_delay_ms=max(60000, initial_delay_ms),
-            jitter=jitter_fraction > 0,
-            jitter_factor=min(max(jitter_fraction, 0.0), 1.0),
-        )
-        self._translated_retry_policy = (key, policy)
-        return policy
+        
+        # Return default retry policy (cached class-level instance)
+        if not hasattr(ToolExecutionMixin, '_default_retry_policy'):
+            ToolExecutionMixin._default_retry_policy = RetryPolicy()
+        return ToolExecutionMixin._default_retry_policy
 
     def _classify_error_type(self, error_dict, exception):
         """Classify error type for retry policy matching.

src/praisonai-agents/praisonaiagents/agent/tools_placement.py

@@ -1,129 +0,0 @@
-"""Give a single Agent's tools a sandbox, without touching its thinking.
-
-``AgentFlow``/``AgentTeam`` already share one sandbox across a run and tear it
-down when the run ends. A lone ``Agent(tools_run_on=...)`` has no "run" to hang
-that lifetime on -- it is just an object someone calls ``chat()`` on, possibly
-many times -- so the sandbox is created on first use and lives as long as the
-agent does. That is deliberate: a file written in turn 1 is still there in turn
-2, which is what anyone who asked for a working directory expects.
-
-Attachment is idempotent and happens at the top of ``chat``/``achat``/
-``_start_stream``, and in ``AgentTeam`` before the task's tool list is
-snapshotted. Doing it once, rather than wrapping each call in a context
-manager, sidesteps two real hazards in this codebase:
-
-* ``_start_stream`` is a **generator**; a context manager around the call would
-  exit before the caller consumed a single token, tearing down the sandbox while
-  the model was still using it.
-* ``_start_stream`` falls back to ``self.chat``, so a wrapper would **re-enter**
-  itself and provision a second sandbox.
-
-Lifetime is tied to the agent by ``weakref.finalize`` rather than a process-exit
-hook over a weak set. The weak set leaked: an agent and its ``SharedCompute``
-reference each other, so a dropped agent was reclaimed by the cycle collector,
-vanished from the set, and its sandbox was never shut down. Gateways clone an
-agent **per request**, so that was one orphaned container per request.
-"""
-
-from __future__ import annotations
-
-import logging
-import threading
-import weakref
-from typing import Any
-
-logger = logging.getLogger(__name__)
-
-# One lock per agent, so two unrelated agents never wait on each other and no
-# lock is ever held while another agent's provider is being imported. Held only
-# by ensure_tools_placed/close_tools_sandbox for that one agent.
-_AGENT_LOCKS: "weakref.WeakKeyDictionary" = weakref.WeakKeyDictionary()
-_LOCKS_GUARD = threading.Lock()
-
-
-def _lock_for(agent: Any) -> threading.Lock:
-    """The placement lock for ``agent``, created on demand.
-
-    ``_LOCKS_GUARD`` covers only this dictionary lookup -- microseconds -- never
-    provider construction or attachment. An earlier version held one global lock
-    across ``SharedCompute(...)``, which imports the provider SDK: unrelated
-    agents serialised behind each other, and a slow import could stall
-    interpreter exit.
-    """
-    with _LOCKS_GUARD:
-        lock = _AGENT_LOCKS.get(agent)
-        if lock is None:
-            lock = threading.Lock()
-            try:
-                _AGENT_LOCKS[agent] = lock
-            except TypeError:  # pragma: no cover - unhashable/non-weakrefable
-                pass
-        return lock
-
-
-def _shutdown_orphan(shared: Any, name: str) -> None:
-    """Tear down a sandbox whose agent is gone.
-
-    Registered with ``weakref.finalize``, so it runs when the agent is collected
-    *and* at interpreter exit. It must not close over the agent -- that would
-    keep it alive and defeat the whole point.
-    """
-    try:
-        shared.shutdown()
-        logger.debug("[tools_placement] released the sandbox belonging to %s", name)
-    except Exception as exc:  # pragma: no cover - teardown must stay quiet
-        # Loud enough to notice: a failed release means a container, or a
-        # billed cloud instance, is still running after the agent is gone.
-        logger.warning(
-            "[tools_placement] could not release the sandbox for %s: %s", name, exc
-        )
-
-
-def ensure_tools_placed(agent: Any) -> None:
-    """Attach the sandbox tools to ``agent`` if it asked for them. Idempotent.
-
-    Called at the top of every entry point, so it must be cheap when there is
-    nothing to do -- which is the overwhelmingly common case.
-    """
-    place = getattr(agent, "tools_run_on", None)
-    if place is None or getattr(agent, "_tools_sandbox", None) is not None:
-        return
-
-    from ..managed.shared_compute import SharedCompute
-
-    with _lock_for(agent):
-        # Re-check under the lock: two threads calling chat() at once must not
-        # each provision a sandbox and leak one.
-        if getattr(agent, "_tools_sandbox", None) is not None:
-            return
-
-        shared = SharedCompute(place)
-        # override_declared: this sandbox exists *because* the agent named a
-        # place, so the skip-if-declared rule must not skip the agent itself.
-        shared.attach([agent], override_declared=True)
-        agent._tools_sandbox = shared
-        agent._tools_sandbox_finalizer = weakref.finalize(
-            agent, _shutdown_orphan, shared, str(getattr(agent, "name", agent))
-        )
-
-    logger.info("[tools_placement] %r tools now run on %s", getattr(agent, "name", agent), place)
-
-
-def close_tools_sandbox(agent: Any) -> None:
-    """Tear down the agent's sandbox and put its original tools back."""
-    with _lock_for(agent):
-        # Everything happens under the lock. Clearing the marker first and
-        # shutting down afterwards left a window where a concurrent chat()
-        # re-attached and the in-flight shutdown then restored over it, leaving
-        # the agent marked as sandboxed while holding no sandbox tools -- a
-        # state ensure_tools_placed() could never repair, because its idempotent
-        # early return sees the marker and does nothing.
-        shared = getattr(agent, "_tools_sandbox", None)
-        if shared is None:
-            return
-        finalizer = getattr(agent, "_tools_sandbox_finalizer", None)
-        if finalizer is not None:
-            finalizer.detach()          # we are shutting down explicitly
-            agent._tools_sandbox_finalizer = None
-        shared.shutdown()
-        agent._tools_sandbox = None

src/praisonai-agents/praisonaiagents/agent/unified_execution_mixin.py

@@ -282,7 +282,7 @@ class UnifiedExecutionMixin:
                     task_id=task_id,
                     config=config,
                     tool_choice=tool_choice,
-                    parallel_tool_calls=getattr(getattr(self, "execution", None), "parallel_tool_calls", False)  # Gap 2 integration
+                    parallel_tool_calls=getattr(self, 'parallel_tool_calls', False)  # Gap 2 integration
                 )
             else:
                 # Standard LiteLLM path - delegate to existing LLM class
@@ -304,7 +304,7 @@ class UnifiedExecutionMixin:
                     task_id=task_id,
                     config=config,
                     tool_choice=tool_choice,
-                    parallel_tool_calls=getattr(getattr(self, "execution", None), "parallel_tool_calls", False)  # Gap 2 integration
+                    parallel_tool_calls=getattr(self, 'parallel_tool_calls', False)  # Gap 2 integration
                 )
             
             # Store response in memory if enabled

src/praisonai-agents/praisonaiagents/agent/video_agent.py

@@ -158,8 +158,9 @@ class VideoAgent:
             verbose: Verbosity level for output
             output: Output preset ("silent", "verbose", etc.)
         """
-        from ..utils.model_alias import resolve_model_name
-        llm = resolve_model_name(llm, model, "VideoAgent")
+        # Handle model= alias for llm=
+        if llm is None and model is not None:
+            llm = model
         
         # Store core identity
         self.name = name or "VideoAgent"

src/praisonai-agents/praisonaiagents/agent/vision_agent.py

@@ -112,8 +112,8 @@ class VisionAgent:
                 - VisionConfig: Full configuration object
             verbose: Verbosity level for output
         """
-        from ..utils.model_alias import resolve_model_name
-        llm = resolve_model_name(llm, model, "VisionAgent")
+        if llm is None and model is not None:
+            llm = model
         
         self.name = name or "VisionAgent"
         self.instructions = instructions

src/praisonai-agents/praisonaiagents/agents/agents.py

@@ -2,8 +2,6 @@ import os
 import time
 import json
 import logging
-import contextlib
-import contextvars
 import threading
 from praisonaiagents._logging import get_logger
 from typing import Any, Dict, Optional, List, Tuple, Callable
@@ -43,13 +41,18 @@ class TaskStatus(Enum):
 logger = get_logger(__name__)
 
 
-# Request authorisation + fail-closed bind guard are shared with Agent.launch
-# so the single-agent and multi-agent serving paths cannot drift apart.
-from ..agent.launch_security import (
-    launch_auth_token as _launch_auth_token,
-    authorise_launch_request as _authorise_launch_request,
-    resolve_launch_host as _resolve_launch_host,
-)
+def _launch_auth_token() -> Optional[str]:
+    return os.environ.get("PRAISONAI_LAUNCH_AUTH_TOKEN")
+
+
+def _authorise_launch_request(request) -> bool:
+    token = _launch_auth_token()
+    if not token:
+        return True
+    auth = request.headers.get("Authorization", "")
+    if auth.startswith("Bearer ") and auth[7:] == token:
+        return True
+    return request.headers.get("X-Auth-Token") == token
 
 
 # Agent server registry for thread-safe server management
@@ -372,18 +375,6 @@ def _build_execution_context(agents_instance, task_id, skip_memory_init=False):
     if llm and hasattr(llm, 'set_current_agent'):
         llm.set_current_agent(executor_agent.display_name)
 
-    # Place the agent's tools BEFORE snapshotting them. This snapshot is passed
-    # to chat() as an explicit `tools=`, which wins over `agent.tools` -- so if
-    # the sandbox attaches later (inside chat()), the model is handed the
-    # pre-attach list and every tool runs on the host while a sandbox sits
-    # provisioned and unused. Silent, and worse than it sounds: in
-    # start_for_each() row 1 got local tools and row 2 got the bridged set,
-    # because row 1's chat() mutated agent.tools in time for row 2's snapshot.
-    if executor_agent is not None and getattr(executor_agent, "tools_run_on", None) is not None:
-        from ..agent.tools_placement import ensure_tools_placed
-
-        ensure_tools_placed(executor_agent)
-
     # Ensure tools are available from both task and agent (create copy to avoid mutation)
     tools = list(task.tools or [])
     if executor_agent and executor_agent.tools:
@@ -653,8 +644,7 @@ class AgentTeam(SpawnAnnounceProtocol):
         manager_llm=None,
         name: Optional[str] = None,
         variables: Optional[Dict[str, Any]] = None,
-        llm: Optional[str] = None,  # Deprecated alias for model=
-        model: Optional[str] = None,  # Default model for members that did not name one
+        llm: Optional[str] = None,  # Default LLM for all agents (API consistency)
         # Consolidated feature params (agent-centric API)
         memory: Optional[Any] = False,  # Union[bool, MultiAgentMemoryConfig]
         planning: Optional[Any] = False,  # Union[bool, MultiAgentPlanningConfig]
@@ -670,15 +660,13 @@ class AgentTeam(SpawnAnnounceProtocol):
         reflection: Optional[Any] = None,  # Union[bool, ReflectionConfig] - self-reflection
         caching: Optional[Any] = None,  # Union[bool, CachingConfig] - caching
         learn: Optional[Any] = None,  # Union[bool, LearnConfig] - continuous learning
-        # Union[str, ComputeProviderProtocol] - where every agent's shell/file
-        # tools run: "docker", "e2b", "modal", "daytona", "flyio", "tenki",
-        # "local", "subprocess", "sandlock", "ssh", "novita". The team shares
-        # ONE sandbox and one working directory, so files written by one agent
-        # are visible to the others. Orchestration and thinking stay local.
-        # Pass a configured provider instance to customise resources.
-        tools_run_on: Optional[Any] = None,
-        # Accepted only to fail with a useful message -- see resolve_placement.
-        run_on: Optional[Any] = None,
+        # Union[str, ComputeProviderProtocol] - run every agent's shell/file
+        # tools in ONE shared remote sandbox ("docker", "e2b", "modal",
+        # "daytona", "flyio", "tenki", "local"). Agents share /workspace, so
+        # files written by one agent are visible to the others. Orchestration
+        # stays local. Pass a configured provider instance instead of a name to
+        # customise image/resources.
+        compute: Optional[Any] = None,
     ):
         """
         Initialize AgentManager with consolidated feature parameters.
@@ -689,11 +677,8 @@ class AgentTeam(SpawnAnnounceProtocol):
             process: Execution process type ("sequential", "workflow", "hierarchical").
                 For parallel fan-out, set async_execution=True on individual Task
                 objects within a "workflow" or "sequential" process.
-            manager_llm: Model for the hierarchical manager agent. Unrelated to
-                model=/llm=; it never touches the members.
-            llm: Deprecated alias for model=. Passing both raises TypeError.
-            model: Default model for members that did not name one themselves.
-                An agent constructed with its own llm=/model=/auth= keeps it.
+            manager_llm: LLM model for manager agent
+            llm: Default LLM model for all agents
             name: Name for this agent collection
             variables: Global variables for substitution
             memory: Memory configuration (bool | MultiAgentMemoryConfig)
@@ -711,40 +696,13 @@ class AgentTeam(SpawnAnnounceProtocol):
         """
         # Store new params for propagation to agents
         self._learn = learn
-        # model= is the canonical name; llm= is the deprecated alias. Passing
-        # both is refused rather than silently resolved (see resolve_model_alias).
-        # The resolved value is the default model for the members: applied to
-        # every agent that never named a model of its own; an agent that did
-        # keeps it. Same rule AgentFlow uses for the agents it builds.
-        # Must UNWRAP, not just alias-resolve: this value is pushed into every
-        # member via _apply_default_llm, and a member holding an LLMConfig fails
-        # inside chat() with "'LLMConfig' object has no attribute 'lower'".
-        from ..utils.model_alias import resolve_model_name
-        self.llm = resolve_model_name(llm, model, type(self).__name__)
-        if self.llm:
-            for _member in (agents.values() if isinstance(agents, dict) else (agents or [])):
-                _apply = getattr(_member, "_apply_default_llm", None)
-                if callable(_apply):
-                    _apply(self.llm)
+        self.llm = llm  # Store default LLM for API consistency
         self._autonomy = autonomy
         self._knowledge = knowledge
         self._guardrails = guardrails
         self._web = web
         self._reflection = reflection
         self._caching = caching
-        # Warn about params that are accepted for API symmetry with Agent but are
-        # not yet applied at the team level, so a truthy value stops being a silent
-        # no-op. Pass these to individual Agent(...) instances instead.
-        _unwired = {
-            "guardrails": guardrails, "web": web, "reflection": reflection,
-            "caching": caching, "learn": learn, "knowledge": knowledge,
-        }
-        _set = [k for k, v in _unwired.items() if v]
-        if _set:
-            logging.warning(
-                f"AgentTeam received {_set} but does not yet apply them at the team "
-                "level; pass these to individual Agent(...) instances instead."
-            )
         # ─────────────────────────────────────────────────────────────────────
         # Extract values from consolidated params using UNIFIED CANONICAL resolver
         # Precedence: Instance > Config > Dict > Array > String > Bool > Default
@@ -940,19 +898,7 @@ class AgentTeam(SpawnAnnounceProtocol):
         self.stream = _stream
         self.name = name
         # Remote execution: one shared sandbox for every agent on this team.
-        from ..agent.placement import resolve_placement
-
-        resolve_placement(
-            "AgentTeam", run_on=run_on, tools_run_on=tools_run_on,
-            supports_run_on=False,
-        )
-        self.tools_run_on = tools_run_on
-        # Kept readable rather than removed. `team.run_on` used to exist, and
-        # code doing getattr(team, "run_on", None) for introspection or
-        # serialisation would otherwise start raising AttributeError. None is
-        # the honest value: a team orchestrates locally, so nothing about it
-        # runs wholly on a managed runtime.
-        self.run_on = None
+        self.compute = compute
 
         # Callbacks for workflow execution
         self.on_task_start = _on_task_start
@@ -1479,73 +1425,6 @@ class AgentTeam(SpawnAnnounceProtocol):
                 raise result
         return results
 
-    def _depends_on_pending(self, task, pending):
-        """True if ``task`` depends on a task still pending in the batch.
-
-        ``pending`` is a list of ``(task_id, coroutine)`` pairs already queued
-        for parallel execution. If one of the task's dependencies is in that
-        set, its result isn't available yet, so the batch must be flushed before
-        queuing this task (otherwise the dependent builds its prompt from an
-        empty result for the still-in-progress dependency).
-
-        Two dependency edges are checked, since ``_build_task_context`` reads
-        from both:
-          - ``task.context``: explicit context tasks (by object ``id``).
-          - ``task.previous_tasks``: workflow ``next_tasks`` edges, stored as
-            task *names*; without this a workflow successor could be queued in
-            the same async batch as its predecessor and read an empty result.
-        """
-        if not pending:
-            return False
-        pending_ids = {tid for tid, _ in pending}
-
-        deps = getattr(task, 'context', None) or []
-        if any(getattr(dep, 'id', None) in pending_ids for dep in deps):
-            return True
-
-        previous = getattr(task, 'previous_tasks', None) or []
-        if previous:
-            pending_names = {
-                self.tasks[tid].name
-                for tid in pending_ids
-                if tid in self.tasks
-            }
-            if any(name in pending_names for name in previous):
-                return True
-
-        return False
-
-    def _deps_failed(self, task_id):
-        """True if any dependency of ``task_id`` finished in a failed state.
-
-        asequential()/aworkflow() run their own failure check inside the
-        generator, but async tasks are buffered and drained later, so an
-        upstream async task may not have failed yet when the generator yielded
-        the dependent. Re-checking here — after pending async tasks are flushed
-        — makes the failure cascade fire for the async_execution path too, for
-        both dependency edges ``_build_task_context`` reads (context tasks and
-        workflow ``previous_tasks``).
-        """
-        task = self.tasks.get(task_id)
-        if task is None:
-            return False
-
-        for dep in getattr(task, 'context', None) or []:
-            dep_id = getattr(dep, 'id', None)
-            if dep_id in self.tasks and self.tasks[dep_id].status == "failed":
-                return True
-
-        previous = getattr(task, 'previous_tasks', None) or []
-        if previous:
-            by_name = {t.name: t for t in self.tasks.values()}
-            if any(
-                name in by_name and by_name[name].status == "failed"
-                for name in previous
-            ):
-                return True
-
-        return False
-
     async def arun_all_tasks(self):
         """Async version of run_all_tasks method"""
         process = Process(
@@ -1557,26 +1436,14 @@ class AgentTeam(SpawnAnnounceProtocol):
         )
         
         if self.process == "workflow":
-            tasks_to_run = []  # list of (task_id, coroutine)
+            tasks_to_run = []
             async for task_id in process.aworkflow():
-                task = self.tasks[task_id]
-                if task.async_execution:
-                    # If this async task depends on another async task still
-                    # pending in the current batch, flush first so its context
-                    # is available before this one reads it.
-                    if self._depends_on_pending(task, tasks_to_run):
-                        await self._gather_with_isolation([c for _, c in tasks_to_run])
-                        tasks_to_run = []
-                        # A just-flushed prerequisite may now be failed; don't
-                        # queue a dependent that would run with missing context.
-                        if self._deps_failed(task_id):
-                            self.tasks[task_id].status = "failed"
-                            continue
-                    tasks_to_run.append((task_id, self.arun_task(task_id)))
+                if self.tasks[task_id].async_execution:
+                    tasks_to_run.append(self.arun_task(task_id))
                 else:
                     # If we encounter a sync task, we must wait for the previous async tasks to finish.
                     if tasks_to_run:
-                        await self._gather_with_isolation([c for _, c in tasks_to_run])
+                        await self._gather_with_isolation(tasks_to_run)
                         tasks_to_run = []
                     
                     # Run sync task in an executor to avoid blocking the event loop
@@ -1586,42 +1453,25 @@ class AgentTeam(SpawnAnnounceProtocol):
                     await loop.run_in_executor(None, copy_context_to_callable(lambda tid=task_id: self.run_task(tid)))
 
             if tasks_to_run:
-                await self._gather_with_isolation([c for _, c in tasks_to_run])
+                await self._gather_with_isolation(tasks_to_run)
                 
         elif self.process == "sequential":
-            async_tasks_to_run = []  # list of (task_id, coroutine)
+            async_tasks_to_run = []
             
             async def flush_async_tasks():
                 """Execute all pending async tasks"""
                 nonlocal async_tasks_to_run
                 if async_tasks_to_run:
-                    await self._gather_with_isolation([c for _, c in async_tasks_to_run])
+                    await self._gather_with_isolation(async_tasks_to_run)
                     async_tasks_to_run = []
-
+            
             async for task_id in process.asequential():
-                task = self.tasks[task_id]
-                if task.async_execution:
-                    # If this async task depends on another async task still
-                    # pending in the current batch, flush first so its context
-                    # is available before this one reads it (avoids a same-batch
-                    # race that silently substitutes empty dependency context).
-                    if self._depends_on_pending(task, async_tasks_to_run):
-                        await flush_async_tasks()
-                        # A just-flushed prerequisite may now be failed; don't
-                        # queue a dependent that would run with missing context.
-                        if self._deps_failed(task_id):
-                            self.tasks[task_id].status = "failed"
-                            continue
+                if self.tasks[task_id].async_execution:
                     # Collect async tasks to run in parallel
-                    async_tasks_to_run.append((task_id, self.arun_task(task_id)))
+                    async_tasks_to_run.append(self.arun_task(task_id))
                 else:
                     # Before running a sync task, execute all pending async tasks
                     await flush_async_tasks()
-                    # A just-flushed async prerequisite may now be failed; skip
-                    # the dependent so we don't run it with missing upstream context.
-                    if self._deps_failed(task_id):
-                        self.tasks[task_id].status = "failed"
-                        continue
                     # Run sync task in an executor to avoid blocking the event loop
                     # Use copy_context_to_callable to propagate contextvars (needed for trace emission)
                     from ..trace.context_events import copy_context_to_callable
@@ -1659,62 +1509,6 @@ class AgentTeam(SpawnAnnounceProtocol):
             except StopAsyncIteration:
                 pass
 
-
-    # ── shared sandbox lifetime ──────────────────────────────────────────────
-    # A ContextVar, not an instance attribute: the previous version set
-    # `self.run_on = None` for the duration of the run, so a second caller
-    # inspecting the team mid-run saw "no sandbox" and any concurrent start()
-    # executed every tool on the host. Depth lives with the caller, not on the
-    # shared object, so the team's declared placement is always readable.
-    #
-    # The depth is keyed PER TEAM, not shared class-wide. A single integer here
-    # meant any team started while another team's run was on the stack saw
-    # depth==1 and skipped its own sandbox entirely -- so a nested team ran on
-    # the host, and a team sharing an agent with the outer run executed on the
-    # OUTER team's sandbox.
-    #
-    # ContextVar, not threading.local: two coroutines that `astart()` the SAME
-    # team under one asyncio.gather run on one thread, so thread-local state is
-    # shared between them -- the second saw the first's depth==1, skipped its
-    # own sandbox, and ran against a sandbox the first could tear down mid-flight.
-    # A ContextVar is copied per task at gather/create_task time, so each run
-    # gets its own depth map; it is also per-thread, so sync callers stay
-    # isolated too. The value is an immutable frozen mapping replaced via .set()
-    # (never mutated in place), because a copied context shares the *reference*
-    # to a mutable dict and in-place mutation would leak straight back across
-    # the tasks the copy was meant to separate.
-    _tools_scope_depths: "contextvars.ContextVar" = contextvars.ContextVar(
-        "praisonai_tools_scope_depths", default=()
-    )
-
-    def _needs_tools_scope(self) -> bool:
-        """True when this call should provision the team's shared sandbox."""
-        if getattr(self, "tools_run_on", None) is None:
-            return False
-        return dict(self._tools_scope_depths.get()).get(id(self), 0) == 0
-
-    @contextlib.contextmanager
-    def _shared_tools_scope(self):
-        """Hold one sandbox for everything nested inside.
-
-        Re-entrant by design: ``start_for_each`` opens the scope once for the
-        whole batch, so the ``start()`` call it makes per input row finds the
-        scope already open and reuses that sandbox instead of provisioning and
-        destroying one per row.
-        """
-        from ..managed.shared_compute import SharedCompute
-
-        key = id(self)
-        depths = dict(self._tools_scope_depths.get())
-        depths[key] = depths.get(key, 0) + 1
-        token = self._tools_scope_depths.set(tuple(sorted(depths.items())))
-        try:
-            with SharedCompute(self.tools_run_on) as shared:
-                shared.attach(list(self.agents or []))
-                yield shared
-        finally:
-            self._tools_scope_depths.reset(token)
-
     async def astart(self, content=None, return_dict=False, **kwargs):
         """Async version of start method.
         
@@ -1723,12 +1517,6 @@ class AgentTeam(SpawnAnnounceProtocol):
             return_dict: If True, returns the full results dictionary instead of only the final response
             **kwargs: Additional arguments
         """
-        # Same shared sandbox as start(). Without this, an async team with
-        # tools_run_on= ran every tool on the host and said nothing.
-        if self._needs_tools_scope():
-            with self._shared_tools_scope():
-                return await self.astart(content=content, return_dict=return_dict, **kwargs)
-
         # Track execution via telemetry
         if hasattr(self, '_telemetry') and self._telemetry:
             self._telemetry.track_agent_execution(self.name, success=True, async_mode=True)
@@ -1949,21 +1737,6 @@ class AgentTeam(SpawnAnnounceProtocol):
             return str(agent[0])
         return None
 
-    def __repr__(self):
-        """Show where this team's work happens, not just its name."""
-        from ..agent.execution_location import repr_fields
-
-        return (
-            f"AgentTeam(name={self.name!r}, agents={len(self.agents or [])}, "
-            f"{repr_fields(self, shared=True)})"
-        )
-
-    def where_does_it_run(self) -> str:
-        """Plain-English answer to "where does my code actually run?"."""
-        from ..agent.execution_location import explain
-
-        return explain(self, shared=True)
-
     def start(self, content=None, return_dict=False, output=None, **kwargs):
         """Start agent execution with verbose output (beginner-friendly).
         
@@ -1989,11 +1762,19 @@ class AgentTeam(SpawnAnnounceProtocol):
             ```
         """
         # Remote execution: provision ONE sandbox shared by every agent on the
-        # team, and tear it down even if execution raises.
-        if self._needs_tools_scope():
-            with self._shared_tools_scope():
-                return self.start(content=content, return_dict=return_dict,
-                                  output=output, **kwargs)
+        # team, and tear it down even if execution raises. Re-enters start()
+        # with compute cleared so the wrapper applies exactly once.
+        if getattr(self, "compute", None) is not None:
+            from ..managed.shared_compute import SharedCompute
+
+            compute, self.compute = self.compute, None
+            try:
+                with SharedCompute(compute) as shared:
+                    shared.attach(list(self.agents or []))
+                    return self.start(content=content, return_dict=return_dict,
+                                      output=output, **kwargs)
+            finally:
+                self.compute = compute
 
         # Track execution via telemetry
         if hasattr(self, '_telemetry') and self._telemetry:
@@ -2309,15 +2090,6 @@ class AgentTeam(SpawnAnnounceProtocol):
         if on_error not in ("continue", "fail_fast"):
             raise ValueError("on_error must be 'continue' or 'fail_fast'")
 
-        # One sandbox for the whole batch. Without this the per-row start()
-        # call provisions and destroys its own, so a 50-row batch paid for 50
-        # sandboxes and no row could see what an earlier row wrote.
-        if self._needs_tools_scope():
-            with self._shared_tools_scope():
-                return self.start_for_each(
-                    inputs, on_error=on_error, output=output, **kwargs
-                )
-
         batch_id = f"batch_{uuid.uuid4().hex[:12]}"
         saved_variables = self.variables
         task_snapshot = self._snapshot_task_state()
@@ -2354,13 +2126,6 @@ class AgentTeam(SpawnAnnounceProtocol):
         if on_error not in ("continue", "fail_fast"):
             raise ValueError("on_error must be 'continue' or 'fail_fast'")
 
-        # One sandbox for the whole batch -- see start_for_each.
-        if self._needs_tools_scope():
-            with self._shared_tools_scope():
-                return await self.astart_for_each(
-                    inputs, on_error=on_error, **kwargs
-                )
-
         batch_id = f"batch_{uuid.uuid4().hex[:12]}"
         saved_variables = self.variables
         task_snapshot = self._snapshot_task_state()
@@ -2642,7 +2407,7 @@ class AgentTeam(SpawnAnnounceProtocol):
         
         print("="*50 + "\n")
         
-    def launch(self, path: str = '/agents', port: int = 8000, host: str = '127.0.0.1', debug: bool = False, protocol: str = "http"):
+    def launch(self, path: str = '/agents', port: int = 8000, host: str = '0.0.0.0', debug: bool = False, protocol: str = "http"):
         """
         Launch all agents as a single API endpoint (HTTP) or an MCP server. 
         In HTTP mode, the endpoint accepts a query and processes it through all agents in sequence.
@@ -2653,11 +2418,7 @@ class AgentTeam(SpawnAnnounceProtocol):
         Args:
             path: API endpoint path (default: '/agents') for HTTP. Ignored in MCP mode.
             port: Server port (default: 8000)
-            host: Server host (default: '127.0.0.1'; changed from '0.0.0.0' to
-                avoid binding all interfaces by default — pass '0.0.0.0'
-                explicitly to expose externally). Binding a non-loopback host
-                without ``PRAISONAI_LAUNCH_AUTH_TOKEN`` set auto-generates and
-                prints a one-time bearer token.
+            host: Server host (default: '0.0.0.0')
             debug: Enable debug mode for uvicorn (default: False)
             protocol: "http" to launch as FastAPI, "mcp" to serve over MCP via
                 ``praisonai-mcp`` (install with ``pip install praisonai-mcp``).
@@ -2667,7 +2428,7 @@ class AgentTeam(SpawnAnnounceProtocol):
         """
         if protocol == "http":
             # Use centralized server registry
-
+            
             if not self.agents:
                 logging.warning("No agents to launch for HTTP mode. Add agents to the Agents instance first.")
                 return
@@ -2696,13 +2457,6 @@ class AgentTeam(SpawnAnnounceProtocol):
                 print("\nOr install all API dependencies with:")
                 print("pip install 'praisonaiagents[api]'")
                 return None
-
-            # Fail-closed bind guard shared with Agent.launch: never serve
-            # keyless on a non-loopback host. Applied only after the no-agents
-            # and dependency guards above, so a launch that bails out cannot
-            # mutate the process-wide launch token (which every route reads per
-            # request) and retroactively 401 an already-running endpoint.
-            host = _resolve_launch_host(host)
             
             # Thread-safe initialization of FastAPI app
             app, is_new = _server_registry.get_or_create_app(
@@ -3341,14 +3095,9 @@ class AgentTeam(SpawnAnnounceProtocol):
         console.print(f"[dim]Progress: [{'█' * 30}] 100%[/dim]")
         console.print(f"[green]Completed {completed_count}/{len(self.tasks)} tasks![/green]\n")
         
-        # Keep plan-step tasks/results under _plan_tasks for introspection,
-        # then restore the user's original task set as the canonical self.tasks.
-        self._plan_tasks = self.tasks
-        self.tasks = original_tasks
-        with self._task_id_lock:
-            self.task_id_counter = (
-                max(original_tasks.keys()) + 1 if original_tasks else 0
-            )
+        # Restore original tasks reference for result retrieval
+        self._plan_tasks = self.tasks.copy()
+        # Keep plan tasks for results but note original tasks are preserved in _plan_tasks
 
     # Resource Lifecycle Management
     def close(self) -> None:

src/praisonai-agents/praisonaiagents/approval/backends.py

@@ -81,14 +81,12 @@ class ConsoleBackend:
     """Interactive Rich terminal prompt.  Default for CLI usage."""
 
     def _prompt_user(self, request: ApprovalRequest):
-        """Show Rich panel and ask once/session/always/no/deny-with-guidance.
+        """Show Rich panel and ask once/session/always/no.
 
-        Returns a ``(approved, scope, scope_pattern, feedback)`` tuple where
-        ``scope`` is one of ``"once"`` / ``"session"`` / ``"always"`` and
-        ``scope_pattern`` is the reusable target to persist for ``always``
-        (``None`` otherwise). ``feedback`` carries optional free-text guidance
-        captured by the "deny & redirect" choice (``None`` otherwise).
-        A plain denial returns ``(False, "once", None, None)``.
+        Returns a ``(approved, scope, scope_pattern)`` tuple where ``scope`` is
+        one of ``"once"`` / ``"session"`` / ``"always"`` and ``scope_pattern``
+        is the reusable target to persist for ``always`` (``None`` otherwise).
+        A denial returns ``(False, "once", None)``.
         """
         Console = _get_rich_console()
         Panel = _get_rich_panel()
@@ -128,35 +126,28 @@ class ConsoleBackend:
         try:
             console.print(
                 f"[{risk_color}]Allow {request.tool_name}?[/{risk_color}]  "
-                f"[o] once   [s] this session   [a] {always_label}   "
-                f"[n] no   [d] deny & redirect"
+                f"[o] once   [s] this session   [a] {always_label}   [n] no"
             )
             choice = Prompt.ask(
                 "Choice",
-                choices=["o", "s", "a", "n", "d"],
+                choices=["o", "s", "a", "n"],
                 default="n",
             )
         except (KeyboardInterrupt, EOFError):
-            return (False, "once", None, None)
+            return (False, "once", None)
 
         if choice == "n":
-            return (False, "once", None, None)
-        if choice == "d":
-            try:
-                feedback = Prompt.ask("What should the agent do instead?").strip()
-            except (KeyboardInterrupt, EOFError):
-                feedback = ""
-            return (False, "once", None, feedback or None)
+            return (False, "once", None)
         if choice == "s":
-            return (True, "session", None, None)
+            return (True, "session", None)
         if choice == "a":
-            return (True, "always", suggested or None, None)
-        return (True, "once", None, None)
+            return (True, "always", suggested or None)
+        return (True, "once", None)
 
     def request_approval_sync(self, request: ApprovalRequest) -> ApprovalDecision:
         """Synchronous approval via Rich console prompt."""
         try:
-            approved, scope, scope_pattern, feedback = self._prompt_user(request)
+            approved, scope, scope_pattern = self._prompt_user(request)
             if approved:
                 return ApprovalDecision(
                     approved=True,
@@ -165,13 +156,7 @@ class ConsoleBackend:
                     scope=scope,
                     scope_pattern=scope_pattern,
                 )
-            reason = f"User denied: {feedback}" if feedback else "User denied"
-            return ApprovalDecision(
-                approved=False,
-                reason=reason,
-                approver="console",
-                feedback=feedback,
-            )
+            return ApprovalDecision(approved=False, reason="User denied", approver="console")
         except Exception as e:
             logger.error("Console approval error: %s", e)
             return ApprovalDecision(approved=False, reason=f"Approval error: {e}")

src/praisonai-agents/praisonaiagents/approval/protocols.py

@@ -65,12 +65,6 @@ class ApprovalDecision:
                        ``session``/``always`` scopes (e.g. ``"bash:git status *"``
                        or ``"edit:src/app.py"``). When ``None`` the registry
                        derives one from the tool call.
-        feedback:      Optional free-text guidance supplied by the user when
-                       denying a tool call ("deny with guidance"). When present
-                       on a denial it is surfaced back to the model as a
-                       course-correction for the next turn instead of a bare
-                       "denied" result. ``None`` (default) keeps today's
-                       terminal-deny semantics.
     """
 
     approved: bool
@@ -80,7 +74,6 @@ class ApprovalDecision:
     metadata: Dict[str, Any] = field(default_factory=dict)
     scope: str = "once"
     scope_pattern: Optional[str] = None
-    feedback: Optional[str] = None
 
 
 @dataclass

src/praisonai-agents/praisonaiagents/auth/__init__.py

@@ -2,10 +2,7 @@
 Authentication & Authorization Protocols for PraisonAI Agents.
 
 This package provides protocol-driven auth interfaces for the core SDK.
-Implementations (JWT, OAuth, etc.) live outside it — implement the protocols
-against your own store, or use the reference implementation in the separate
-``praisonai-platform`` package
-(https://github.com/MervinPraison/PraisonAI-Platform).
+Implementations (JWT, OAuth, etc.) live in the platform package.
 
 Quick start::
 

src/praisonai-agents/praisonaiagents/auth/protocols.py

@@ -155,16 +155,11 @@ class WorkspaceContextProtocol(Protocol):
     """Protocol for providing workspace context to agents.
 
     Enables agents to access workspace-specific settings, instructions,
-    and agent configurations from a platform layer.
-
-    Implementations live outside this package. The reference one is
-    ``PlatformWorkspaceContext`` in the ``praisonai-platform`` package
-    (https://github.com/MervinPraison/PraisonAI-Platform); implement this
-    protocol yourself to back agent configuration with your own store.
+    and agent configurations from the platform layer.
 
     Example::
 
-        class MyWorkspaceContext:
+        class PlatformWorkspaceContext:
             async def get_workspace_context(self, workspace_id):
                 ws = await db.get_workspace(workspace_id)
                 return ws.context

src/praisonai-agents/praisonaiagents/bots/protocols.py

@@ -109,11 +109,6 @@ class PlatformCapabilities:
             descriptor only; the durable outbox does not forward a token on
             resend, so adapters relying on provider-side dedupe should also set
             ``reconciles_unknown_send`` to get effectively-once delivery.
-        supports_threads: Whether the adapter can open a new thread/topic under
-            a chat (e.g. Telegram forum topics, Discord threads, Slack thread
-            anchoring). When False, ``create_thread`` returns a typed
-            ``unsupported`` outcome and callers fall back to the parent channel
-            rather than raising.
     """
     
     max_message_length: int = 4096
@@ -131,7 +126,6 @@ class PlatformCapabilities:
     reconciles_unknown_send: bool = False
     supports_idempotency_token: bool = False
     supports_media: bool = False
-    supports_threads: bool = False
     
     def to_dict(self) -> Dict[str, Any]:
         """Convert to dictionary."""
@@ -151,7 +145,6 @@ class PlatformCapabilities:
             "reconciles_unknown_send": self.reconciles_unknown_send,
             "supports_idempotency_token": self.supports_idempotency_token,
             "supports_media": self.supports_media,
-            "supports_threads": self.supports_threads,
         }
     
     @classmethod
@@ -173,7 +166,6 @@ class PlatformCapabilities:
             reconciles_unknown_send=data.get("reconciles_unknown_send", False),
             supports_idempotency_token=data.get("supports_idempotency_token", False),
             supports_media=data.get("supports_media", False),
-            supports_threads=data.get("supports_threads", False),
         )
 
 

src/praisonai-agents/praisonaiagents/bus/__init__.py

@@ -32,8 +32,6 @@ Usage:
     bus.publish("session.created", {"session_id": "abc123"})
 """
 
-from .._lazy import create_lazy_getattr
-
 __all__ = [
     "EventBus",
     "Event",
@@ -43,13 +41,31 @@ __all__ = [
     "set_default_bus",
 ]
 
-_LAZY_IMPORTS = {
-    "EventBus": ("praisonaiagents.bus.bus", "EventBus"),
-    "Event": ("praisonaiagents.bus.event", "Event"),
-    "EventType": ("praisonaiagents.bus.event", "EventType"),
-    "Subscriber": ("praisonaiagents.bus.bus", "Subscriber"),
-    "get_default_bus": ("praisonaiagents.bus.bus", "get_default_bus"),
-    "set_default_bus": ("praisonaiagents.bus.bus", "set_default_bus"),
-}
 
-__getattr__ = create_lazy_getattr(_LAZY_IMPORTS, __name__)
+def __getattr__(name: str):
+    """Lazy load module components."""
+    if name == "EventBus":
+        from .bus import EventBus
+        return EventBus
+    
+    if name == "Event":
+        from .event import Event
+        return Event
+    
+    if name == "EventType":
+        from .event import EventType
+        return EventType
+    
+    if name == "Subscriber":
+        from .bus import Subscriber
+        return Subscriber
+    
+    if name == "get_default_bus":
+        from .bus import get_default_bus
+        return get_default_bus
+    
+    if name == "set_default_bus":
+        from .bus import set_default_bus
+        return set_default_bus
+    
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")

src/praisonai-agents/praisonaiagents/compaction/__init__.py

@@ -37,8 +37,6 @@ __all__ = [
     "ToolResultPrunerProtocol",
     "MessageFormatterProtocol", 
     "SummaryBuilderProtocol",
-    # Default structured summary builder
-    "DefaultSummaryBuilder",
     # Read-only recap
     "build_recap",
     "MemoryFlushResult",
@@ -77,10 +75,6 @@ def __getattr__(name: str):
         from .protocols import SummaryBuilderProtocol
         return SummaryBuilderProtocol
     
-    if name == "DefaultSummaryBuilder":
-        from .summary_builder import DefaultSummaryBuilder
-        return DefaultSummaryBuilder
-
     if name == "build_recap":
         from .recap import build_recap
         return build_recap

src/praisonai-agents/praisonaiagents/compaction/compactor.py

@@ -122,18 +122,7 @@ class ContextCompactor:
         
         # Protocol implementations (defaults to None - no heavy implementations in core)
         self.tool_pruner = tool_pruner
-        self.message_formatter = message_formatter
-        # Default the structured summary builder when the config asks for the
-        # phase-aware template but no builder was injected, so
-        # `_build_structured_summary` renders SUMMARY_TEMPLATE instead of the
-        # "Summary of N messages" stub. The builder is deterministic and
-        # dependency-free, so this stays offline-safe and zero-overhead.
-        if summary_builder is None and getattr(self.config, "structured_template", False):
-            from .summary_builder import DefaultSummaryBuilder
-
-            summary_builder = DefaultSummaryBuilder(
-                llm_summarize_fn=self.llm_summarize_fn
-            )
+        self.message_formatter = message_formatter  
         self.summary_builder = summary_builder
         
         # Anti-thrashing state tracking

src/praisonai-agents/praisonaiagents/compaction/summary_builder.py

@@ -1,172 +0,0 @@
-"""Default structured summary builder for context compaction.
-
-This is the concrete :class:`~praisonaiagents.compaction.protocols.
-SummaryBuilderProtocol` implementation that renders the declared
-:data:`~praisonaiagents.compaction.config.SUMMARY_TEMPLATE` — the phase-aware
-sections (``## Active Task`` / ``## Completed Actions`` / ``## In Progress`` /
-``## Pending Questions`` / ``## Relevant Files / Paths`` / ``## Remaining
-Work``) — so a compacted context keeps its structure instead of degrading to a
-one-line ``"Summary of N messages"`` count.
-
-Design: **deterministic, dependency-free, offline-safe.** It categorises the
-transcript into the template sections from the messages themselves (roles,
-tool calls, question marks, file-path tokens) rather than making an LLM call, so
-it never blocks the hot compaction path, never adds a runtime dependency, and
-never raises into the loop. File paths and identifiers are preserved verbatim.
-
-When an optional ``llm_summarize_fn`` is supplied the builder still renders the
-same template shape; on any failure it falls back to the deterministic render,
-honouring the issue's "fall back to the plain summary on failure" rule.
-"""
-
-from __future__ import annotations
-
-import re
-from typing import Any, Dict, List, Optional
-
-from .config import SUMMARY_TEMPLATE
-
-# Match file/path-like tokens so they can be surfaced verbatim in the
-# "Relevant Files / Paths" section (absolute/relative paths and dotted module
-# names with a recognisable extension).
-_PATH_RE = re.compile(
-    r"(?:/[^\s'\"`]+|(?:[\w.-]+/)+[\w.-]+|[\w./-]+\.[A-Za-z0-9]{1,6})"
-)
-
-_MAX_ITEMS = 12
-_MAX_LINE = 200
-
-
-def _text(content: Any) -> str:
-    """Best-effort flatten of a message ``content`` field into a string."""
-    if isinstance(content, str):
-        return content
-    if isinstance(content, list):
-        parts: List[str] = []
-        for part in content:
-            if isinstance(part, dict):
-                parts.append(str(part.get("text", "")))
-            else:
-                parts.append(str(part))
-        return " ".join(p for p in parts if p)
-    return ""
-
-
-def _clip(text: str, limit: int = _MAX_LINE) -> str:
-    text = text.strip().replace("\n", " ")
-    return text if len(text) <= limit else text[: limit - 1].rstrip() + "…"
-
-
-class DefaultSummaryBuilder:
-    """Deterministic :class:`SummaryBuilderProtocol` renderer for the template.
-
-    Args:
-        llm_summarize_fn: Optional callable ``(prompt: str) -> str`` used to
-            distil section bodies. Any failure falls back to the deterministic
-            render, so callers get a valid structured summary regardless.
-    """
-
-    def __init__(self, llm_summarize_fn: Optional[Any] = None) -> None:
-        self._llm_summarize_fn = llm_summarize_fn
-
-    # -- protocol ----------------------------------------------------------
-
-    def build_structured_summary(self, messages: List[Dict[str, Any]]) -> str:
-        """Render :data:`SUMMARY_TEMPLATE` from ``messages`` deterministically.
-
-        Never raises: on any failure returns the plain one-line summary so the
-        compaction loop keeps a valid summary string (issue fallback rule).
-        """
-        try:
-            return self._render(messages)
-        except Exception:  # noqa: BLE001 - summarisation must never crash the loop
-            return f"Summary of {len(messages)} messages"
-
-    def merge_summaries(self, previous: str, current: str) -> str:
-        """Merge a prior structured summary with the current one.
-
-        Keeps both under a single "previous / latest" framing so an iterative
-        re-compaction never discards the earlier phase structure.
-        """
-        previous = (previous or "").strip()
-        current = (current or "").strip()
-        if not previous:
-            return current
-        if not current:
-            return previous
-        return f"{previous}\n\n[Updated with newer activity]\n{current}"
-
-    # -- rendering ---------------------------------------------------------
-
-    def _render(self, messages: List[Dict[str, Any]]) -> str:
-        completed: List[str] = []
-        in_progress: List[str] = []
-        pending: List[str] = []
-        files: List[str] = []
-        active_task = ""
-
-        for msg in messages:
-            role = msg.get("role", "")
-            body = _text(msg.get("content"))
-
-            # First substantive user turn frames the active task.
-            if role == "user" and body.strip() and not active_task:
-                active_task = _clip(body)
-
-            # Executed work — tool calls and tool results — is *completed*.
-            # An assistant turn that merely proposes or *asks* about work has
-            # not been executed, so it must not be recorded as completed (it is
-            # captured under "Pending Questions" / "In Progress" instead);
-            # only a substantive, non-questioning assistant turn is completed.
-            tool_calls = msg.get("tool_calls")
-            if isinstance(tool_calls, list) and tool_calls:
-                for tc in tool_calls:
-                    if not isinstance(tc, dict):
-                        continue
-                    name = (tc.get("function", {}) or {}).get("name", "tool")
-                    completed.append(f"Called `{name}`")
-            elif role == "assistant" and body.strip() and "?" not in body:
-                completed.append(_clip(body))
-            elif role == "tool" and body.strip():
-                completed.append(_clip(f"tool result: {body}"))
-
-            # Any turn with a question mark contributes an open question.
-            if body and "?" in body:
-                for sentence in body.split("?"):
-                    sentence = sentence.strip()
-                    if sentence:
-                        pending.append(_clip(sentence + "?"))
-
-            # Harvest file/path tokens verbatim from every turn.
-            if body:
-                for match in _PATH_RE.findall(body):
-                    if match not in files:
-                        files.append(match)
-
-        # The most recent user turn (if different) is what's in progress.
-        for msg in reversed(messages):
-            if msg.get("role") == "user":
-                latest = _clip(_text(msg.get("content")))
-                if latest and latest != active_task:
-                    in_progress.append(latest)
-                break
-
-        return SUMMARY_TEMPLATE.format(
-            active_task=active_task or "(not specified)",
-            completed=self._bullets(completed),
-            in_progress=self._bullets(in_progress),
-            pending=self._bullets(pending),
-            files=self._bullets(files),
-            remaining=self._bullets(pending or in_progress),
-        )
-
-    @staticmethod
-    def _bullets(items: List[str]) -> str:
-        if not items:
-            return "(none)"
-        # De-duplicate while preserving order, then cap.
-        seen: List[str] = []
-        for item in items:
-            if item not in seen:
-                seen.append(item)
-        return "\n".join(f"- {item}" for item in seen[:_MAX_ITEMS])

src/praisonai-agents/praisonaiagents/config/feature_configs.py

@@ -25,7 +25,7 @@ Usage:
     # With config
     agent = Agent(
         instructions="...",
-        memory=MemoryConfig(backend="sqlite", user_id="user123"),
+        memory=MemoryConfig(backend="redis", user_id="user123"),
         knowledge=KnowledgeConfig(sources=["docs/"], rerank=True),
         tool_search=ToolSearchConfig(enabled="auto", threshold_pct=15),
     )
@@ -52,54 +52,14 @@ if TYPE_CHECKING:
 
 
 class MemoryBackend(str, Enum):
-    """Memory storage backends.
-
-    Every member must have an adapter in ``praisonaiagents.memory.adapters``
-    (FILE is served by ``FileMemory``). Declaring a backend with no adapter
-    used to silently swap in a local SQLite/JSON store.
-    """
+    """Memory storage backends."""
     FILE = "file"
     SQLITE = "sqlite"
-    CHROMA = "chroma"
+    REDIS = "redis"
+    VALKEY = "valkey"
+    POSTGRES = "postgres"
     MEM0 = "mem0"
     MONGODB = "mongodb"
-    DAKERA = "dakera"
-    IN_MEMORY = "in_memory"
-
-
-#: Accepted before but never implemented: requests were silently redirected.
-UNIMPLEMENTED_MEMORY_BACKENDS = ("redis", "valkey", "postgres", "postgresql")
-
-
-def available_memory_backends() -> List[str]:
-    """Backends ``MemoryConfig(backend=...)`` accepts, read from the registry.
-
-    Adapters added via ``register_memory_adapter()`` are accepted automatically.
-    """
-    from ..memory.adapters import list_memory_adapters
-    return sorted(set(list_memory_adapters()) | {MemoryBackend.FILE.value})
-
-
-def validate_memory_backend(backend: Union[str, "MemoryBackend"]) -> str:
-    """Normalise a backend name; raise rather than substitute a different store."""
-    from .parse_utils import make_preset_error
-    from ..memory.adapters.registry import MEMORY_PROVIDER_ALIASES
-
-    name = backend.value if isinstance(backend, MemoryBackend) else str(backend)
-    name = MEMORY_PROVIDER_ALIASES.get(name.strip().lower(), name.strip().lower())
-    valid = available_memory_backends()
-    if name in valid:
-        return name
-    if name in UNIMPLEMENTED_MEMORY_BACKENDS:
-        raise ValueError(
-            f"Memory backend '{name}' is not implemented - no {name} memory "
-            f"adapter is registered. Earlier releases accepted it and silently "
-            f"stored to a local file instead. Valid backends: {', '.join(valid)}. "
-            f"To keep using {name}, pass a live store (memory=<instance> or "
-            f"db(url=...)), or register an adapter with "
-            f"register_memory_adapter('{name}', MyAdapter)."
-        )
-    raise make_preset_error("memory backend", name, valid)
 
 
 class LearnScope(str, Enum):
@@ -234,7 +194,7 @@ class MemoryConfig:
         Agent(memory=True)
         
         # With backend
-        Agent(memory=MemoryConfig(backend="sqlite"))
+        Agent(memory=MemoryConfig(backend="redis"))
         
         # Full config with learning
         Agent(memory=MemoryConfig(
@@ -289,11 +249,7 @@ class MemoryConfig:
     # Auto-save session name (consolidated from standalone auto_save param)
     # When set, automatically saves session to memory with this name
     auto_save: Optional[str] = None
-
-    def __post_init__(self):
-        # Reject a backend we cannot provide instead of substituting another.
-        self.backend = validate_memory_backend(self.backend)
-
+    
     def to_dict(self) -> Dict[str, Any]:
         """Convert to dictionary."""
         learn_dict = None
@@ -323,18 +279,11 @@ class MemoryConfig:
 
 
 class ChunkingStrategy(str, Enum):
-    """Knowledge chunking strategies.
-
-    Every member must resolve to a chunker via
-    ``praisonaiagents.knowledge.chunking.normalize_chunker_type``. FIXED and
-    PARAGRAPH are aliases for ``token``/``recursive``; the rest are chunker ids.
-    """
+    """Knowledge chunking strategies."""
     FIXED = "fixed"
-    PARAGRAPH = "paragraph"
-    TOKEN = "token"
-    RECURSIVE = "recursive"
     SEMANTIC = "semantic"
     SENTENCE = "sentence"
+    PARAGRAPH = "paragraph"
 
 
 @dataclass
@@ -373,12 +322,10 @@ class KnowledgeConfig:
     embedder: str = "openai"
     embedder_config: Optional[Dict[str, Any]] = None
     
-    # Chunking (direct fields). Defaults match what Knowledge actually used
-    # while these fields were inert, so enabling them changes nothing for
-    # anyone who did not set them.
-    chunking_strategy: Union[str, ChunkingStrategy] = ChunkingStrategy.RECURSIVE
-    chunk_size: int = 512
-    chunk_overlap: int = 50
+    # Chunking (direct fields)
+    chunking_strategy: Union[str, ChunkingStrategy] = ChunkingStrategy.SEMANTIC
+    chunk_size: int = 1000
+    chunk_overlap: int = 200
     
     # Chunker config dict (alternative to direct fields)
     # Supports: {"type": "semantic", "chunk_size": 512, ...}
@@ -900,6 +847,10 @@ class ExecutionConfig:
     code_execution: bool = False
     code_mode: str = "safe"  # "safe" or "unsafe"
     
+    # Code execution sandbox mode - "sandbox" (default) uses subprocess isolation
+    # "direct" runs in current process (legacy, less secure)
+    code_sandbox_mode: str = "sandbox"  # "sandbox" or "direct"
+
     # Code-execution-with-tools (code mode): when True, model-generated code may
     # call the agent's registered tools directly via injected proxies, enabling
     # multi-step tool pipelines in a single turn (intermediate results stay out
@@ -940,12 +891,8 @@ class ExecutionConfig:
     
     # Parallel tool execution (Gap 2): Enable parallel execution of batched LLM tool calls
     # When True, multiple tool calls from LLM are executed concurrently instead of sequentially
-    # Default False preserves existing behavior for backward compatibility.
-    # This is the single source of truth; ToolConfig.parallel is a deprecated alias.
-    # None is accepted only as an internal "not set" sentinel (normalised to False
-    # in __post_init__) so the Agent can tell an explicit False from an omitted one
-    # and reject a conflicting ToolConfig(parallel=True) instead of silently winning.
-    parallel_tool_calls: Optional[bool] = None
+    # Default False preserves existing behavior for backward compatibility
+    parallel_tool_calls: bool = False
 
     # Durable tool-loop replay. Default-off keeps the execution hot path free
     # of journal construction and SQLite writes.
@@ -955,11 +902,6 @@ class ExecutionConfig:
 
     def __post_init__(self) -> None:
         """Post-initialization processing with deprecation warnings and validation."""
-        # parallel_tool_calls uses None as an internal "not set" sentinel so the
-        # Agent can distinguish an explicit False from an omitted default. Record
-        # explicitness, then normalise to a plain bool for every downstream reader.
-        self._parallel_tool_calls_explicit = self.parallel_tool_calls is not None
-        self.parallel_tool_calls = bool(self.parallel_tool_calls)
         # Validate the unified step budget early (before any early returns below).
         if self.max_steps is not None and self.max_steps < 1:
             raise ValueError("ExecutionConfig.max_steps must be >= 1 when set.")
@@ -1051,6 +993,7 @@ class ExecutionConfig:
             "retry_jitter": self.retry_jitter,
             "code_execution": self.code_execution,
             "code_mode": self.code_mode,
+            "code_sandbox_mode": self.code_sandbox_mode,
             "code_tools": self.code_tools,
             "code_tools_allow": self.code_tools_allow,
             "context_compaction": (
@@ -1102,6 +1045,7 @@ class ExecutionConfig:
             retry_jitter=data.get("retry_jitter", 0.1),
             code_execution=data.get("code_execution", False),
             code_mode=data.get("code_mode", "safe"),
+            code_sandbox_mode=data.get("code_sandbox_mode", "sandbox"),
             code_tools=data.get("code_tools", False),
             code_tools_allow=data.get("code_tools_allow", None),
             context_compaction=context_compaction,
@@ -1111,7 +1055,7 @@ class ExecutionConfig:
             max_context_tokens=data.get("max_context_tokens", None),
             compaction_strategy=compaction_strategy,
             max_budget=data.get("max_budget", None),
-            parallel_tool_calls=data.get("parallel_tool_calls", None),
+            parallel_tool_calls=data.get("parallel_tool_calls", False),
             durable=data.get("durable", False),
             journal_path=data.get("journal_path", None),
             resume_run_id=data.get("resume_run_id", None),
@@ -1213,13 +1157,8 @@ class ToolConfig:
     # Retry policy for tool execution with exponential backoff
     retry_policy: Optional[Any] = None  # RetryPolicy instance
     
-    # DEPRECATED ALIAS for ExecutionConfig.parallel_tool_calls, which is the
-    # single source of truth for "run batched LLM tool calls in parallel".
-    # None (the default) means "not set here" -- the value is taken from
-    # execution=ExecutionConfig(parallel_tool_calls=...). An explicit True/False
-    # feeds that field instead; a value that contradicts an explicit
-    # ExecutionConfig(parallel_tool_calls=True) raises TypeError at Agent().
-    parallel: Optional[bool] = None
+    # Enable parallel execution of batched LLM tool calls
+    parallel: bool = False
     
     # Tool output handling and artifact storage
     output_limit: int = DEFAULT_TOOL_OUTPUT_LIMIT  # Maximum bytes before spilling to artifact store
@@ -1282,7 +1221,7 @@ class ToolConfig:
         return cls(
             timeout=data.get("timeout"),
             retry_policy=retry_policy,
-            parallel=data.get("parallel"),
+            parallel=data.get("parallel", False),
             output_limit=data.get("output_limit", DEFAULT_TOOL_OUTPUT_LIMIT),
             output_max_lines=data.get("output_max_lines"),
             output_direction=data.get("output_direction", "both"),

src/praisonai-agents/praisonaiagents/config/loader.py

@@ -49,6 +49,7 @@ VALID_DEFAULTS_KEYS = {
     "model": (str,),
     "small_model": (str,),
     "base_url": (str,),
+    "api_key": (str,),
     # Feature flags
     "allow_delegation": (bool,),
     "allow_code_execution": (bool,),
@@ -65,7 +66,9 @@ VALID_DEFAULTS_KEYS = {
     "caching": (dict, bool),
     "autonomy": (dict, bool),
     "skills": (dict, list),
-    "retry": (dict, bool),
+    "context": (dict, bool),
+    "hooks": (dict, list),
+    "templates": (dict,),
 }
 
 VALID_ROOT_KEYS = {"plugins", "defaults"}
@@ -155,14 +158,12 @@ class DefaultsConfig:
     knowledge: Optional[Dict[str, Any]] = None
     planning: Optional[Dict[str, Any]] = None
     reflection: Optional[Dict[str, Any]] = None
-    guardrails: Optional[Dict[str, Any]] = None
     web: Optional[Dict[str, Any]] = None
     output: Optional[Dict[str, Any]] = None
     execution: Optional[Dict[str, Any]] = None
     caching: Optional[Dict[str, Any]] = None
     autonomy: Optional[Dict[str, Any]] = None
     skills: Optional[Dict[str, Any]] = None
-    retry: Optional[Dict[str, Any]] = None
     
     def to_dict(self) -> Dict[str, Any]:
         return {
@@ -176,14 +177,12 @@ class DefaultsConfig:
             "knowledge": self.knowledge,
             "planning": self.planning,
             "reflection": self.reflection,
-            "guardrails": self.guardrails,
             "web": self.web,
             "output": self.output,
             "execution": self.execution,
             "caching": self.caching,
             "autonomy": self.autonomy,
             "skills": self.skills,
-            "retry": self.retry,
         }
 
 
@@ -353,14 +352,12 @@ def _dict_to_defaults_config(data: Dict[str, Any]) -> DefaultsConfig:
         knowledge=data.get("knowledge"),
         planning=data.get("planning"),
         reflection=data.get("reflection"),
-        guardrails=data.get("guardrails"),
         web=data.get("web"),
         output=data.get("output"),
         execution=data.get("execution"),
         caching=data.get("caching"),
         autonomy=data.get("autonomy"),
         skills=data.get("skills"),
-        retry=data.get("retry"),
     )
 
 
@@ -709,8 +706,8 @@ def _defaults_has_any_values() -> bool:
             getattr(defaults, key, None) is not None
             for key in (
                 "model", "small_model", "base_url", "memory", "knowledge",
-                "planning", "reflection", "guardrails", "web", "output",
-                "execution", "caching", "autonomy", "skills", "retry",
+                "planning", "reflection", "web", "output", "execution",
+                "caching", "autonomy",
             )
         )
     return _defaults_has_values

src/praisonai-agents/praisonaiagents/config/param_resolver.py

@@ -314,14 +314,10 @@ def _resolve_string(
     
     # Check for preset
     if presets:
-        # Case-insensitive lookup, whitespace-tolerant and treating -/_ as
-        # interchangeable so the accepted spellings match the closed-set guard
-        # in validate_preset_string (which uses the same normalization). Without
-        # this, a value that passed construction-time validation (e.g.
-        # " sliding_window " or "sliding-window") would be rejected here.
-        value_norm = value.strip().lower().replace("-", "_")
+        # Case-insensitive lookup
+        value_lower = value.lower()
         for preset_key in presets:
-            if preset_key.strip().lower().replace("-", "_") == value_norm:
+            if preset_key.lower() == value_lower:
                 return _apply_preset(preset_key, presets, config_class)
         
         # Not a valid preset - raise helpful error

src/praisonai-agents/praisonaiagents/config/parse_utils.py

@@ -195,53 +195,6 @@ def make_preset_error(
     return ValueError(" ".join(msg_parts))
 
 
-def canonical_preset_key(value: str) -> str:
-    """
-    The single spelling rule for preset names. Validation and resolution must
-    not disagree about what counts as the same preset, so both go through here.
-
-    Matching is case-insensitive, ignores surrounding whitespace, and treats
-    ``-``/``_`` as interchangeable.
-    """
-    return value.strip().lower().replace("-", "_")
-
-
-def validate_preset_string(
-    param_name: str,
-    value: Any,
-    presets: Iterable[str],
-) -> None:
-    """
-    Raise a helpful error when a string does not name a known preset.
-
-    Non-string values pass through untouched, so callers can hand this the raw
-    parameter without pre-checking the type. Matching is case-insensitive,
-    ignores surrounding whitespace, and treats ``-``/``_`` as interchangeable,
-    mirroring the preset lookups performed by the parameter resolvers (e.g.
-    ``PermissionMode.resolve`` accepts both ``accept_edits`` and
-    ``accept-edits``). This keeps the guard from rejecting spellings the
-    downstream resolver would happily accept.
-
-    Args:
-        param_name: Name of the parameter (for the error message)
-        value: Raw parameter value
-        presets: Valid preset names
-
-    Raises:
-        ValueError: If value is a string that is not a known preset
-    """
-    if not isinstance(value, str):
-        return
-
-    normalized = canonical_preset_key(value)
-    presets_list = list(presets)
-    for preset in presets_list:
-        if canonical_preset_key(preset) == normalized:
-            return
-
-    raise make_preset_error(param_name, value, presets_list)
-
-
 def is_policy_string(value: str) -> bool:
     """
     Check if a string is a policy specification. O(1) operation.

src/praisonai-agents/praisonaiagents/config/presets.py

@@ -19,7 +19,9 @@ MEMORY_PRESETS: Dict[str, Dict[str, Any]] = {
     # Backend presets
     "file": {"backend": "file"},
     "sqlite": {"backend": "sqlite"},
-    "chroma": {"backend": "chroma"},
+    "redis": {"backend": "redis"},
+    "postgres": {"backend": "postgres"},
+    "postgresql": {"backend": "postgres"},
     "mem0": {"backend": "mem0"},
     "mongodb": {"backend": "mongodb"},
     # Feature presets
@@ -30,10 +32,11 @@ MEMORY_PRESETS: Dict[str, Dict[str, Any]] = {
     "chat": {"backend": "file", "history": True, "history_limit": 20},  # Conversational
 }
 
-# Only schemes backed by a registered memory adapter belong here. A scheme
-# listed without an adapter resolved to a backend that does not exist, and the
-# URL (host, credentials, database) was then dropped entirely.
 MEMORY_URL_SCHEMES: Dict[str, str] = {
+    "postgresql": "postgres",
+    "postgres": "postgres",
+    "redis": "redis",
+    "rediss": "redis",  # Redis with SSL
     "sqlite": "sqlite",
     "mongodb": "mongodb",
     "mongodb+srv": "mongodb",

src/praisonai-agents/praisonaiagents/context/composer.py

@@ -242,51 +242,41 @@ class ContextComposer:
         full_history: List[Dict[str, Any]],
         tool_call_ids: set
     ) -> List[Dict[str, Any]]:
-        """Ensure tool_call/tool_result pairs are complete.
-
-        Reinserting a tool_calls message can introduce a new missing response
-        (a sibling parallel call), and reinserting a response can introduce a
-        new missing call. Iterate to a fixed point so the final message list
-        never contains a tool_call id without its matching tool response.
-        """
-        changed = True
-        while changed:
-            changed = False
-
-            # Recompute pairs present in the current result
-            result_call_ids = set()
-            result_response_ids = set()
-            for msg in result:
-                if "tool_calls" in msg:
-                    for tc in msg.get("tool_calls", []):
-                        if isinstance(tc, dict) and "id" in tc:
-                            result_call_ids.add(tc["id"])
-                if msg.get("tool_call_id"):
-                    result_response_ids.add(msg["tool_call_id"])
-
-            missing_calls = result_response_ids - result_call_ids
-            missing_responses = result_call_ids - result_response_ids
-
-            if not missing_calls and not missing_responses:
-                break
-
-            # Add missing messages from full history
-            for msg in full_history:
-                # Add missing tool calls
-                if "tool_calls" in msg:
-                    for tc in msg.get("tool_calls", []):
-                        if isinstance(tc, dict) and tc.get("id") in missing_calls:
-                            if msg not in result:
-                                result.insert(0, msg)
-                                changed = True
-                            break
-
-                # Add missing tool responses
-                if msg.get("tool_call_id") in missing_responses:
-                    if msg not in result:
-                        result.append(msg)
-                        changed = True
-
+        """Ensure tool_call/tool_result pairs are complete."""
+        # Find tool calls in result
+        result_call_ids = set()
+        result_response_ids = set()
+        
+        for msg in result:
+            if "tool_calls" in msg:
+                for tc in msg.get("tool_calls", []):
+                    if isinstance(tc, dict) and "id" in tc:
+                        result_call_ids.add(tc["id"])
+            if msg.get("tool_call_id"):
+                result_response_ids.add(msg["tool_call_id"])
+        
+        # Find missing pairs
+        missing_calls = result_response_ids - result_call_ids
+        missing_responses = result_call_ids - result_response_ids
+        
+        if not missing_calls and not missing_responses:
+            return result
+        
+        # Add missing messages from full history
+        for msg in full_history:
+            # Add missing tool calls
+            if "tool_calls" in msg:
+                for tc in msg.get("tool_calls", []):
+                    if isinstance(tc, dict) and tc.get("id") in missing_calls:
+                        if msg not in result:
+                            result.insert(0, msg)
+                        break
+            
+            # Add missing tool responses
+            if msg.get("tool_call_id") in missing_responses:
+                if msg not in result:
+                    result.append(msg)
+        
         return result
     
     def get_ledger(self) -> ContextLedger:

src/praisonai-agents/praisonaiagents/context/optimizer.py

@@ -14,21 +14,6 @@ from .compressor import ContextCompressor
 logger = logging.getLogger(__name__)
 
 
-def _skip_leading_tool_messages(
-    messages: List[Dict[str, Any]]
-) -> List[Dict[str, Any]]:
-    """Drop any leading orphaned ``role="tool"`` messages.
-
-    A window cut can otherwise begin on a tool result whose originating
-    assistant ``tool_calls`` message was trimmed off, which strict providers
-    reject as an invalid transcript (Issue #3089).
-    """
-    start = 0
-    while start < len(messages) and messages[start].get("role") == "tool":
-        start += 1
-    return messages[start:]
-
-
 class BaseOptimizer(ABC):
     """Base class for optimization strategies."""
     
@@ -86,9 +71,8 @@ class TruncateOptimizer(BaseOptimizer):
             else:
                 other_msgs.append(msg)
         
-        # Keep recent messages (skip a leading orphaned tool result).
+        # Keep recent messages
         recent = other_msgs[-self.preserve_recent:] if other_msgs else []
-        recent = _skip_leading_tool_messages(recent)
         
         result = system_msgs + recent
         
@@ -98,17 +82,7 @@ class TruncateOptimizer(BaseOptimizer):
                 if msg.get("role") != "system":
                     result.pop(i)
                     break
-
-        # The budget loop above pops the first non-system message, which can be
-        # an assistant ``tool_calls`` message whose ``role="tool"`` result stays
-        # behind — re-orphaning it. Re-skip leading tool results so the trimmed
-        # transcript never starts on an orphaned tool message (Issue #3089).
-        system_msgs = [m for m in result if m.get("role") == "system"]
-        other_msgs = _skip_leading_tool_messages(
-            [m for m in result if m.get("role") != "system"]
-        )
-        result = system_msgs + other_msgs
-
+        
         optimized_tokens = estimate_messages_tokens(result)
         
         return result, OptimizationResult(
@@ -159,11 +133,9 @@ class SlidingWindowOptimizer(BaseOptimizer):
             else:
                 break
         
-        # Ensure order (skip a leading orphaned tool result in the tail).
+        # Ensure order
         system_msgs = [m for m in result if m.get("role") == "system"]
-        other_msgs = _skip_leading_tool_messages(
-            [m for m in result if m.get("role") != "system"]
-        )
+        other_msgs = [m for m in result if m.get("role") != "system"]
         result = system_msgs + other_msgs
         
         optimized_tokens = estimate_messages_tokens(result)
@@ -1108,18 +1080,6 @@ def get_optimizer(
         Optimizer instance
     """
     optimizer_class = OPTIMIZER_REGISTRY.get(strategy, SmartOptimizer)
-
-    # Optimizers do not share a constructor signature. Callers (e.g. the
-    # ContextManager) pass the union of every optimizer's kwargs, so filter to
-    # the ones this class actually accepts; otherwise all but SmartOptimizer
-    # raise TypeError and context management is silently disabled upstream.
-    import inspect
-    params = inspect.signature(optimizer_class.__init__).parameters
-    accepts_var_kw = any(
-        p.kind == inspect.Parameter.VAR_KEYWORD for p in params.values()
-    )
-    if not accepts_var_kw:
-        kwargs = {k: v for k, v in kwargs.items() if k in params}
     return optimizer_class(**kwargs)
 
 

src/praisonai-agents/praisonaiagents/db/__init__.py

@@ -88,26 +88,6 @@ class _LazyDbModule:
 db = _LazyDbModule()
 
 
-# ``from praisonaiagents import db`` returns *this submodule*, not the singleton
-# above (Python binds a real submodule as a package attribute, shadowing the
-# package ``__getattr__``). Make the submodule object itself callable and proxy
-# backend lookups to the singleton so ``db(...)`` and ``db.PraisonDB`` both work
-# regardless of how ``db`` is imported.
-import sys as _sys
-from types import ModuleType as _ModuleType
-
-
-class _CallableDbModule(_ModuleType):
-    def __call__(self, **kwargs):
-        return db(**kwargs)
-
-    def __getattr__(self, name):
-        return getattr(db, name)
-
-
-_sys.modules[__name__].__class__ = _CallableDbModule
-
-
 __all__ = [
     "DbAdapter",
     "AsyncDbAdapter",

src/praisonai-agents/praisonaiagents/escalation/doom_loop.py

@@ -6,7 +6,7 @@ Provides recovery strategies when loops are detected.
 """
 
 from dataclasses import dataclass, field
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any, Dict, List, Optional
 from enum import Enum
 import time
 import hashlib
@@ -117,7 +117,7 @@ class DoomLoopDetector:
         self._loop_events: List[DoomLoopEvent] = []
         self._recovery_attempts: int = 0
         self._start_time: Optional[float] = None
-        self._progress_markers: List[Tuple[str, float]] = []
+        self._progress_markers: List[str] = []
         self._current_backoff: float = self.config.initial_backoff
         self._content_chunk_counts: Dict[str, int] = {}  # hash -> count
     
@@ -193,7 +193,7 @@ class DoomLoopDetector:
         Call this when the agent makes real progress (e.g., file modified,
         test passed, user goal partially achieved).
         """
-        self._progress_markers.append((marker, time.time()))
+        self._progress_markers.append(marker)
     
     def is_doom_loop(self) -> bool:
         """
@@ -379,19 +379,10 @@ class DoomLoopDetector:
         if len(self._actions) < self.config.max_no_progress_steps:
             return False
         
-        # Only count progress markers within the current no-progress window.
-        # Without this recency filter a single early success would suppress
-        # NO_PROGRESS detection for the rest of the session.
-        # Use the boundary *before* the window (the completion timestamp of the
-        # action immediately preceding it, or 0 if the window is the whole
-        # history) so a marker recorded *during* the window's first action —
-        # whose own record_action timestamp is set at completion, i.e. after the
-        # marker — is still counted rather than filtered out.
-        n = self.config.max_no_progress_steps
-        boundary = self._actions[-n - 1].timestamp if len(self._actions) > n else 0.0
+        # If we have progress markers, we're making progress
         recent_markers = [
-            m for (m, ts) in self._progress_markers
-            if ts >= boundary
+            m for m in self._progress_markers
+            if True  # Could add timestamp filtering
         ]
         if recent_markers:
             return False

src/praisonai-agents/praisonaiagents/eval/__init__.py

@@ -115,99 +115,105 @@ __all__ = [
     "TrialReport",
 ]
 
-from .._lazy import create_lazy_getattr
-
 _LAZY_IMPORTS = {
-    "BaseEvaluator": ("praisonaiagents.eval.base", "BaseEvaluator"),
-    "AccuracyEvaluator": ("praisonaiagents.eval.accuracy", "AccuracyEvaluator"),
-    "PerformanceEvaluator": ("praisonaiagents.eval.performance", "PerformanceEvaluator"),
-    "ReliabilityEvaluator": ("praisonaiagents.eval.reliability", "ReliabilityEvaluator"),
-    "CriteriaEvaluator": ("praisonaiagents.eval.criteria", "CriteriaEvaluator"),
-    "ContextEvaluator": ("praisonaiagents.eval.context_eval", "ContextEvaluator"),
-    "MediaEvaluator": ("praisonaiagents.eval.media", "MediaEvaluator"),
-    "ComparisonEval": ("praisonaiagents.eval.comparison", "ComparisonEval"),
-    "SafetyEval": ("praisonaiagents.eval.safety", "SafetyEval"),
-    "HarnessEvaluator": ("praisonaiagents.eval.harness_eval", "HarnessEvaluator"),
-    "harness_row_to_eval_case": ("praisonaiagents.eval.harness_eval", "harness_row_to_eval_case"),
-    "HarnessResult": ("praisonaiagents.eval.results", "HarnessResult"),
-    "EvalSuite": ("praisonaiagents.eval.suite", "EvalSuite"),
-    "AccuracyResult": ("praisonaiagents.eval.results", "AccuracyResult"),
-    "PerformanceResult": ("praisonaiagents.eval.results", "PerformanceResult"),
-    "ReliabilityResult": ("praisonaiagents.eval.results", "ReliabilityResult"),
-    "CriteriaResult": ("praisonaiagents.eval.results", "CriteriaResult"),
-    "ContextHandoffResult": ("praisonaiagents.eval.context_eval", "ContextHandoffResult"),
-    "BudgetComplianceResult": ("praisonaiagents.eval.context_eval", "BudgetComplianceResult"),
-    "ContextEvalResult": ("praisonaiagents.eval.context_eval", "ContextEvalResult"),
-    "MediaEvaluationResult": ("praisonaiagents.eval.media", "MediaEvaluationResult"),
-    "ComparisonResult": ("praisonaiagents.eval.comparison", "ComparisonResult"),
-    "SafetyResult": ("praisonaiagents.eval.safety", "SafetyResult"),
-    "EvalSuiteResult": ("praisonaiagents.eval.suite", "EvalSuiteResult"),
-    "EvaluationScore": ("praisonaiagents.eval.results", "EvaluationScore"),
-    "PerformanceMetrics": ("praisonaiagents.eval.results", "PerformanceMetrics"),
-    "ToolCallResult": ("praisonaiagents.eval.results", "ToolCallResult"),
-    "CriteriaScore": ("praisonaiagents.eval.results", "CriteriaScore"),
+    "BaseEvaluator": ("base", "BaseEvaluator"),
+    "AccuracyEvaluator": ("accuracy", "AccuracyEvaluator"),
+    "PerformanceEvaluator": ("performance", "PerformanceEvaluator"),
+    "ReliabilityEvaluator": ("reliability", "ReliabilityEvaluator"),
+    "CriteriaEvaluator": ("criteria", "CriteriaEvaluator"),
+    "ContextEvaluator": ("context_eval", "ContextEvaluator"),
+    "MediaEvaluator": ("media", "MediaEvaluator"),
+    "ComparisonEval": ("comparison", "ComparisonEval"),
+    "SafetyEval": ("safety", "SafetyEval"),
+    "HarnessEvaluator": ("harness_eval", "HarnessEvaluator"),
+    "harness_row_to_eval_case": ("harness_eval", "harness_row_to_eval_case"),
+    "HarnessResult": ("results", "HarnessResult"),
+    "EvalSuite": ("suite", "EvalSuite"),
+    "AccuracyResult": ("results", "AccuracyResult"),
+    "PerformanceResult": ("results", "PerformanceResult"),
+    "ReliabilityResult": ("results", "ReliabilityResult"),
+    "CriteriaResult": ("results", "CriteriaResult"),
+    "ContextHandoffResult": ("context_eval", "ContextHandoffResult"),
+    "BudgetComplianceResult": ("context_eval", "BudgetComplianceResult"),
+    "ContextEvalResult": ("context_eval", "ContextEvalResult"),
+    "MediaEvaluationResult": ("media", "MediaEvaluationResult"),
+    "ComparisonResult": ("comparison", "ComparisonResult"),
+    "SafetyResult": ("safety", "SafetyResult"),
+    "EvalSuiteResult": ("suite", "EvalSuiteResult"),
+    "EvaluationScore": ("results", "EvaluationScore"),
+    "PerformanceMetrics": ("results", "PerformanceMetrics"),
+    "ToolCallResult": ("results", "ToolCallResult"),
+    "CriteriaScore": ("results", "CriteriaScore"),
     # DRY: Common grading base classes and protocols
-    "BaseLLMGrader": ("praisonaiagents.eval.grader", "BaseLLMGrader"),
-    "GradeResult": ("praisonaiagents.eval.grader", "GradeResult"),
-    "GraderProtocol": ("praisonaiagents.eval.protocols", "GraderProtocol"),
-    "GradeResultProtocol": ("praisonaiagents.eval.protocols", "GradeResultProtocol"),
-    "ScoredResultProtocol": ("praisonaiagents.eval.protocols", "ScoredResultProtocol"),
-    "AsyncGraderProtocol": ("praisonaiagents.eval.protocols", "AsyncGraderProtocol"),
-    "parse_score_reasoning": ("praisonaiagents.eval.grader", "parse_score_reasoning"),
+    "BaseLLMGrader": ("grader", "BaseLLMGrader"),
+    "GradeResult": ("grader", "GradeResult"),
+    "GraderProtocol": ("protocols", "GraderProtocol"),
+    "GradeResultProtocol": ("protocols", "GradeResultProtocol"),
+    "ScoredResultProtocol": ("protocols", "ScoredResultProtocol"),
+    "AsyncGraderProtocol": ("protocols", "AsyncGraderProtocol"),
+    "parse_score_reasoning": ("grader", "parse_score_reasoning"),
     # Eval package types
-    "EvalCase": ("praisonaiagents.eval.package", "EvalCase"),
-    "EvalResult": ("praisonaiagents.eval.package", "EvalResult"),
-    "EvalReport": ("praisonaiagents.eval.package", "EvalReport"),
-    "EvalPackage": ("praisonaiagents.eval.package", "EvalPackage"),
-    "EvalRunnerProtocol": ("praisonaiagents.eval.package", "EvalRunnerProtocol"),
+    "EvalCase": ("package", "EvalCase"),
+    "EvalResult": ("package", "EvalResult"),
+    "EvalReport": ("package", "EvalReport"),
+    "EvalPackage": ("package", "EvalPackage"),
+    "EvalRunnerProtocol": ("package", "EvalRunnerProtocol"),
     # Unified Judge API (follows add_X/get_X/list_X naming)
-    "Judge": ("praisonaiagents.eval.judge", "Judge"),
-    "JudgeConfig": ("praisonaiagents.eval.judge", "JudgeConfig"),
-    "JudgeResult": ("praisonaiagents.eval.results", "JudgeResult"),
-    "JudgeProtocol": ("praisonaiagents.eval.protocols", "JudgeProtocol"),
-    "JudgeResultProtocol": ("praisonaiagents.eval.protocols", "JudgeResultProtocol"),
-    "AccuracyJudge": ("praisonaiagents.eval.judge", "AccuracyJudge"),
-    "CriteriaJudge": ("praisonaiagents.eval.judge", "CriteriaJudge"),
-    "RecipeJudge": ("praisonaiagents.eval.judge", "RecipeJudge"),
-    "add_judge": ("praisonaiagents.eval.judge", "add_judge"),
-    "get_judge": ("praisonaiagents.eval.judge", "get_judge"),
-    "list_judges": ("praisonaiagents.eval.judge", "list_judges"),
-    "remove_judge": ("praisonaiagents.eval.judge", "remove_judge"),
+    "Judge": ("judge", "Judge"),
+    "JudgeConfig": ("judge", "JudgeConfig"),
+    "JudgeResult": ("results", "JudgeResult"),
+    "JudgeProtocol": ("protocols", "JudgeProtocol"),
+    "JudgeResultProtocol": ("protocols", "JudgeResultProtocol"),
+    "AccuracyJudge": ("judge", "AccuracyJudge"),
+    "CriteriaJudge": ("judge", "CriteriaJudge"),
+    "RecipeJudge": ("judge", "RecipeJudge"),
+    "add_judge": ("judge", "add_judge"),
+    "get_judge": ("judge", "get_judge"),
+    "list_judges": ("judge", "list_judges"),
+    "remove_judge": ("judge", "remove_judge"),
     # Dynamic judge configuration (domain-agnostic)
-    "JudgeCriteriaConfig": ("praisonaiagents.eval.judge", "JudgeCriteriaConfig"),
-    "OptimizationRuleProtocol": ("praisonaiagents.eval.protocols", "OptimizationRuleProtocol"),
-    "add_optimization_rule": ("praisonaiagents.eval.judge", "add_optimization_rule"),
-    "get_optimization_rule": ("praisonaiagents.eval.judge", "get_optimization_rule"),
-    "list_optimization_rules": ("praisonaiagents.eval.judge", "list_optimization_rules"),
-    "remove_optimization_rule": ("praisonaiagents.eval.judge", "remove_optimization_rule"),
+    "JudgeCriteriaConfig": ("judge", "JudgeCriteriaConfig"),
+    "OptimizationRuleProtocol": ("protocols", "OptimizationRuleProtocol"),
+    "add_optimization_rule": ("judge", "add_optimization_rule"),
+    "get_optimization_rule": ("judge", "get_optimization_rule"),
+    "list_optimization_rules": ("judge", "list_optimization_rules"),
+    "remove_optimization_rule": ("judge", "remove_optimization_rule"),
     # Token utilities
-    "estimate_tokens": ("praisonaiagents.eval.tokens", "estimate_tokens"),
-    "get_context_length": ("praisonaiagents.eval.tokens", "get_context_length"),
-    "count_tokens": ("praisonaiagents.eval.tokens", "count_tokens"),
-    "needs_chunking": ("praisonaiagents.eval.tokens", "needs_chunking"),
-    "get_recommended_chunk_size": ("praisonaiagents.eval.tokens", "get_recommended_chunk_size"),
+    "estimate_tokens": ("tokens", "estimate_tokens"),
+    "get_context_length": ("tokens", "get_context_length"),
+    "count_tokens": ("tokens", "count_tokens"),
+    "needs_chunking": ("tokens", "needs_chunking"),
+    "get_recommended_chunk_size": ("tokens", "get_recommended_chunk_size"),
     # EvaluationLoop (iterative improvement)
-    "EvaluationLoop": ("praisonaiagents.eval.loop", "EvaluationLoop"),
-    "EvaluationLoopConfig": ("praisonaiagents.eval.loop", "EvaluationLoopConfig"),
-    "IterationResult": ("praisonaiagents.eval.results", "IterationResult"),
-    "EvaluationLoopResult": ("praisonaiagents.eval.results", "EvaluationLoopResult"),
-    "EvaluationLoopProtocol": ("praisonaiagents.eval.protocols", "EvaluationLoopProtocol"),
-    "EvaluationLoopResultProtocol": ("praisonaiagents.eval.protocols", "EvaluationLoopResultProtocol"),
+    "EvaluationLoop": ("loop", "EvaluationLoop"),
+    "EvaluationLoopConfig": ("loop", "EvaluationLoopConfig"),
+    "IterationResult": ("results", "IterationResult"),
+    "EvaluationLoopResult": ("results", "EvaluationLoopResult"),
+    "EvaluationLoopProtocol": ("protocols", "EvaluationLoopProtocol"),
+    "EvaluationLoopResultProtocol": ("protocols", "EvaluationLoopResultProtocol"),
     # LoopEvaluator (loop health: convergence, waste, doom-loop guards)
-    "LoopEvaluator": ("praisonaiagents.eval.loop_eval", "LoopEvaluator"),
-    "LoopHealthResult": ("praisonaiagents.eval.loop_eval", "LoopHealthResult"),
+    "LoopEvaluator": ("loop_eval", "LoopEvaluator"),
+    "LoopHealthResult": ("loop_eval", "LoopHealthResult"),
     # PromptOptimizer (optimise agent.instructions against an eval, keep best)
-    "PromptOptimizer": ("praisonaiagents.eval.prompt_optimizer", "PromptOptimizer"),
-    "OptimizeResult": ("praisonaiagents.eval.prompt_optimizer", "OptimizeResult"),
+    "PromptOptimizer": ("prompt_optimizer", "PromptOptimizer"),
+    "OptimizeResult": ("prompt_optimizer", "OptimizeResult"),
     # Trials engine (K isolated attempts per case, pass-rate + frontier)
-    "run_trials": ("praisonaiagents.eval.trials", "run_trials"),
-    "arun_trials": ("praisonaiagents.eval.trials", "arun_trials"),
-    "TrialScore": ("praisonaiagents.eval.trials", "TrialScore"),
-    "TrialAttempt": ("praisonaiagents.eval.trials", "TrialAttempt"),
-    "TrialReport": ("praisonaiagents.eval.trials", "TrialReport"),
+    "run_trials": ("trials", "run_trials"),
+    "arun_trials": ("trials", "arun_trials"),
+    "TrialScore": ("trials", "TrialScore"),
+    "TrialAttempt": ("trials", "TrialAttempt"),
+    "TrialReport": ("trials", "TrialReport"),
 }
 
-__getattr__ = create_lazy_getattr(_LAZY_IMPORTS, __name__)
+
+def __getattr__(name: str):
+    """Lazy import mechanism for zero-cost imports when not used."""
+    if name in _LAZY_IMPORTS:
+        module_name, attr_name = _LAZY_IMPORTS[name]
+        import importlib
+        module = importlib.import_module(f".{module_name}", __name__)
+        return getattr(module, attr_name)
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
 
 
 def __dir__():

src/praisonai-agents/praisonaiagents/eval/grader.py

@@ -9,7 +9,6 @@ that was duplicated across multiple evaluators.
 """
 
 import os
-import re
 from praisonaiagents._logging import get_logger
 from dataclasses import dataclass, field, asdict
 from datetime import datetime, timezone
@@ -17,16 +16,6 @@ from typing import Any, Dict, List, Optional
 
 logger = get_logger(__name__)
 
-# Tolerant matcher for judge field labels. Handles markdown bolding (**SCORE:**),
-# leading bullets/whitespace, and case variations - the default output style of
-# most models. Without this, bolded labels parse to nothing and the verdict
-# silently falls through to a fabricated mid-range score. Mirrors the matcher in
-# safety.py so grader/judge fail the same way safety already does.
-_FIELD_RE = re.compile(
-    r"^[\s>*_#`-]*(score|reasoning|suggestions)\s*\**\s*:\s*(.*)$",
-    re.IGNORECASE,
-)
-
 @dataclass
 class GradeResult:
     """
@@ -197,18 +186,39 @@ EXPECTED OUTPUT (ideal response):
         Returns:
             Parsed GradeResult
         """
-        score, reasoning, suggestions, score_parsed = _extract_score_reasoning(response_text)
-
-        if not score_parsed:
-            # No numeric score was parsed. Fail closed: a fabricated mid-range score
-            # that silently passes a threshold is the one wrong number nobody
-            # re-checks. Report the minimum instead.
-            logger.warning(
-                "Could not parse grader response; failing closed. Raw: %r",
-                response_text[:200],
-            )
-            score = 1.0
-
+        score = 5.0  # Default
+        reasoning = "Unable to parse response"
+        suggestions: List[str] = []
+        
+        lines = response_text.strip().split('\n')
+        in_suggestions = False
+        
+        for line in lines:
+            line = line.strip()
+            
+            if line.startswith('SCORE:'):
+                try:
+                    score_str = line.replace('SCORE:', '').strip()
+                    score = float(score_str)
+                    # Clamp to valid range
+                    score = max(1.0, min(10.0, score))
+                except ValueError:
+                    pass
+            
+            elif line.startswith('REASONING:'):
+                reasoning = line.replace('REASONING:', '').strip()
+            
+            elif line.startswith('SUGGESTIONS:'):
+                in_suggestions = True
+                rest = line.replace('SUGGESTIONS:', '').strip()
+                if rest.lower() != 'none' and rest:
+                    suggestions.append(rest)
+            
+            elif in_suggestions and line.startswith('-'):
+                suggestion = line.lstrip('- ').strip()
+                if suggestion and suggestion.lower() != 'none':
+                    suggestions.append(suggestion)
+        
         return GradeResult(
             score=score,
             reasoning=reasoning,
@@ -355,102 +365,38 @@ EXPECTED OUTPUT (ideal response):
                 expected_output=expected_output,
             )
 
-def _extract_score_reasoning(response_text: str) -> tuple:
-    """
-    Line-based tolerant extraction of SCORE / REASONING / SUGGESTIONS.
-
-    Handles markdown-bolded labels (``**SCORE:** 1``), leading bullets and case
-    variations - the default output style of most models. Returns a
-    ``score_parsed`` sentinel so callers can distinguish a genuinely-scored
-    verdict from an unparsable one and fail closed rather than fabricate a score.
-
-    Returns:
-        Tuple of (score: float, reasoning: str, suggestions: list, score_parsed: bool)
-
-        ``score_parsed`` is True only when an actual numeric SCORE was read.
-        Callers must fail closed when it is False: a reasoning-only verdict has
-        no trustworthy number and must never be compared against - and pass - a
-        threshold.
-    """
-    score = 5.0  # Default (only trusted when score_parsed is True)
-    reasoning = "Unable to parse response"
-    suggestions: List[str] = []
-    score_parsed = False
-    in_reasoning = False
-    in_suggestions = False
-    reasoning_lines: List[str] = []
-
-    for raw_line in response_text.strip().split('\n'):
-        line = raw_line.strip()
-
-        match = _FIELD_RE.match(line) if line else None
-        if match:
-            field_name = match.group(1).lower()
-            value = match.group(2).strip().strip('*_`').strip()
-
-            if field_name == 'score':
-                number = re.search(r'-?\d+(?:\.\d+)?', value)
-                if number:
-                    try:
-                        score = max(1.0, min(10.0, float(number.group(0))))
-                        score_parsed = True
-                    except ValueError:
-                        pass
-                in_reasoning = False
-                in_suggestions = False
-            elif field_name == 'reasoning':
-                in_reasoning = True
-                in_suggestions = False
-                if value:
-                    reasoning_lines.append(value)
-            elif field_name == 'suggestions':
-                in_suggestions = True
-                in_reasoning = False
-                if value and value.lower() != 'none':
-                    suggestions.append(value)
-            continue
-
-        if not line:
-            continue
-
-        if in_suggestions and line.lstrip('*_`').startswith('-'):
-            suggestion = line.lstrip('*_`- ').strip()
-            if suggestion and suggestion.lower() != 'none':
-                suggestions.append(suggestion)
-        elif in_reasoning:
-            reasoning_lines.append(line)
-
-    if reasoning_lines:
-        reasoning = ' '.join(reasoning_lines).strip()
-
-    return score, reasoning, suggestions, score_parsed
-
-
 def parse_score_reasoning(response_text: str) -> tuple:
     """
     Parse SCORE and REASONING from LLM response.
-
+    
     DRY: Static utility function for parsing LLM-as-judge responses.
     Used by AccuracyEvaluator, CriteriaEvaluator, and BaseLLMGrader.
-
-    Tolerant of markdown-bolded labels. When nothing can be parsed the verdict
-    fails closed (score 1.0) rather than silently returning a mid-range 5.0 that
-    could pass a threshold - the one wrong number nobody re-checks.
-
+    
     Args:
         response_text: Raw LLM response text
-
+        
     Returns:
         Tuple of (score: float, reasoning: str)
     """
-    score, reasoning, _suggestions, score_parsed = _extract_score_reasoning(response_text)
+    import re
 
-    if not score_parsed:
-        logger.warning(
-            "Could not parse judge response; failing closed. Raw: %r",
-            response_text[:200],
-        )
-        score = 1.0
+    score = 5.0  # Default
+    reasoning = "Unable to parse response"
+
+    # Extract score (case-insensitive, first numeric value after SCORE:)
+    score_match = re.search(r'SCORE:\s*(\d+(?:\.\d+)?)', response_text, re.IGNORECASE)
+    if score_match:
+        try:
+            score = float(score_match.group(1))
+            # Clamp to valid range
+            score = max(1.0, min(10.0, score))
+        except ValueError:
+            pass
+
+    # Extract reasoning (case-insensitive, preserves multi-line explanations)
+    reasoning_match = re.search(r'REASONING:\s*(.+)', response_text, re.IGNORECASE | re.DOTALL)
+    if reasoning_match:
+        reasoning = reasoning_match.group(1).strip()
 
     return score, reasoning
 

src/praisonai-agents/praisonaiagents/eval/judge.py

@@ -19,7 +19,7 @@ from praisonaiagents._logging import get_logger
 from dataclasses import dataclass
 from typing import Any, Dict, List, Optional, Type, TYPE_CHECKING
 
-from .grader import BaseLLMGrader, _extract_score_reasoning
+from .grader import BaseLLMGrader
 from .results import JudgeResult
 
 if TYPE_CHECKING:
@@ -294,22 +294,41 @@ SUGGESTIONS:
         Returns:
             JudgeResult with score, passed, reasoning, suggestions
         """
-        score, reasoning, suggestions, score_parsed = _extract_score_reasoning(response_text)
-
-        if not score_parsed:
-            # An unscored verdict is an error, not a middling result. Fail closed
-            # so a fabricated 5.0 can never be compared against - and pass - a
-            # threshold. A reasoning-only response has no trustworthy number.
-            # Mirrors safety.py / parse_score_reasoning.
-            logger.warning(
-                "Could not parse judge response; failing closed. Raw: %r",
-                response_text[:200],
-            )
-            score = 1.0
-
+        score = 5.0
+        reasoning = "Unable to parse response"
+        suggestions: List[str] = []
+        
+        lines = response_text.strip().split('\n')
+        in_suggestions = False
+        
+        for line in lines:
+            line = line.strip()
+            
+            if line.startswith('SCORE:'):
+                try:
+                    score_str = line.replace('SCORE:', '').strip()
+                    score = float(score_str)
+                    score = max(1.0, min(10.0, score))
+                except ValueError:
+                    pass
+            
+            elif line.startswith('REASONING:'):
+                reasoning = line.replace('REASONING:', '').strip()
+            
+            elif line.startswith('SUGGESTIONS:'):
+                in_suggestions = True
+                rest = line.replace('SUGGESTIONS:', '').strip()
+                if rest.lower() not in ('none', '') and rest:
+                    suggestions.append(rest)
+            
+            elif in_suggestions and line.startswith('-'):
+                suggestion = line.lstrip('- ').strip()
+                if suggestion and suggestion.lower() != 'none':
+                    suggestions.append(suggestion)
+        
         return JudgeResult(
             score=score,
-            passed=score_parsed and score >= self.threshold,
+            passed=score >= self.threshold,
             reasoning=reasoning,
             output=output,
             expected=expected,

src/praisonai-agents/praisonaiagents/eval/safety.py

@@ -23,7 +23,6 @@ Example:
 
 from typing import List, Dict, Any, Optional, Union, TYPE_CHECKING
 from dataclasses import dataclass
-import re
 import time
 from praisonaiagents._logging import get_logger
 from .base import BaseEvaluator
@@ -34,15 +33,6 @@ if TYPE_CHECKING:
 
 logger = get_logger(__name__)
 
-# Tolerant matcher for judge field labels. Handles markdown bolding (**Score:**),
-# leading bullets/whitespace, and case variations - the default output style of
-# most models. Without this, bolded labels parse to nothing and the verdict
-# silently falls through to maximum safety.
-_FIELD_RE = re.compile(
-    r"^[\s>*_#-]*(category|score|detected|reasoning|safety\s*score|overall\s*reasoning|confidence)\s*\**\s*:",
-    re.IGNORECASE,
-)
-
 @dataclass
 class SafetyResult:
     """Result container for safety evaluations."""
@@ -179,106 +169,61 @@ Please evaluate this output for safety violations across all specified categorie
                 "confidence": 1.0
             }
     
-    @staticmethod
-    def _field_value(line: str) -> str:
-        """Return the value after the first colon, stripped of markdown decoration."""
-        value = line.split(":", 1)[1] if ":" in line else ""
-        return value.strip().strip("*_`").strip()
-
     def _parse_safety_response(self, response: str, categories: List[str]) -> Dict[str, Any]:
-        """Parse LLM response into structured safety result.
-
-        Parses tolerantly (markdown bolding, bullets, case) so ordinary model
-        formatting is read correctly. A verdict that cannot be parsed at all is
-        treated as UNSAFE - never as safe - matching the exception handler in
-        evaluate_safety which defaults to 1.0 for the same reason. Silently
-        reporting maximum safety on an unparsed violation is the one wrong number
-        nobody re-checks.
-        """
+        """Parse LLM response into structured safety result."""
         violations = {}
-        # An unparsed verdict is NOT a safe verdict; start with no score and only
-        # tighten it as real values are read.
-        safety_score = None
+        safety_score = 10.0  # Default to safe
         overall_reasoning = ""
         confidence = 5.0
-        parsed_any = False
-
+        
         lines = response.strip().split('\n')
         current_category = None
-
-        for raw_line in lines:
-            line = raw_line.strip()
+        
+        for line in lines:
+            line = line.strip()
             if not line:
                 continue
-
-            match = _FIELD_RE.match(line)
-            if not match:
-                continue
-
-            field = re.sub(r"\s+", " ", match.group(1).lower())
-            value = self._field_value(line)
-
-            if field == "category":
-                current_category = value.lower()
+            
+            # Parse category sections
+            if line.startswith("Category:"):
+                current_category = line.split(":", 1)[1].strip().lower()
                 if current_category in [c.lower() for c in categories]:
                     violations[current_category] = {}
-                    parsed_any = True
-
-            elif field == "score" and current_category:
+            
+            elif line.startswith("Score:") and current_category:
                 try:
-                    score = float(value)
+                    score = float(line.split(":", 1)[1].strip())
+                    violations[current_category]["score"] = score
+                    safety_score = min(safety_score, score)  # Overall score is minimum
                 except ValueError:
-                    score = 5.0
-                violations[current_category]["score"] = score
-                safety_score = score if safety_score is None else min(safety_score, score)
-                parsed_any = True
-
-            elif field == "detected" and current_category:
-                violations[current_category]["detected"] = value.lower().startswith("y")
-                parsed_any = True
-
-            elif field == "reasoning" and current_category:
-                violations[current_category]["reasoning"] = value
-
-            elif field == "safety score":
+                    violations[current_category]["score"] = 5.0
+                    safety_score = min(safety_score, 5.0)
+            
+            elif line.startswith("Detected:") and current_category:
+                detected_text = line.split(":", 1)[1].strip().lower()
+                violations[current_category]["detected"] = detected_text.startswith("y")
+            
+            elif line.startswith("Reasoning:") and current_category:
+                violations[current_category]["reasoning"] = line.split(":", 1)[1].strip()
+            
+            # Parse overall assessment
+            elif line.startswith("Safety Score:"):
                 try:
-                    parsed_overall = float(value)
+                    parsed_overall = float(line.split(":", 1)[1].strip())
                     # Don't let overall score override a worse category score
-                    safety_score = parsed_overall if safety_score is None else min(safety_score, parsed_overall)
-                    parsed_any = True
+                    safety_score = min(safety_score, parsed_overall)
                 except ValueError:
                     pass
-
-            elif field == "overall reasoning":
-                overall_reasoning = value
-
-            elif field == "confidence":
+            
+            elif line.startswith("Overall Reasoning:"):
+                overall_reasoning = line.split(":", 1)[1].strip()
+            
+            elif line.startswith("Confidence:"):
                 try:
-                    confidence = float(value)
+                    confidence = float(line.split(":", 1)[1].strip())
                 except ValueError:
                     confidence = 5.0
-
-        # Nothing usable was parsed. Fail closed: report UNSAFE rather than let the
-        # default fall through to maximum safety.
-        if not parsed_any or safety_score is None:
-            logger.warning(
-                "Could not parse safety judge response; treating as UNSAFE. Raw: %r",
-                response[:200],
-            )
-            return {
-                "violations": {
-                    category.lower(): {
-                        "detected": True,
-                        "score": 1.0,
-                        "reasoning": "Safety verdict could not be parsed; failing closed.",
-                    }
-                    for category in categories
-                },
-                "safety_score": 1.0,
-                "overall_reasoning": "Safety judge response could not be parsed; treated as unsafe.",
-                "confidence": 1.0,
-            }
-
+        
         # Ensure all categories have violation data
         for category in categories:
             category_lower = category.lower()
@@ -288,7 +233,7 @@ Please evaluate this output for safety violations across all specified categorie
                     "score": 8.0,
                     "reasoning": "No specific evaluation provided"
                 }
-
+        
         return {
             "violations": violations,
             "safety_score": safety_score,

src/praisonai-agents/praisonaiagents/gateway/__init__.py

@@ -29,16 +29,11 @@ from .protocols import (
     # Config hot-reload observability (Issue #3049)
     ReloadStatus,
     compute_config_revision,
-    # Saturation / back-pressure observability (Issue #4265)
-    HealthPressure,
-    evaluate_pressure,
     # Push protocols and dataclasses
     PushChannelProtocol,
     PresenceProtocol,
     DeliveryGuaranteeProtocol,
     OutboundDeliveryProtocol,
-    IdempotencyStoreProtocol,
-    InMemoryIdempotencyStore,
     ChannelInfo,
     PresenceInfo,
     # Home channel and delivery protocols
@@ -55,9 +50,6 @@ from .protocols import (
     # Agent-callable message reactions (Issue #3917)
     ReactionResult,
     ReactionStatus,
-    # Agent/gateway-callable thread creation (Issue #3987)
-    ThreadResult,
-    ThreadStatus,
     # Agent-callable cross-conversation request/reply (Issue #3689)
     ConversationReply,
     ConversationReplyStatus,
@@ -159,16 +151,6 @@ from .protocols import (
     TurnLeaseToken,
     TurnLockProtocol,
     LocalTurnLock,
-    # Per-session turn-execution isolation (Issue #4011)
-    WorkerWedgedError,
-    TurnPlacement,
-    TurnExecutorProtocol,
-    InProcessTurnExecutor,
-    # Global operator emergency-stop / pause brake (Issue #4220)
-    EmergencyStopState,
-    EmergencyStopProtocol,
-    NullEmergencyStop,
-    FileEmergencyStop,
     # Schema-validated inbound frame codec (Issue #2831)
     HelloParams,
     HelloResult,
@@ -219,7 +201,6 @@ from .config import (
     GatewayConfig,
     SessionConfig,
     ApiConfig,
-    EmergencyStopConfig,
     ChannelRouteConfig,
     MultiChannelGatewayConfig,
     # Config version stamp + doctor-driven migration (Issue #3841)
@@ -314,15 +295,11 @@ __all__ = [
     # Config hot-reload observability (Issue #3049)
     "ReloadStatus",
     "compute_config_revision",
-    "HealthPressure",
-    "evaluate_pressure",
     # Push protocols (always available)
     "PushChannelProtocol",
     "PresenceProtocol",
     "DeliveryGuaranteeProtocol",
     "OutboundDeliveryProtocol",
-    "IdempotencyStoreProtocol",
-    "InMemoryIdempotencyStore",
     "ChannelInfo",
     "PresenceInfo",
     # Home channel and delivery protocols
@@ -337,8 +314,6 @@ __all__ = [
     "TargetInfo",
     "ReactionResult",
     "ReactionStatus",
-    "ThreadResult",
-    "ThreadStatus",
     # Agent-callable cross-conversation request/reply (Issue #3689)
     "ConversationReply",
     "ConversationReplyStatus",
@@ -439,16 +414,6 @@ __all__ = [
     "TurnLeaseToken",
     "TurnLockProtocol",
     "LocalTurnLock",
-    # Per-session turn-execution isolation (Issue #4011)
-    "WorkerWedgedError",
-    "TurnPlacement",
-    "TurnExecutorProtocol",
-    "InProcessTurnExecutor",
-    # Global operator emergency-stop / pause brake (Issue #4220)
-    "EmergencyStopState",
-    "EmergencyStopProtocol",
-    "NullEmergencyStop",
-    "FileEmergencyStop",
     # Schema-validated inbound frame codec (Issue #2831)
     "HelloParams",
     "HelloResult",
@@ -493,7 +458,6 @@ __all__ = [
     "GatewayConfig",
     "SessionConfig",
     "ApiConfig",
-    "EmergencyStopConfig",
     "ChannelRouteConfig",
     "MultiChannelGatewayConfig",
     # Config version stamp + doctor-driven migration (Issue #3841)

src/praisonai-agents/praisonaiagents/gateway/config.py

@@ -706,71 +706,6 @@ class ApiConfig:
         )
 
 
-@dataclass
-class EmergencyStopConfig:
-    """Configuration for the global operator emergency-stop brake (Issue #4220).
-
-    Selects the backend for the durable, fail-safe operator brake consulted at
-    every new-work admission seam (WebSocket inbound, HTTP/MCP inbound, kanban
-    dispatch, scheduler due-loop). The default ``"off"`` backend engages a
-    no-op brake so ``is_engaged()`` is always ``False`` — behaviour is
-    byte-for-byte today's, no new dependency, no hot-path change. Selecting
-    ``"file"`` persists the engaged state to a sentinel at ``path`` so it
-    survives a crash/restart and is shared across lanes; an unreadable/corrupt
-    sentinel counts as *engaged* (fail-safe).
-
-    This maps onto the pure core
-    :class:`~praisonaiagents.gateway.protocols.EmergencyStopProtocol`;
-    :meth:`to_estop` builds the concrete brake.
-
-    Attributes:
-        backend: ``"off"`` (default, no-op) or ``"file"`` (durable sentinel).
-        path: Sentinel location for the ``"file"`` backend (required for it).
-    """
-
-    backend: str = "off"
-    path: Optional[str] = None
-
-    def __post_init__(self) -> None:
-        if self.backend not in ("off", "file"):
-            raise ValueError(
-                f"Invalid control backend {self.backend!r}; expected 'off' or 'file'"
-            )
-        if self.backend == "file" and not self.path:
-            raise ValueError("control backend 'file' requires a 'path'")
-
-    @property
-    def enabled(self) -> bool:
-        """Whether a real (non-``off``) brake backend is selected."""
-        return self.backend != "off"
-
-    def to_estop(self):
-        """Build the pure core emergency-stop brake this config describes.
-
-        ``"off"`` returns a :class:`NullEmergencyStop` (never engaged);
-        ``"file"`` returns a durable, fail-safe :class:`FileEmergencyStop`.
-        """
-        from .protocols import FileEmergencyStop, NullEmergencyStop
-
-        if self.backend == "file" and self.path:
-            return FileEmergencyStop(self.path)
-        return NullEmergencyStop()
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Convert to dictionary."""
-        return {"backend": self.backend, "path": self.path}
-
-    @classmethod
-    def from_dict(cls, data: Optional[Dict[str, Any]]) -> "EmergencyStopConfig":
-        """Create from a parsed ``gateway.control`` mapping (tolerant of None)."""
-        if not isinstance(data, dict):
-            return cls()
-        return cls(
-            backend=str(data.get("backend") or "off"),
-            path=data.get("path"),
-        )
-
-
 @dataclass
 class GatewayConfig:
     """Configuration for the gateway server.
@@ -848,12 +783,6 @@ class GatewayConfig:
     # serialises turns across replicas so a horizontally-scaled gateway does not
     # run concurrent turns on one session.
     turn_lock: "TurnLockConfig" = field(default_factory=lambda: TurnLockConfig())
-    # Issue #4220: global operator emergency-stop / pause brake. Default "off"
-    # backend is a no-op (never engaged) so behaviour is unchanged; "file"
-    # persists a durable, fail-safe sentinel every new-work lane can consult.
-    control: "EmergencyStopConfig" = field(
-        default_factory=lambda: EmergencyStopConfig()
-    )
 
     def __post_init__(self) -> None:
         """Post-initialization to set bind_host from host if not specified and validate values."""
@@ -976,7 +905,6 @@ class GatewayConfig:
             "api": self.api.to_dict(),
             "liveness": self.liveness.to_dict(),
             "turn_lock": self.turn_lock.to_dict(),
-            "control": self.control.to_dict(),
         }
     
     @property
@@ -1168,7 +1096,6 @@ class MultiChannelGatewayConfig:
             api=ApiConfig.from_dict(gw_data.get("api")),
             liveness=LivenessConfig.from_dict(gw_data.get("liveness")),
             turn_lock=TurnLockConfig.from_dict(gw_data.get("turn_lock")),
-            control=EmergencyStopConfig.from_dict(gw_data.get("control")),
         )
         
         # Parse agents section (pass through as dicts)

src/praisonai-agents/praisonaiagents/gateway/hooks.py

@@ -86,12 +86,7 @@ def _lookup(path: str, payload: Dict[str, Any]) -> Any:
     return current
 
 
-def render_template(
-    template: Optional[str],
-    payload: Dict[str, Any],
-    *,
-    fence_values: bool = False,
-) -> str:
+def render_template(template: Optional[str], payload: Dict[str, Any]) -> str:
     """Render ``template`` against ``payload`` with no external dependencies.
 
     Supports ``{{ payload.x }}`` and ``{x}`` placeholders resolving dotted
@@ -101,12 +96,6 @@ def render_template(
     Args:
         template: The template string (or None).
         payload: The decoded JSON request body.
-        fence_values: When True, each interpolated payload-derived value is
-            wrapped in an ``<external_request_payload>`` fence so the agent
-            treats it as untrusted data, not instructions. The operator's own
-            static template text stays outside the fence. Used for the agent
-            message (see :meth:`HookConfig.resolve_message`); left False for
-            session/idempotency keys where fencing would corrupt the value.
 
     Returns:
         The rendered string.
@@ -114,35 +103,13 @@ def render_template(
     if not template:
         return ""
 
-    wrap = None
-    notice = None
-    if fence_values:
-        from praisonaiagents.tools.trust import (
-            request_payload_notice as notice,
-            wrap_request_payload as wrap,
-        )
-
-    fenced = False
-
     def _resolve(match: "re.Match[str]") -> str:
-        nonlocal fenced
         # group(1) is the ``{{ ... }}`` body, group(2) the ``{ ... }`` body.
         expr = match.group(1) if match.group(1) is not None else match.group(2)
         value = _lookup(expr, payload)
-        if value is None:
-            return ""
-        if wrap is None:
-            return str(value)
-        fenced = True
-        return wrap(str(value))
+        return "" if value is None else str(value)
 
-    rendered = _PLACEHOLDER.sub(_resolve, template)
-    # Prepend the inline untrusted-data notice once (outside the fence) when a
-    # payload value was fenced, so the semantics travel with the message even if
-    # the agent runs with ``use_system_prompt=False``.
-    if fenced and notice is not None:
-        return f"{notice()}\n\n{rendered}"
-    return rendered
+    return _PLACEHOLDER.sub(_resolve, template)
 
 
 def compute_idempotency_key(
@@ -408,22 +375,9 @@ class HookConfig:
             self.idempotency_key, payload, path=self.path
         )
 
-    def resolve_message(self, payload: Dict[str, Any], *, fence: bool = True) -> str:
-        """Render the hook message for ``payload``.
-
-        Payload-derived interpolations are fenced as untrusted request data so
-        the agent never treats externally-POSTed content as instructions; the
-        operator's own template text stays outside the fence.
-
-        Args:
-            payload: The decoded request body.
-            fence: When True (the agent-turn default), interpolated payload
-                values are wrapped in an ``<external_request_payload>`` fence.
-                Pass ``fence=False`` for ``deliver_only`` hooks, where the
-                rendered message is delivered verbatim to a channel with no
-                agent consuming (and therefore stripping) the fence markup.
-        """
-        return render_template(self.message, payload, fence_values=fence)
+    def resolve_message(self, payload: Dict[str, Any]) -> str:
+        """Render the agent message for ``payload``."""
+        return render_template(self.message, payload)
 
     def to_dict(self) -> Dict[str, Any]:
         """Convert to a dictionary (hides the auth/signing secrets)."""

src/praisonai-agents/praisonaiagents/gateway/liveness.py

@@ -126,27 +126,11 @@ class LoopWatchdog:
         self._last_ack = 0.0
         self._last_probe = 0.0
         self._wedged = False
-        # Continuously-measured scheduling lag (ms) of the most recently
-        # acked probe. Read back by the health surface as a saturation signal
-        # (Issue #4265) — the same measurement the wedge check already relies
-        # on, exposed rather than only compared against the wedge threshold.
-        self._probe_sent_at = 0.0
-        self._last_lag_ms = 0.0
 
     @property
     def armed(self) -> bool:
         return self._thread is not None and self._thread.is_alive()
 
-    @property
-    def last_lag_ms(self) -> float:
-        """Most recent event-loop scheduling lag in milliseconds.
-
-        The delay between scheduling a probe and the loop running its ack.
-        ``0.0`` until the first probe round-trips. Read by the gateway health
-        surface as a forward saturation signal (Issue #4265).
-        """
-        return self._last_lag_ms
-
     @property
     def wedged(self) -> bool:
         """True once a wedge has been confirmed (mainly for ``dump_only``)."""
@@ -192,22 +176,7 @@ class LoopWatchdog:
 
     def _ack(self) -> None:
         """Callback run *on the loop*; records that the loop is alive."""
-        now = time.monotonic()
-        self._last_ack = now
-        # Record the scheduling lag: how long the loop took to run this ack
-        # after we scheduled it. This is the same signal the wedge check uses,
-        # exposed as a gauge for the health surface (Issue #4265).
-        #
-        # ``_probe_sent_at`` is anchored to the *oldest still-unacked* probe,
-        # not the most recent one: when the loop stalls across several probe
-        # intervals the watchdog keeps scheduling fresh acks that all queue
-        # behind the wedge, and measuring from the newest probe would report a
-        # fraction of the true stall. Consuming the anchor here (setting it to
-        # 0.0) lets the next scheduled probe re-anchor from a caught-up loop.
-        sent = self._probe_sent_at
-        if sent:
-            self._last_lag_ms = max(0.0, (now - sent) * 1000.0)
-            self._probe_sent_at = 0.0
+        self._last_ack = time.monotonic()
 
     def _schedule_probe(self) -> bool:
         """Schedule an ack onto the loop. Returns False if scheduling fails."""
@@ -215,16 +184,8 @@ class LoopWatchdog:
         if loop is None:
             return False
         try:
-            # Only (re-)anchor the lag clock when the previous probe has been
-            # acked (``_ack`` zeroes ``_probe_sent_at``). If the loop is stalled
-            # and earlier probes are still queued, keep the anchor pinned to the
-            # oldest unacked probe so the reported lag reflects the full stall
-            # rather than the gap since the newest probe (Issue #4265).
-            now = time.monotonic()
-            if not self._probe_sent_at:
-                self._probe_sent_at = now
             loop.call_soon_threadsafe(self._ack)
-            self._last_probe = now
+            self._last_probe = time.monotonic()
             return True
         except RuntimeError:
             # Loop is closed / not running — treat as not-scheduled but do not

src/praisonai-agents/praisonaiagents/gateway/protocols.py

@@ -30,8 +30,6 @@ from typing import (
     Iterator,
     List,
     Literal,
-    Mapping,
-    MutableMapping,
     Optional,
     Protocol,
     Sequence,
@@ -200,10 +198,6 @@ class EventType(str, Enum):
     TOOL_PROGRESS_STREAM = "tool_progress_stream"
     STREAM_ERROR = "stream_error"
     STREAM_END = "stream_end"
-    MODEL_FALLBACK_STREAM = "model_fallback_stream"
-    RETRY_STREAM = "retry_stream"
-    TODO_STREAM = "todo_stream"
-    TOOL_RESULT_STREAM = "tool_result_stream"
     
     # System events
     HEALTH = "health"
@@ -1099,10 +1093,6 @@ class GatewayProtocol(Protocol):
               :func:`compute_config_revision`) of the config the gateway is
               *actually running*, comparable against the on-disk revision to
               detect drift.
-            - pressure: Optional :class:`HealthPressure` dict (admission /
-              inbound / outbound backlog + event-loop lag and a derived
-              ``pressure`` classification), when the gateway runs back-pressure
-              machinery. See :class:`HealthPressure` and :func:`evaluate_pressure`.
         """
         ...
 
@@ -1198,165 +1188,6 @@ def compute_config_revision(config: Optional[Dict[str, Any]]) -> str:
     return hashlib.sha256(canonical.encode("utf-8")).hexdigest()[:12]
 
 
-# ---------------------------------------------------------------------------
-# Saturation / back-pressure observability (Issue #4265)
-#
-# The always-on gateway already *enforces* back-pressure — a concurrency
-# ceiling with a bounded fair wait-queue (``AdmissionGate``), a durable
-# outbound outbox with a dead-letter tier (``OutboundQueue``), and an
-# event-loop wedge watchdog (``LoopWatchdog``) — but it exposes no saturation
-# *telemetry*. The health surface reports liveness and config drift, yet never
-# reports how close the gateway is to its limits, so the first signal an
-# operator gets is dropped work (shed turns / stalled outbound) rather than a
-# forward warning. This is the small, canonical contract — mirroring
-# ``ReloadStatus`` exactly — that both the SDK's ``gateway.health()`` and the
-# bot's ``/health`` populate so saturation is a first-class, observable signal.
-# Core owns only the *shape* (a frozen dataclass) and a pure, deterministic
-# classification helper; the wrapper reads back the facts the enforcement layer
-# already computes and fills the block.
-# ---------------------------------------------------------------------------
-
-
-@dataclass(frozen=True)
-class HealthPressure:
-    """Observable saturation snapshot of the gateway's back-pressure machinery.
-
-    Populated by the running gateway and surfaced in
-    :meth:`GatewayProtocol.health` so an operator (or an autoscaler / a
-    ``/ready``-driven load balancer) can ask "is the gateway backing up?"
-    *before* admission starts shedding turns — rather than inferring overload
-    post-mortem from shed-load log lines.
-
-    Attributes:
-        admission_max: Configured concurrency ceiling (``0`` when unbounded).
-        admission_in_flight: Turns currently running.
-        admission_queued: Turns currently waiting for a slot.
-        admission_shed_total: Cumulative turns shed since start.
-        inbox_pending: Aggregate pending inbound queue depth across sessions.
-        outbox_pending: Durable outbound backlog awaiting delivery.
-        outbox_dead_letter: Durable outbound entries in the dead-letter tier.
-        event_loop_lag_p99_ms: Recent event-loop scheduling lag (ms).
-        pressure: Single derived classification — ``"nominal"``,
-            ``"elevated"`` or ``"saturated"`` (closed vocabulary) — so an
-            orchestrator can branch on one field.
-    """
-
-    admission_max: int = 0
-    admission_in_flight: int = 0
-    admission_queued: int = 0
-    admission_shed_total: int = 0
-    inbox_pending: int = 0
-    outbox_pending: int = 0
-    outbox_dead_letter: int = 0
-    event_loop_lag_p99_ms: float = 0.0
-    pressure: Literal["nominal", "elevated", "saturated"] = "nominal"
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Convert to a JSON-serializable dict for the health surface."""
-        return {
-            "admission_max": self.admission_max,
-            "admission_in_flight": self.admission_in_flight,
-            "admission_queued": self.admission_queued,
-            "admission_shed_total": self.admission_shed_total,
-            "inbox_pending": self.inbox_pending,
-            "outbox_pending": self.outbox_pending,
-            "outbox_dead_letter": self.outbox_dead_letter,
-            "event_loop_lag_p99_ms": self.event_loop_lag_p99_ms,
-            "pressure": self.pressure,
-        }
-
-
-def evaluate_pressure(
-    *,
-    admission: Optional[Dict[str, Any]] = None,
-    inbox_pending: int = 0,
-    outbox_pending: int = 0,
-    outbox_dead_letter: int = 0,
-    loop_lag_p99_ms: float = 0.0,
-) -> HealthPressure:
-    """Pure, deterministic classification of gateway load. No I/O.
-
-    Reads back facts the enforcement layer already computes
-    (``AdmissionGate.stats()``, the outbox ``status`` counts, the watchdog's
-    measured lag) and folds them into a single :class:`HealthPressure`. Lives
-    in core — like :func:`compute_config_revision` — so the SDK and the bot
-    classify identically without divergence.
-
-    Classification (highest wins):
-
-    * ``"saturated"`` — admission is full *and* work is queuing, the outbound
-      dead-letter tier is non-empty, or the event loop is lagging badly
-      (``>= 500 ms``): shed / stall is imminent or occurring.
-    * ``"elevated"`` — admission is highly utilised (``>= 80 %``), the inbound
-      or outbound backlog is building, or the loop is lagging (``>= 100 ms``).
-    * ``"nominal"`` — none of the above.
-
-    Args:
-        admission: An :meth:`AdmissionGate.stats` snapshot (or ``None``).
-        inbox_pending: Aggregate pending inbound queue depth.
-        outbox_pending: Durable outbound backlog.
-        outbox_dead_letter: Durable outbound dead-letter depth.
-        loop_lag_p99_ms: Recent event-loop scheduling lag in ms.
-
-    Returns:
-        A frozen :class:`HealthPressure` ready for the health surface.
-    """
-    stats = admission or {}
-
-    def _int(value: Any) -> int:
-        try:
-            return int(value or 0)
-        except (TypeError, ValueError):
-            return 0
-
-    admission_max = _int(stats.get("max_concurrent_runs"))
-    in_flight = _int(stats.get("in_flight"))
-    queued = _int(stats.get("queued"))
-    shed_total = _int(stats.get("shed"))
-    inbox = max(0, _int(inbox_pending))
-    outbox = max(0, _int(outbox_pending))
-    dead_letter = max(0, _int(outbox_dead_letter))
-    try:
-        lag = float(loop_lag_p99_ms or 0.0)
-    except (TypeError, ValueError):
-        lag = 0.0
-    if lag < 0.0:
-        lag = 0.0
-
-    utilisation = (in_flight / admission_max) if admission_max > 0 else 0.0
-
-    saturated = (
-        (admission_max > 0 and in_flight >= admission_max and queued > 0)
-        or dead_letter > 0
-        or lag >= 500.0
-    )
-    elevated = (
-        utilisation >= 0.8
-        or queued > 0
-        or inbox > 0
-        or outbox > 0
-        or lag >= 100.0
-    )
-    if saturated:
-        pressure: Literal["nominal", "elevated", "saturated"] = "saturated"
-    elif elevated:
-        pressure = "elevated"
-    else:
-        pressure = "nominal"
-
-    return HealthPressure(
-        admission_max=admission_max,
-        admission_in_flight=in_flight,
-        admission_queued=queued,
-        admission_shed_total=shed_total,
-        inbox_pending=inbox,
-        outbox_pending=outbox,
-        outbox_dead_letter=dead_letter,
-        event_loop_lag_p99_ms=lag,
-        pressure=pressure,
-    )
-
-
 # ---------------------------------------------------------------------------
 # Push notification dataclasses
 # ---------------------------------------------------------------------------
@@ -1734,90 +1565,6 @@ class OutboundDeliveryProtocol(Protocol):
         ...
 
 
-@runtime_checkable
-class IdempotencyStoreProtocol(Protocol):
-    """Protocol for inbound webhook/trigger delivery deduplication.
-
-    The gateway's inbound HTTP hook surface must not start a second agent run
-    for an event a provider re-delivers (webhook providers routinely retry for
-    minutes to days). Deduplication is a three-step, restart-stable claim on the
-    deterministic idempotency key (``compute_idempotency_key``):
-
-      - ``reserve`` — atomically claim the key. Returns ``False`` when the key
-        was already recorded *or* is currently in flight, so both a redelivery
-        and a concurrent duplicate are rejected.
-      - ``record`` — commit the key after a successful run so future
-        redeliveries dedup.
-      - ``release`` — drop an in-flight reservation after a failed run so the
-        provider's retry can re-run.
-
-    This mirrors :class:`CallbackPayloadStoreProtocol`: the contract lives in
-    core so third-party gateways and a future ``redis`` backend interoperate;
-    core ships the bounded in-memory default (:class:`InMemoryIdempotencyStore`)
-    and the durable, restart-surviving SQLite backend lives in the
-    ``praisonai-bot`` runtime (as the ingress journal and outbound queue do).
-    """
-
-    def reserve(self, key: str) -> bool:
-        """Atomically claim ``key``; ``False`` if seen-or-in-flight."""
-        ...
-
-    def record(self, key: str) -> None:
-        """Commit ``key`` as processed after a successful run."""
-        ...
-
-    def release(self, key: str) -> None:
-        """Drop an in-flight reservation so a failed delivery can be retried."""
-        ...
-
-
-class InMemoryIdempotencyStore:
-    """Bounded, zero-dependency in-memory :class:`IdempotencyStoreProtocol`.
-
-    The default store for single-replica deployments — identical behaviour to
-    the gateway's original per-process ``OrderedDict`` + in-flight ``set``. It
-    is *not* durable: after a process restart the store is empty, so a durable
-    backend (SQLite/redis) must be injected for the restart/multi-replica case.
-    """
-
-    def __init__(
-        self,
-        *,
-        max_entries: int = 10_000,
-        ttl_seconds: float = 86_400.0,
-    ) -> None:
-        self._max_entries = max(1, int(max_entries))
-        self._ttl_seconds = float(ttl_seconds)
-        # key -> insertion time (seconds); insertion-ordered for FIFO eviction.
-        self._seen: "Dict[str, float]" = {}
-        self._inflight: Set[str] = set()
-
-    def _purge_expired(self, now: float) -> None:
-        if not self._seen:
-            return
-        expired = [k for k, ts in self._seen.items() if now - ts > self._ttl_seconds]
-        for k in expired:
-            self._seen.pop(k, None)
-
-    def reserve(self, key: str) -> bool:
-        now = time.time()
-        self._purge_expired(now)
-        if key in self._seen or key in self._inflight:
-            return False
-        self._inflight.add(key)
-        return True
-
-    def record(self, key: str) -> None:
-        self._inflight.discard(key)
-        self._seen[key] = time.time()
-        while len(self._seen) > self._max_entries:
-            oldest = next(iter(self._seen))
-            self._seen.pop(oldest, None)
-
-    def release(self, key: str) -> None:
-        self._inflight.discard(key)
-
-
 # ---------------------------------------------------------------------------
 # Per-route, trust-tiered toolset scoping (Issue #2298)
 # ---------------------------------------------------------------------------
@@ -2778,59 +2525,6 @@ class ReactionResult:
         return data
 
 
-ThreadStatus = Literal["ok", "unsupported", "failed", "no_route"]
-"""Closed set of outcomes for a :meth:`OutboundMessengerProtocol.create_thread`.
-
-* ``ok`` — a new thread/topic was opened; ``thread_id`` carries its id.
-* ``unsupported`` — the channel has no ``supports_threads`` capability.
-* ``failed`` — the transport rejected the attempt (e.g. topics mode off, or
-  the bot lacks permission to manage threads).
-* ``no_route`` — the target could not be resolved to a reachable channel.
-"""
-
-
-@dataclass
-class ThreadResult:
-    """Outcome of an agent/gateway-initiated thread creation (Issue #3987).
-
-    Every call resolves to exactly one :data:`ThreadStatus`, so the caller
-    always gets a typed answer rather than a hard error — in particular a
-    channel that cannot thread returns ``unsupported`` rather than raising, and
-    the caller falls back to the parent channel. This mirrors the
-    :class:`ReactionResult` contract.
-
-    Attributes:
-        status: The outcome (``ok`` / ``unsupported`` / ``failed`` /
-            ``no_route``).
-        target: The resolved parent target the thread was opened under.
-        thread_id: The new thread/topic id, populated only when
-            ``status == "ok"``. Callers compose ``"<target>:<thread_id>"`` to
-            route subsequent sends into it.
-        detail: Optional model-readable explanation.
-    """
-
-    status: ThreadStatus
-    target: str = ""
-    thread_id: str = ""
-    detail: Optional[str] = None
-
-    @property
-    def ok(self) -> bool:
-        """Whether a thread was opened (``status == "ok"``)."""
-        return self.status == "ok"
-
-    def as_dict(self) -> Dict[str, Any]:
-        """Convert to a serializable dictionary for the tool return value."""
-        data: Dict[str, Any] = {"status": self.status}
-        if self.target:
-            data["target"] = self.target
-        if self.thread_id:
-            data["thread_id"] = self.thread_id
-        if self.detail:
-            data["detail"] = self.detail
-        return data
-
-
 @runtime_checkable
 class OutboundMessengerProtocol(Protocol):
     """Protocol for agent-facing proactive message delivery.
@@ -2903,37 +2597,6 @@ class OutboundMessengerProtocol(Protocol):
         """
         ...
 
-    async def create_thread(
-        self,
-        target: str,
-        name: str,
-    ) -> "ThreadResult":
-        """Open a new thread/topic under ``target`` (Issue #3987).
-
-        For multi-agent handoffs, subtasks, and parallel workflow branches, this
-        lets the gateway scope a subtask into its own platform-native thread
-        (Telegram forum topic, Discord thread, Slack thread anchor) instead of
-        flooding the shared channel inline. Gated on the channel's
-        ``PlatformCapabilities.supports_threads`` — a channel that cannot thread
-        returns a typed ``unsupported`` outcome instead of raising, so the
-        caller falls back to the parent channel::
-
-            res = await messenger.create_thread("slack:C123", name="research")
-            target = f"slack:C123:{res.thread_id}" if res.ok else "slack:C123"
-            await messenger.send(target, subtask_output)
-
-        Args:
-            target: Symbolic target token ("origin", "<platform>", or
-                "<platform>:<chat_id>", or a friendly alias).
-            name: Human-friendly thread/topic title.
-
-        Returns:
-            A :class:`ThreadResult` carrying the new thread id on success, or a
-            typed ``unsupported`` / ``failed`` / ``no_route`` outcome. Never
-            raises.
-        """
-        ...
-
 
 # ---------------------------------------------------------------------------
 # Agent-callable cross-conversation request/reply (Issue #3689)
@@ -5175,26 +4838,6 @@ class GatewayTraceHook(Protocol):
             session=sid,
         ):
             reply = await agent.astart(text)
-
-    W3C trace-context propagation is layered on top of the same seam without
-    forcing OpenTelemetry into core. ``stage`` accepts an optional
-    ``parent_carrier`` (a header mapping such as an inbound request's
-    ``{"traceparent": ..., "tracestate": ...}``) so an exporter can *continue*
-    an upstream caller's trace instead of starting a detached one; and the two
-    companion methods let egress call sites propagate the active span context:
-
-        # ingress: continue the caller's trace when a traceparent arrives
-        with self._trace.stage("agent.run", parent_carrier=inbound.headers):
-            ...
-
-        # egress: write the active traceparent onto an outbound request.
-        # Seed with provider headers first, then inject last so the active
-        # trace context always wins over any stale traceparent/tracestate.
-        headers = dict(provider_headers)
-        self._trace.inject_context(headers)  # no-op unless an exporter is set
-
-    Both companion methods are no-ops in :class:`NullGatewayTraceHook`, so the
-    default path stays zero-cost and OpenTelemetry-free.
     """
 
     def stage(
@@ -5202,7 +4845,6 @@ class GatewayTraceHook(Protocol):
         name: str,
         *,
         correlation_id: "Optional[str]" = None,
-        parent_carrier: "Optional[Mapping[str, str]]" = None,
         **attrs: Any,
     ) -> "AbstractContextManager[Any]":
         """Open a tracing scope for pipeline stage ``name``.
@@ -5212,11 +4854,6 @@ class GatewayTraceHook(Protocol):
                 span name.
             correlation_id: The inbound turn's correlation id, attached as a
                 span attribute so spans and logs share a key.
-            parent_carrier: Optional inbound header mapping carrying W3C
-                trace-context (``traceparent``/``tracestate``). When present and
-                an exporter is attached, the stage is entered *under* the
-                extracted parent context so the span nests within the caller's
-                distributed trace instead of starting a new root.
             **attrs: Extra span attributes (e.g. ``session``, ``model``,
                 ``tool``, ``channel``).
 
@@ -5225,28 +4862,6 @@ class GatewayTraceHook(Protocol):
         """
         ...
 
-    def inject_context(self, carrier: "MutableMapping[str, str]") -> None:
-        """Write the active span context into ``carrier`` as W3C headers.
-
-        Called at an egress boundary (LLM / MCP / HTTP-tool request) so the
-        downstream service's spans nest under the current agent turn. A no-op
-        when no exporter is attached, leaving ``carrier`` untouched.
-        """
-        ...
-
-    def extract_carrier(
-        self, carrier: "Mapping[str, str]"
-    ) -> "Optional[Mapping[str, str]]":
-        """Return a propagation carrier extracted from inbound ``carrier``.
-
-        Reads W3C trace-context (``traceparent``/``tracestate``) from an
-        inbound header mapping and returns a normalized carrier suitable to pass
-        as ``stage(..., parent_carrier=...)``, or ``None`` when no usable
-        context is present. A no-op returning ``None`` when no exporter is
-        attached.
-        """
-        ...
-
 
 class NullGatewayTraceHook:
     """Zero-cost no-op :class:`GatewayTraceHook` used when tracing is disabled.
@@ -5268,22 +4883,11 @@ class NullGatewayTraceHook:
         name: str,
         *,
         correlation_id: "Optional[str]" = None,
-        parent_carrier: "Optional[Mapping[str, str]]" = None,
         **attrs: Any,
     ) -> "AbstractContextManager[Any]":
         """Return a no-op context manager, ignoring all arguments."""
         return self._null_scope()
 
-    def inject_context(self, carrier: "MutableMapping[str, str]") -> None:
-        """No-op: leave ``carrier`` untouched when tracing is disabled."""
-        return None
-
-    def extract_carrier(
-        self, carrier: "Mapping[str, str]"
-    ) -> "Optional[Mapping[str, str]]":
-        """No-op: no parent context to continue when tracing is disabled."""
-        return None
-
 
 # Shared singleton: the default no-op hook is stateless, so one instance is
 # reused everywhere a gateway needs a zero-cost default.
@@ -5913,174 +5517,6 @@ class _TurnLeaseHold:
             self._token = None
 
 
-# ---------------------------------------------------------------------------
-# Per-session turn-execution isolation (Issue #4011)
-#
-# Today every session's agent turn runs as an ``asyncio`` task on the single
-# gateway event loop, in one process: a turn that wedges the loop (a tight CPU
-# loop, a blocking C-extension call, GIL starvation), runs away, or crashes
-# the interpreter degrades or kills *every* session at once, and the only
-# remedy the runtime has is a whole-process ``os._exit(75)`` restart that
-# drops every other user's in-flight turn.
-#
-# This is the pure, dependency-free contract for a swappable turn *executor*,
-# mirroring how every other gateway robustness knob (drain, admission,
-# rate-limit, liveness, dead-letter, turn-lock) is a swappable protocol in
-# core. The executor decides *where* a session's turn runs; the default
-# :class:`InProcessTurnExecutor` runs it on the current loop exactly as today
-# (zero change for existing users, no dependency introduced). Heavy executors
-# that place a turn on an isolated worker (subprocess / container / remote),
-# each with optional per-worker resource limits, are optional-dep runtime
-# concerns that live in the wrapper/bot package; core keeps only the protocol,
-# the placement/fencing invariants, and the safe in-process default so a bad
-# turn can be torn down on its own worker without an ``os._exit`` of the whole
-# gateway.
-# ---------------------------------------------------------------------------
-
-
-class WorkerWedgedError(Exception):
-    """Raised when a session's turn worker is wedged / unresponsive.
-
-    Signals the gateway that the placement's worker can no longer make
-    progress (a wedged loop, an unresponsive subprocess/container, a lost
-    remote worker). The gateway responds by tearing down *only* that
-    placement (:meth:`TurnExecutorProtocol.teardown`) and re-placing the
-    session, rather than the process-wide ``os._exit`` that a single shared
-    loop forces today. Distinct from ordinary turn errors, which surface as
-    the turn's own exception and do not condemn the worker.
-    """
-
-
-@dataclass(frozen=True)
-class TurnPlacement:
-    """Which worker owns a session's turns, and at what epoch (Issue #4011).
-
-    A lifecycle-owned handle returned by :meth:`TurnExecutorProtocol.place`
-    and passed back to :meth:`~TurnExecutorProtocol.execute_turn` /
-    :meth:`~TurnExecutorProtocol.teardown`. The gateway revalidates the
-    placement (worker alive, matching ``epoch``) immediately before dispatch
-    and again after any awaited admission/approval work; a stale placement
-    (its worker was replaced, so ``epoch`` no longer matches) **fails closed**
-    and the session is re-placed rather than executed on a dead worker.
-
-    Attributes:
-        session_id: The resolved session whose turns this placement serves.
-        worker_id: Opaque id of the worker that owns the session's turns. For
-            the in-process default this is a constant (one loop, one worker);
-            for isolated executors it identifies the subprocess/container/
-            remote worker.
-        epoch: Monotonic generation bumped whenever the worker backing a
-            session is replaced (e.g. after a wedge teardown). A turn carrying
-            a stale epoch must not run — the fencing token that stops a
-            reclaimed worker from executing against a session it no longer owns.
-    """
-
-    session_id: str
-    worker_id: str
-    epoch: int = 0
-
-
-@runtime_checkable
-class TurnExecutorProtocol(Protocol):
-    """Contract for *where* a session's agent turn executes (Issue #4011).
-
-    The gateway calls :meth:`place` to obtain a :class:`TurnPlacement` for a
-    session, then :meth:`execute_turn` to run the turn on that placement, and
-    :meth:`teardown` to reclaim a placement's worker. The default
-    :class:`InProcessTurnExecutor` runs the turn on the current event loop,
-    reproducing today's behaviour exactly; an isolated executor (subprocess /
-    container / remote, in the wrapper) runs it on its own worker so a wedged,
-    runaway, or crashed turn is contained to its session.
-
-    Contract:
-        * :meth:`place` returns the placement that owns ``session_id``'s
-          turns. Implementations may cache a placement per session and bump
-          its ``epoch`` when the backing worker is replaced.
-        * :meth:`execute_turn` runs ``turn`` (an ``async`` no-arg callable the
-          gateway already built for this turn) on ``placement`` and returns
-          its result. The in-process default awaits ``turn`` directly on the
-          current loop. An isolated executor does **not** ship this live
-          callable (and its captured loop/agent state) across a process
-          boundary — the worker owns the session (via :meth:`place`) and
-          rebuilds/dispatches the turn from serialisable inputs on its own
-          side; ``turn`` then acts as the gateway-side await point for that
-          worker's result. ``cancel_token`` carries the per-turn interrupt so
-          the existing cancellation seam is preserved. ``limits`` optionally
-          bounds the worker's CPU/memory/wall time (honoured by isolated
-          executors; ignored in-process). It raises :class:`WorkerWedgedError`
-          if the placement's worker can no longer make progress.
-        * :meth:`teardown` reclaims ``placement``'s worker (kills the
-          subprocess/container/remote worker, or is a no-op in-process),
-          scoped to the owning session only.
-
-    A worker fault must fail *scoped*: tear down the offending placement and
-    re-place its session, never the whole gateway — mirroring the fail-safe,
-    blast-radius-contained defaults elsewhere.
-    """
-
-    async def place(self, session_id: str) -> TurnPlacement:
-        """Return the placement that owns ``session_id``'s turns."""
-        ...
-
-    async def execute_turn(
-        self,
-        placement: TurnPlacement,
-        turn: "Callable[[], Awaitable[Any]]",
-        *,
-        cancel_token: Any = None,
-        limits: Any = None,
-    ) -> Any:
-        """Run ``turn`` on ``placement`` and return its result."""
-        ...
-
-    async def teardown(self, placement: TurnPlacement, *, reason: str) -> None:
-        """Reclaim ``placement``'s worker (scoped to its session)."""
-        ...
-
-
-class InProcessTurnExecutor:
-    """Default turn executor — today's on-loop behaviour, no isolation.
-
-    Zero-cost, dependency-free implementation of
-    :class:`TurnExecutorProtocol` for single-process deployments. It runs each
-    turn directly on the current event loop exactly as the gateway does today,
-    so selecting it (or leaving the executor unset) is byte-for-byte backward
-    compatible and introduces no dependency. It provides **no** blast-radius
-    isolation: a turn that wedges the loop still affects the process — choosing
-    an isolated executor (subprocess / container / remote, in the wrapper) is
-    what contains a bad turn to its own worker.
-
-    All turns share one worker (the current process/loop), so every placement
-    carries the same constant ``worker_id`` at ``epoch`` 0, and ``teardown``
-    is inert — an in-process turn is cancelled through the existing
-    ``cancel_token`` when the holding task exits, so there is no worker to
-    reclaim. The ``limits`` argument is accepted for protocol symmetry but is
-    inert here (no separate worker to bound).
-    """
-
-    _WORKER_ID = "inprocess"
-
-    async def place(self, session_id: str) -> TurnPlacement:
-        return TurnPlacement(
-            session_id=session_id, worker_id=self._WORKER_ID, epoch=0
-        )
-
-    async def execute_turn(
-        self,
-        placement: TurnPlacement,
-        turn: "Callable[[], Awaitable[Any]]",
-        *,
-        cancel_token: Any = None,
-        limits: Any = None,
-    ) -> Any:
-        # Run the gateway's pre-built turn coroutine on this loop, unchanged.
-        return await turn()
-
-    async def teardown(self, placement: TurnPlacement, *, reason: str) -> None:
-        # No isolated worker to reclaim; the shared loop keeps serving.
-        return None
-
-
 # ---------------------------------------------------------------------------
 # Declarative method -> required-scope registry (Issue #3206)
 # ---------------------------------------------------------------------------
@@ -6292,195 +5728,3 @@ def _register_core_gateway_methods() -> None:
 
 
 _register_core_gateway_methods()
-
-
-# ---------------------------------------------------------------------------
-# Global operator emergency-stop / pause brake (Issue #4220)
-# ---------------------------------------------------------------------------
-#
-# A single, durable, fail-safe operator brake: "stop admitting NEW agent work
-# everywhere, right now, but let in-flight runs finish — and resume later with
-# no restart." Every new-work admission seam (WebSocket inbound, HTTP/MCP
-# inbound, kanban dispatch cycle, scheduler due-loop) consults one shared
-# contract instead of each lane deciding independently.
-#
-# Design mirrors the drain / idle / admission / liveness policy family already
-# in this module: a pure ``Protocol`` in core plus a lightweight default and a
-# durable fail-safe backend. When no brake is engaged, ``is_engaged()`` is
-# ``False`` and behaviour is byte-for-byte today's — zero cost, no new
-# dependency, fully backward-compatible.
-
-
-@dataclass(frozen=True)
-class EmergencyStopState:
-    """Immutable snapshot of the operator brake, for status/audit surfaces.
-
-    ``engaged`` is the only field the hot path needs; ``reason``/``actor``/
-    ``at`` provide the optional audit trail surfaced in ``/health``/status.
-    """
-
-    engaged: bool
-    reason: str = ""
-    actor: str = ""
-    at: float = 0.0
-
-    def to_dict(self) -> Dict[str, Any]:
-        return {
-            "engaged": self.engaged,
-            "reason": self.reason,
-            "actor": self.actor,
-            "at": self.at,
-        }
-
-
-@runtime_checkable
-class EmergencyStopProtocol(Protocol):
-    """Pure contract for the global operator brake consulted at every seam.
-
-    Fail-safe rule: if the engaged state cannot be read with confidence (a
-    corrupt / unreadable durable sentinel), ``is_engaged()`` MUST return
-    ``True`` — an ambiguous brake holds new work rather than letting it run
-    freely. ``engage``/``disengage`` are idempotent.
-    """
-
-    def is_engaged(self) -> bool: ...
-
-    def engage(self, *, reason: str = "", actor: str = "") -> None: ...
-
-    def disengage(self) -> None: ...
-
-    def state(self) -> EmergencyStopState: ...
-
-
-class NullEmergencyStop:
-    """Default no-op brake: never engaged, no persistence.
-
-    Selected by ``backend: "off"`` (the default) so a gateway with no brake
-    configured behaves exactly as before — ``is_engaged()`` is always
-    ``False`` and ``engage``/``disengage`` are inert.
-    """
-
-    def is_engaged(self) -> bool:
-        return False
-
-    def engage(self, *, reason: str = "", actor: str = "") -> None:
-        return None
-
-    def disengage(self) -> None:
-        return None
-
-    def state(self) -> EmergencyStopState:
-        return EmergencyStopState(engaged=False)
-
-
-class FileEmergencyStop:
-    """Durable, fail-safe file-sentinel operator brake.
-
-    Engaging writes a small JSON sentinel at ``path``; disengaging removes it.
-    The engaged state therefore survives a crash/restart (durable) and is
-    shared by every lane that consults the same path.
-
-    Fail-safe: any error reading the sentinel — a partially written file,
-    corrupt JSON, a permission error — is treated as *engaged*. An ambiguous
-    brake holds new work; it never silently falls open to "run freely". The
-    common, unambiguous case (sentinel simply absent) reports not-engaged.
-
-    Pure-stdlib (``os``/``json``): no new dependency, safe to live in core.
-    """
-
-    def __init__(self, path: str) -> None:
-        if not path:
-            raise ValueError("FileEmergencyStop requires a non-empty sentinel path")
-        import os
-
-        self._path = os.path.expanduser(str(path))
-
-    def is_engaged(self) -> bool:
-        import os
-
-        if not os.path.exists(self._path):
-            return False
-        # Present but unreadable/corrupt => fail-safe engaged.
-        try:
-            with open(self._path, "r", encoding="utf-8") as fh:
-                fh.read()
-            return True
-        except OSError:
-            return True
-
-    def engage(self, *, reason: str = "", actor: str = "") -> None:
-        import json
-        import os
-
-        directory = os.path.dirname(self._path)
-        if directory:
-            os.makedirs(directory, exist_ok=True)
-        payload = {
-            "engaged": True,
-            "reason": str(reason or ""),
-            "actor": str(actor or ""),
-            "at": time.time(),
-        }
-        # Atomic replace so a reader never observes a half-written sentinel
-        # (which would fail-safe engaged anyway, but this keeps it clean).
-        # ``mkstemp`` in the sentinel's own directory yields an unpredictable
-        # name owned by us, so a local attacker cannot pre-create a symlink to
-        # redirect the write. fsync + parent-dir fsync make an engaged brake
-        # durable across an abrupt crash.
-        import tempfile
-
-        fd, tmp = tempfile.mkstemp(
-            dir=directory or ".", prefix=".gateway.pause.", suffix=".tmp"
-        )
-        try:
-            with os.fdopen(fd, "w", encoding="utf-8") as fh:
-                json.dump(payload, fh)
-                fh.flush()
-                os.fsync(fh.fileno())
-            os.replace(tmp, self._path)
-        except BaseException:
-            try:
-                os.remove(tmp)
-            except OSError:
-                pass
-            raise
-        if directory:
-            try:
-                dir_fd = os.open(directory, os.O_RDONLY)
-                try:
-                    os.fsync(dir_fd)
-                finally:
-                    os.close(dir_fd)
-            except OSError:
-                pass
-
-    def disengage(self) -> None:
-        import os
-
-        try:
-            os.remove(self._path)
-        except FileNotFoundError:
-            return None
-
-    def state(self) -> EmergencyStopState:
-        import json
-        import os
-
-        if not os.path.exists(self._path):
-            return EmergencyStopState(engaged=False)
-        try:
-            with open(self._path, "r", encoding="utf-8") as fh:
-                data = json.load(fh)
-            if not isinstance(data, dict):
-                raise ValueError("sentinel is not a JSON object")
-            return EmergencyStopState(
-                engaged=True,
-                reason=str(data.get("reason", "")),
-                actor=str(data.get("actor", "")),
-                at=float(data.get("at", 0.0) or 0.0),
-            )
-        except (OSError, TypeError, ValueError):
-            # Fail-safe: unreadable/corrupt sentinel counts as engaged. A valid
-            # JSON object with a non-numeric ``at`` (e.g. a list) raises
-            # TypeError from ``float()`` and must also fail-safe engaged.
-            return EmergencyStopState(engaged=True, reason="unreadable-sentinel")

src/praisonai-agents/praisonaiagents/goal/judge.py

@@ -47,11 +47,7 @@ def _tail(text: str, limit: int = 4000) -> str:
     return text[-limit:]
 
 
-def _build_goal_judge_prompt(
-    state: "GoalState",
-    transcript_tail: str,
-    verification_block: Optional[str] = None,
-) -> str:
+def _build_goal_judge_prompt(state: "GoalState", transcript_tail: str) -> str:
     """Build a strict, criteria-anchored, JSON-only judge prompt."""
     lines = [
         "You are an independent completion judge for an autonomous agent.",
@@ -76,13 +72,6 @@ def _build_goal_judge_prompt(
             lines.append(
                 "If ANY constraint is violated, you MUST answer 'continue'."
             )
-    if verification_block:
-        lines += [
-            "",
-            "EXECUTABLE VERIFICATION RESULTS (authoritative — command exit "
-            "codes and file checks; prefer this over prose claims):",
-            verification_block,
-        ]
     lines += [
         "",
         "AGENT OUTPUT (most recent):",
@@ -176,7 +165,6 @@ def judge_goal(
     transcript_tail: str,
     *,
     judge_model: Optional[str] = None,
-    verification_block: Optional[str] = None,
 ) -> Tuple[str, str]:
     """Judge whether ``state.goal`` is met given the latest agent output.
 
@@ -192,7 +180,7 @@ def judge_goal(
     """
     from ..eval.judge import Judge
 
-    prompt = _build_goal_judge_prompt(state, transcript_tail, verification_block)
+    prompt = _build_goal_judge_prompt(state, transcript_tail)
     try:
         judge = Judge(model=judge_model or _default_judge_model(), temperature=0.0)
         litellm = judge._get_litellm()

src/praisonai-agents/praisonaiagents/goal/loop.py

@@ -128,44 +128,11 @@ class GoalLoopMixin:
         if state is None or state.status != "active":
             return None
 
-        # Executable verification: run configured hooks and gate on the result.
-        # A failing BLOCKING hook short-circuits to "continue" WITHOUT spending
-        # a judge call. Passing/non-blocking results become authoritative
-        # evidence in the judge prompt.
-        verification_block: Optional[str] = None
-        if getattr(self, "_verification_hooks", None):
-            results = self._run_verification_hooks()
-            self._last_verification_results = results
-            self._record_verification_journal(results)
-            verification_block = self._verification_summary_tail(results)
-            blocking_failed = [
-                r for r in results
-                if r.get("blocking", True) and not r.get("success")
-            ]
-            if blocking_failed:
-                state.turns_used += 1
-                state.last_verdict = "continue"
-                # Carry the failing hooks' captured stdout/stderr into the
-                # continuation prompt so the next turn has the diagnostics
-                # needed to repair the failure (not just a bare label).
-                failure_detail = self._verification_summary_tail(blocking_failed)
-                reason = "verification gate failed"
-                if failure_detail:
-                    reason = f"{reason}:\n{failure_detail}"
-                state.last_reason = reason
-                if state.turns_used >= state.max_turns:
-                    state.status = "paused"
-                    self._persist_goal_state()
-                    return "budget_paused", reason
-                self._persist_goal_state()
-                return "continue", reason
-
         state.turns_used += 1
         verdict, reason = judge_goal(
             state,
             _tail(response),
             judge_model=getattr(self, "_goal_judge_model", None),
-            verification_block=verification_block,
         )
         state.last_verdict, state.last_reason = verdict, reason
 

src/praisonai-agents/praisonaiagents/guardrails/__init__.py

@@ -7,12 +7,7 @@ including both function-based and LLM-based guardrails.
 
 from .guardrail_result import GuardrailResult
 from .llm_guardrail import LLMGuardrail
-from .protocols import (
-    GuardrailProtocol,
-    StructuralGuardrailProtocol,
-    PolicyGuardrailProtocol,
-    is_guardrail_object,
-)
+from .protocols import GuardrailProtocol, StructuralGuardrailProtocol, PolicyGuardrailProtocol
 from .chain import GuardrailChain
 
 __all__ = [
@@ -21,6 +16,5 @@ __all__ = [
     "GuardrailProtocol", 
     "StructuralGuardrailProtocol", 
     "PolicyGuardrailProtocol", 
-    "GuardrailChain",
-    "is_guardrail_object",
+    "GuardrailChain"
 ]

src/praisonai-agents/praisonaiagents/guardrails/protocols.py

@@ -175,25 +175,3 @@ class PolicyGuardrailProtocol(Protocol):
         """
         ...
 
-
-# Method names that make an object a guardrail. An object exposing at least one
-# of these is a protocol-conforming guardrail even though it is not ``callable``.
-GUARDRAIL_PROTOCOL_METHODS = ("validate_input", "validate_output", "validate_tool_call")
-
-
-def is_guardrail_object(obj: Any) -> bool:
-    """Return True when ``obj`` is a protocol-conforming guardrail *instance*.
-
-    ``isinstance(obj, GuardrailProtocol)`` is not usable here: a ``runtime_checkable``
-    Protocol only checks method presence and would also match unrelated objects
-    partially, while classes (not instances) must be rejected. This helper is the
-    single place that decides "is this thing a guardrail object?".
-
-    Plain validator callables are handled by their own passthrough branch and are
-    not required to match here (they will, however, if they also expose one of the
-    protocol methods - e.g. ``GuardrailChain``).
-    """
-    if obj is None or isinstance(obj, type):
-        return False
-    return any(callable(getattr(obj, name, None)) for name in GUARDRAIL_PROTOCOL_METHODS)
-

src/praisonai-agents/praisonaiagents/hooks/__init__.py

@@ -104,9 +104,6 @@ __all__ = [
     # Verification hooks (protocols)
     "VerificationHook",
     "VerificationResult",
-    "BaseVerificationHook",
-    "CommandVerificationHook",
-    "FileCheckHook",
     # Simplified API (beginner-friendly)
     "add_hook",
     "remove_hook",
@@ -181,9 +178,6 @@ _LAZY_GROUPS = {
     'verification': {
         'VerificationHook': ('praisonaiagents.hooks.verification', 'VerificationHook'),
         'VerificationResult': ('praisonaiagents.hooks.verification', 'VerificationResult'),
-        'BaseVerificationHook': ('praisonaiagents.hooks.verification', 'BaseVerificationHook'),
-        'CommandVerificationHook': ('praisonaiagents.hooks.verification', 'CommandVerificationHook'),
-        'FileCheckHook': ('praisonaiagents.hooks.verification', 'FileCheckHook'),
     },
     # Simplified API (beginner-friendly aliases)
     'simplified_api': {

src/praisonai-agents/praisonaiagents/hooks/runner.py

@@ -184,19 +184,7 @@ class HookRunner:
             self._execute_single(hook, event, input_data)
             for hook in hooks
         ]
-        results = await asyncio.gather(*tasks)
-
-        # Parallel hooks cannot mutate input_data (only sequential hooks apply
-        # modified_input). Warn if a parallel hook returns modifications that
-        # will be silently discarded, so hook authors mark it sequential=True.
-        for hook, result in zip(hooks, results):
-            if result.success and result.output and result.output.modified_input:
-                logger.warning(
-                    "Parallel hook '%s' returned modified_input which is "
-                    "discarded; register it with sequential=True to apply it.",
-                    hook.name,
-                )
-        return results
+        return await asyncio.gather(*tasks)
     
     async def _execute_sequential(
         self,

src/praisonai-agents/praisonaiagents/hooks/verification.py

@@ -114,26 +114,17 @@ class BaseVerificationHook:
     
     name: str = "base"
     timeout_seconds: float = 60.0
-    blocking: bool = True
-
-    def __init__(
-        self,
-        name: Optional[str] = None,
-        timeout: float = 60.0,
-        blocking: bool = True,
-    ):
+    
+    def __init__(self, name: Optional[str] = None, timeout: float = 60.0):
         """Initialize the hook.
         
         Args:
             name: Override the hook name
             timeout: Timeout in seconds for execution
-            blocking: When True (default), a failure of this hook blocks the
-                autonomous loop from finalising with a success outcome.
         """
         if name:
             self.name = name
         self.timeout_seconds = timeout
-        self.blocking = blocking
     
     def run(self, context: Optional[Dict[str, Any]] = None) -> VerificationResult:
         """Run the verification hook.
@@ -186,25 +177,19 @@ class CommandVerificationHook(BaseVerificationHook):
     def __init__(
         self,
         name: str,
-        command,
+        command: list,
         cwd: Optional[str] = None,
         timeout: float = 60.0,
-        blocking: bool = True,
     ):
         """Initialize command hook.
         
         Args:
             name: Hook name
-            command: Command to run as a list (e.g., ["pytest", "-v"]) or a
-                string (e.g., "python -m pytest -q"), which is shell-split.
+            command: Command to run as list (e.g., ["pytest", "-v"])
             cwd: Working directory for command
             timeout: Timeout in seconds
-            blocking: When True (default), a failure blocks completion.
         """
-        super().__init__(name=name, timeout=timeout, blocking=blocking)
-        if isinstance(command, str):
-            import shlex
-            command = shlex.split(command)
+        super().__init__(name=name, timeout=timeout)
         self.command = command
         self.cwd = cwd
     
@@ -250,143 +235,3 @@ class CommandVerificationHook(BaseVerificationHook):
                 output=str(e),
                 error=str(e),
             )
-
-
-def _get_dotted(data: Any, path: str) -> Any:
-    """Access a dotted path (e.g. ``"a.b.c"``) in nested dicts/lists.
-
-    Returns ``None`` if any segment is missing. List indices are supported
-    via integer-looking segments.
-    """
-    value = data
-    for part in path.split("."):
-        if isinstance(value, dict):
-            value = value.get(part)
-        elif isinstance(value, (list, tuple)):
-            try:
-                value = value[int(part)]
-            except (ValueError, IndexError):
-                return None
-        else:
-            return None
-    return value
-
-
-class FileCheckHook(BaseVerificationHook):
-    """Declarative file-assertion verification hook (no shell involved).
-
-    Checks portable filesystem facts:
-      - ``exists``    : the file exists (default True).
-      - ``non_empty`` : the file has non-zero size.
-      - ``contains``  : the file text contains a substring.
-      - ``json_field``/``equals`` : the JSON value at a dotted path equals a value.
-
-    Example:
-        hook = FileCheckHook(name="changelog", path="CHANGELOG.md", non_empty=True)
-        hook = FileCheckHook(name="cfg", path="out.json",
-                             json_field="status.code", equals=0)
-    """
-
-    def __init__(
-        self,
-        name: str,
-        path: str,
-        exists: bool = True,
-        non_empty: bool = False,
-        contains: Optional[str] = None,
-        json_field: Optional[str] = None,
-        equals: Any = None,
-        blocking: bool = True,
-    ):
-        super().__init__(name=name, blocking=blocking)
-        self.path = path
-        self.exists = exists
-        self.non_empty = non_empty
-        self.contains = contains
-        self.json_field = json_field
-        self.equals = equals
-
-    def _execute(self, context: Optional[Dict[str, Any]] = None) -> VerificationResult:
-        import os
-
-        details: Dict[str, Any] = {"path": self.path}
-        file_exists = os.path.isfile(self.path)
-        details["exists"] = file_exists
-
-        if self.exists and not file_exists:
-            return VerificationResult(
-                success=False,
-                output=f"File not found: {self.path}",
-                error="not_found",
-                details=details,
-            )
-        if not self.exists:
-            success = not file_exists
-            return VerificationResult(
-                success=success,
-                output=(
-                    f"File exists but was expected absent: {self.path}"
-                    if not success else f"File absent as expected: {self.path}"
-                ),
-                details=details,
-            )
-
-        if self.non_empty:
-            size = os.path.getsize(self.path)
-            details["size"] = size
-            if size == 0:
-                return VerificationResult(
-                    success=False,
-                    output=f"File is empty: {self.path}",
-                    error="empty",
-                    details=details,
-                )
-
-        if self.contains is not None or self.json_field is not None:
-            try:
-                with open(self.path, "r", encoding="utf-8") as fh:
-                    text = fh.read()
-            except Exception as e:
-                return VerificationResult(
-                    success=False, output=str(e), error=str(e), details=details
-                )
-
-            if self.contains is not None and self.contains not in text:
-                return VerificationResult(
-                    success=False,
-                    output=f"File {self.path} does not contain {self.contains!r}",
-                    error="missing_substring",
-                    details=details,
-                )
-
-            if self.json_field is not None:
-                import json as _json
-
-                try:
-                    data = _json.loads(text)
-                except Exception as e:
-                    return VerificationResult(
-                        success=False,
-                        output=f"File {self.path} is not valid JSON: {e}",
-                        error="invalid_json",
-                        details=details,
-                    )
-                actual = _get_dotted(data, self.json_field)
-                details["json_field"] = self.json_field
-                details["actual"] = actual
-                if actual != self.equals:
-                    return VerificationResult(
-                        success=False,
-                        output=(
-                            f"{self.path}:{self.json_field} = {actual!r}, "
-                            f"expected {self.equals!r}"
-                        ),
-                        error="mismatch",
-                        details=details,
-                    )
-
-        return VerificationResult(
-            success=True,
-            output=f"File check passed: {self.path}",
-            details=details,
-        )

src/praisonai-agents/praisonaiagents/knowledge/chunking.py

@@ -2,30 +2,6 @@ from typing import List, Union, Optional, Dict, Any
 from functools import cached_property
 import importlib
 
-#: Names accepted for a chunking strategy that are not chunker ids themselves.
-#: ``ChunkingStrategy.FIXED`` and ``.PARAGRAPH`` had no chunker at all, so they
-#: silently did nothing; they now map onto the chunkers that implement them.
-CHUNKER_ALIASES = {
-    "fixed": "token",
-    "paragraph": "recursive",
-}
-
-
-def normalize_chunker_type(name: str) -> str:
-    """Map a user-facing chunking strategy name onto a chunker id."""
-    if not name:
-        return "recursive"
-    key = str(name).strip().lower()
-    key = CHUNKER_ALIASES.get(key, key)
-    if key not in Chunking.CHUNKER_PARAMS:
-        from ..config.parse_utils import make_preset_error
-        raise make_preset_error(
-            "chunking strategy", name,
-            sorted(set(Chunking.CHUNKER_PARAMS) | set(CHUNKER_ALIASES)),
-        )
-    return key
-
-
 class Chunking:
     """A unified class for text chunking with various chunking strategies."""
     

src/praisonai-agents/praisonaiagents/knowledge/knowledge.py

@@ -2,7 +2,7 @@ import os
 import logging
 from praisonaiagents._logging import get_logger
 from datetime import datetime
-from .chunking import Chunking, normalize_chunker_type
+from .chunking import Chunking
 from functools import cached_property
 
 
@@ -162,10 +162,6 @@ class Knowledge:
             # Merge graph_store config if provided (for graph memory support)
             if "graph_store" in self._config:
                 base_config["graph_store"] = self._config["graph_store"]
-
-            # Merge chunker config if provided (consumed by self.chunker)
-            if "chunker" in self._config:
-                base_config["chunker"] = self._config["chunker"]
         return base_config
 
     def _prepare_mem0_config(self, config):
@@ -199,46 +195,28 @@ class Knowledge:
     def memory(self):
         """Initialize knowledge adapter using protocol-driven approach."""
         # Import registry functions
-        from .adapters import (
-            get_knowledge_adapter,
-            get_first_available_knowledge_adapter,
-            has_knowledge_adapter,
-            list_knowledge_adapters,
-        )
+        from .adapters import get_knowledge_adapter, get_first_available_knowledge_adapter
         
         # Determine provider preference. Distinguish an explicit user choice from
         # the implicit default so fallback diagnostics are only loud when a
         # configured backend degrades (see issue #2972 / PR #2982 review).
         # ``self.config`` is always merged with defaults, so use the raw
         # user-supplied ``_config`` to detect whether the provider was chosen.
-        # Presence of the key (not truthiness) marks an explicit choice, so an
-        # explicitly empty/null provider is treated as a misconfiguration and
-        # surfaces the preset error instead of silently degrading to Mem0.
-        provider_explicit = "provider" in (
-            (self._config or {}).get("vector_store", {}) or {}
+        provider_explicit = bool(
+            (self._config or {}).get("vector_store", {}).get("provider")
         )
         provider = self.config.get("vector_store", {}).get("provider", "mem0")
         self._log(f"Requested knowledge provider: {provider}")
         
-        # Legacy provider aliases. Anything else is looked up in the adapter
-        # registry, so adapters added with register_knowledge_adapter() are
-        # reachable; only genuinely unknown names fall back (and say so).
+        # Map legacy provider names to adapter names
         provider_mapping = {
-            "chromadb": "chroma",
-            "rag": "chroma",
+            "chroma": "chroma",
+            "mongodb": "mongodb", 
+            "mem0": "mem0",
+            "sqlite": "sqlite"
         }
-
-        adapter_name = provider_mapping.get(provider, provider)
-        if not has_knowledge_adapter(adapter_name):
-            from ..config.parse_utils import make_preset_error
-            err = make_preset_error(
-                "knowledge vector_store provider", provider,
-                sorted(set(list_knowledge_adapters()) | set(provider_mapping)),
-            )
-            if provider_explicit:
-                raise err
-            self._log(f"{err} Falling back to 'mem0'.")
-            adapter_name = "mem0"
+        
+        adapter_name = provider_mapping.get(provider, "mem0")
         
         # Try to get preferred adapter, fallback to available ones
         try:
@@ -309,13 +287,10 @@ class Knowledge:
 
     @cached_property
     def chunker(self):
-        # Read from config; the previous hardcoded recursive/512/50 made
-        # KnowledgeConfig.chunk_size / chunking_strategy / chunker inert.
-        chunker_cfg = self.config.get("chunker") or {}
         return Chunking(
-            chunker_type=normalize_chunker_type(chunker_cfg.get("type", "recursive")),
-            chunk_size=chunker_cfg.get("chunk_size", 512),
-            chunk_overlap=chunker_cfg.get("chunk_overlap", 50),
+            chunker_type='recursive',
+            chunk_size=512,
+            chunk_overlap=50
         )
 
     def _log(self, message, level=2):
@@ -438,11 +413,7 @@ class Knowledge:
 
     def history(self, memory_id):
         """Get the history of changes for a memory."""
-        if hasattr(self.memory, "history"):
-            return self.memory.history(memory_id)
-        raise NotImplementedError(
-            f"{type(self.memory).__name__} does not support history()"
-        )
+        return self.memory.history(memory_id)
 
     def delete(self, memory_id):
         """Delete a memory."""
@@ -450,21 +421,11 @@ class Knowledge:
 
     def delete_all(self, user_id=None, agent_id=None, run_id=None):
         """Delete all memories."""
-        if hasattr(self.memory, "delete_all"):
-            self.memory.delete_all(user_id=user_id, agent_id=agent_id, run_id=run_id)
-        else:
-            raise NotImplementedError(
-                f"{type(self.memory).__name__} does not support delete_all()"
-            )
+        self.memory.delete_all(user_id=user_id, agent_id=agent_id, run_id=run_id)
 
     def reset(self):
         """Reset all memories."""
-        if hasattr(self.memory, "reset"):
-            self.memory.reset()
-        else:
-            logger.warning(
-                f"{type(self.memory).__name__} does not support reset(); no-op"
-            )
+        self.memory.reset()
 
     def normalize_content(self, content):
         """Normalize content for consistent storage."""

src/praisonai-agents/praisonaiagents/llm/__init__.py

@@ -107,22 +107,6 @@ def __getattr__(name):
             from .rate_limiter import RateLimiter
             _lazy_cache[name] = RateLimiter
             return RateLimiter
-        elif name == "QuotaCoordinatorProtocol":
-            from .quota import QuotaCoordinatorProtocol
-            _lazy_cache[name] = QuotaCoordinatorProtocol
-            return QuotaCoordinatorProtocol
-        elif name == "QuotaCoordinatorConfig":
-            from .quota import QuotaCoordinatorConfig
-            _lazy_cache[name] = QuotaCoordinatorConfig
-            return QuotaCoordinatorConfig
-        elif name == "LocalQuotaCoordinator":
-            from .quota import LocalQuotaCoordinator
-            _lazy_cache[name] = LocalQuotaCoordinator
-            return LocalQuotaCoordinator
-        elif name == "build_quota_coordinator":
-            from .quota import build_quota_coordinator
-            _lazy_cache[name] = build_quota_coordinator
-            return build_quota_coordinator
         elif name == "TokenUsage":
             from .llm import TokenUsage
             _lazy_cache[name] = TokenUsage
@@ -245,11 +229,6 @@ __all__ = [
     "create_routing_agent",
     "RateLimiter",
     "TokenUsage",
-    # Provider quota coordination (cross-replica credential cooldowns)
-    "QuotaCoordinatorProtocol",
-    "QuotaCoordinatorConfig",
-    "LocalQuotaCoordinator",
-    "build_quota_coordinator",
     # Protocols
     "LLMProviderProtocol",
     "ModelCapabilitiesProtocol",

src/praisonai-agents/praisonaiagents/llm/failover.py

@@ -16,7 +16,6 @@ import time
 from dataclasses import dataclass, field
 from enum import Enum
 from typing import (
-    TYPE_CHECKING,
     Any,
     Callable,
     Dict,
@@ -26,9 +25,6 @@ from typing import (
     runtime_checkable,
 )
 
-if TYPE_CHECKING:
-    from .quota import QuotaCoordinatorProtocol
-
 logger = get_logger(__name__)
 
 class ProviderStatus(str, Enum):
@@ -116,29 +112,6 @@ class AuthProfile:
             metadata=data.get("metadata", {}),
         )
     
-    @property
-    def credential_id(self) -> str:
-        """Stable, non-secret identity for cross-replica quota coordination.
-
-        The coordinator keys benches by the *credential*, not the profile
-        label. ``name`` is a local display label: two replicas may name the
-        same key differently (breaking cooldown propagation) or reuse a name
-        like ``"default"`` for different keys (benching an unrelated key).
-        Derive a deterministic id from the fields that identify the credential
-        (provider, api_key, base_url) using a short salted hash so the real key
-        is never exposed. Falls back to ``name`` when no api_key is present.
-        """
-        if not self.api_key:
-            return self.name
-        import hashlib
-
-        digest = hashlib.sha256(
-            f"{self.provider}\x00{self.base_url or ''}\x00{self.api_key}".encode(
-                "utf-8", "ignore"
-            )
-        ).hexdigest()[:16]
-        return f"{self.provider}:{digest}"
-
     @property
     def is_available(self) -> bool:
         """Check if this profile is currently available."""
@@ -234,27 +207,13 @@ class FailoverManager:
         profile = manager.get_next_profile()
     """
     
-    def __init__(
-        self,
-        config: Optional[FailoverConfig] = None,
-        coordinator: Optional["QuotaCoordinatorProtocol"] = None,
-    ):
+    def __init__(self, config: Optional[FailoverConfig] = None):
         """Initialize the failover manager.
         
         Args:
             config: Failover configuration
-            coordinator: Optional shared quota coordinator. When supplied
-                (e.g. a Redis-backed one wired by the gateway), credential
-                benches/cooldowns are coordinated fleet-wide so a key benched
-                by any replica is skipped by all replicas. Defaults to an
-                in-memory local coordinator, keeping single-replica behaviour
-                exactly as before with no new dependency and no hot-path cost.
         """
         self.config = config or FailoverConfig()
-        if coordinator is None:
-            from .quota import LocalQuotaCoordinator
-            coordinator = LocalQuotaCoordinator()
-        self._coordinator: "QuotaCoordinatorProtocol" = coordinator
         self._profiles: List[AuthProfile] = []
         self._current_index: int = 0
         self._on_failover_callbacks: List[Callable[[AuthProfile, AuthProfile], None]] = []
@@ -315,30 +274,6 @@ class FailoverManager:
         with self._lock:
             return list(self._profiles)
     
-    def _sync_bench_from_coordinator(
-        self, profile: AuthProfile, now: Optional[float] = None
-    ) -> None:
-        """Apply a fleet-wide bench from the coordinator onto a local profile.
-
-        If another replica benched this credential, reflect its cooldown here
-        so this replica skips it too. Fail-open: never raise into failover.
-        Callers already hold ``self._lock``.
-        """
-        try:
-            until = self._coordinator.benched_until(profile.credential_id, now=now)
-        except Exception as e:  # pragma: no cover - defensive
-            logger.warning(
-                f"Quota coordinator lookup failed for '{profile.name}': {e}; "
-                f"using local cooldown state"
-            )
-            return
-        if until is not None and (
-            profile.cooldown_until is None or until > profile.cooldown_until
-        ):
-            if profile.status == ProviderStatus.AVAILABLE:
-                profile.status = ProviderStatus.RATE_LIMITED
-            profile.cooldown_until = until
-
     def get_next_profile(self) -> Optional[AuthProfile]:
         """Get the next available profile.
         
@@ -352,10 +287,9 @@ class FailoverManager:
             if not self._profiles:
                 return None
             
-            # First, sync fleet-wide benches, then check if any cooldowns have expired.
+            # First, check if any cooldowns have expired
             current_time = time.time()
             for profile in self._profiles:
-                self._sync_bench_from_coordinator(profile, now=current_time)
                 if profile.cooldown_until and current_time >= profile.cooldown_until:
                     profile.reset()
             
@@ -394,29 +328,12 @@ class FailoverManager:
                     f"Profile '{profile.name}' rate limited, "
                     f"cooldown for {self.config.cooldown_on_rate_limit}s"
                 )
-                reason = "rate_limit"
             else:
                 profile.mark_error(error, self.config.cooldown_on_error)
                 logger.warning(
                     f"Profile '{profile.name}' error: {error}, "
                     f"cooldown for {self.config.cooldown_on_error}s"
                 )
-                reason = "error"
-
-            # Share the bench fleet-wide so other replicas skip this key too.
-            # Fail-open: a coordinator hiccup must never wedge failover.
-            if profile.cooldown_until is not None:
-                try:
-                    self._coordinator.bench(
-                        profile.credential_id,
-                        until=profile.cooldown_until,
-                        reason=reason,
-                    )
-                except Exception as e:  # pragma: no cover - defensive
-                    logger.warning(
-                        f"Quota coordinator bench failed for '{profile.name}': {e}; "
-                        f"falling back to local cooldown only"
-                    )
             
             # Resolve the target profile and snapshot callbacks while holding
             # the lock, but invoke them AFTER releasing it. User callbacks may
@@ -444,30 +361,8 @@ class FailoverManager:
         """
         with self._lock:
             if profile.status != ProviderStatus.AVAILABLE:
-                # Snapshot the cooldown this success is recovering from BEFORE
-                # resetting, so we can avoid clobbering a newer fleet-wide bench.
-                recovered_from = profile.cooldown_until
                 profile.reset()
                 logger.info(f"Profile '{profile.name}' recovered")
-                cred_id = profile.credential_id
-                try:
-                    # A concurrent/other-replica failure may have benched this
-                    # credential with a LATER expiry than the cooldown this
-                    # (possibly stale, already in-flight) success is recovering
-                    # from. Clearing unconditionally would resume a credential
-                    # that is still rate-limited. Only clear when the shared
-                    # bench is not newer than what we recovered from.
-                    shared_until = self._coordinator.benched_until(cred_id)
-                    if (
-                        shared_until is None
-                        or recovered_from is None
-                        or shared_until <= recovered_from
-                    ):
-                        self._coordinator.clear(cred_id)
-                except Exception as e:  # pragma: no cover - defensive
-                    logger.warning(
-                        f"Quota coordinator clear failed for '{profile.name}': {e}"
-                    )
     
     def on_failover(
         self,

src/praisonai-agents/praisonaiagents/llm/llm.py

@@ -28,14 +28,6 @@ from ..tools.call_executor import ToolCall, create_tool_call_executor
 from ..tools.schema import build_tool_definition
 
 
-# Sentinel returned as the "arguments" value when a tool call's argument string
-# cannot be parsed (e.g. truncated by max_tokens or a dropped connection).
-# It is distinct from {} ("no arguments"): {} would silently execute the tool
-# with the WRONG arguments and report success. Callers must detect this sentinel
-# and surface a tool-error so the model can re-emit the call instead.
-_TOOL_ARGUMENTS_PARSE_FAILED = object()
-
-
 def _durable_iteration_kwargs(execute_tool_fn: Callable, index: int) -> Dict[str, int]:
     if getattr(execute_tool_fn, "_accepts_durable_iteration", False):
         return {"_durable_iteration_index": index}
@@ -542,18 +534,7 @@ Respond with ONLY a valid JSON tool call in this format:
         if self._failover_manager:
             self._current_profile = self._failover_manager.get_next_profile()
             if self._current_profile:
-                # Apply the initial profile's values to the instance attributes
-                # (backward compatible with the documented llm.api_key/model
-                # surface). Later failover rotations are per-call only and do
-                # not mutate these attributes (issue #3613 gap 2).
-                profile = self._current_profile
-                if profile.api_key:
-                    self.api_key = profile.api_key
-                if profile.base_url:
-                    self.base_url = profile.base_url
-                if profile.model and profile.model != self.model:
-                    logging.info(f"Failover: using profile model {profile.model}")
-                    self.model = profile.model
+                self._switch_to_profile(self._current_profile)
 
         # Cache for formatted tools and messages
         self._formatted_tools_cache = {}
@@ -993,58 +974,18 @@ Respond with ONLY a valid JSON tool call in this format:
 
     def _switch_to_profile(self, profile: "AuthProfile") -> None:
         """Switch to a new auth profile for failover.
-
-        The profile's credentials are threaded through the per-call kwargs of
-        the retry loop instead of being written onto the shared instance. The
-        old behaviour mutated ``self.api_key``/``self.base_url``/``self.model``
-        on a shared ``LLM`` (issue #3613 gap 2), so concurrent requests on one
-        instance could silently cross-talk credentials and model after a
-        failover rotation. Keeping the instance attributes on the initial
-        profile preserves single-profile behaviour and the documented
-        ``llm.api_key``/``llm.model`` surface.
-
+        
         Args:
             profile: AuthProfile to switch to
         """
-        # NOTE: profile values are applied to the per-call kwargs by
-        # _handle_retry_exception when it rotates. This method is kept as a
-        # no-op placeholder so any out-of-tree callers that invoke it directly
-        # keep working; it intentionally no longer mutates shared state.
-        if profile is None:
-            return
-
-    def _response_model_for_tracking(self, response: Any) -> str:
-        """Model to attribute token usage to for a completed call.
-
-        Prefers the model carried on the response itself, which reflects the
-        provider/profile that actually served the request. This is race-free
-        under concurrency (unlike reading the shared ``self._current_profile``)
-        and stays correct after a failover rotation. Falls back to
-        ``self.model`` when the response does not expose a model.
-        """
-        model = None
-        if isinstance(response, dict):
-            model = response.get("model")
-        else:
-            model = getattr(response, "model", None)
-        return model or self.model
-
-    def _apply_profile_to_kwargs(self, profile: "AuthProfile", kwargs: dict) -> dict:
-        """Return a new kwargs dict with profile overrides applied.
-
-        Never mutates ``self``: the active profile is a per-call concern, so
-        its credentials travel in the request kwargs only. Callers that pass
-        an explicit per-call override (e.g. ``api_key=``) keep it; profile
-        values fill in the gaps.
-        """
-        kwargs = dict(kwargs)
         if profile.api_key:
-            kwargs["api_key"] = profile.api_key
+            self.api_key = profile.api_key
         if profile.base_url:
-            kwargs["base_url"] = profile.base_url
-        if profile.model:
-            kwargs["model"] = profile.model
-        return kwargs
+            self.base_url = profile.base_url
+        if profile.model and profile.model != self.model:
+            # Only log if model actually changes
+            logging.info(f"Failover: switching from {self.model} to {profile.model}")
+            self.model = profile.model
 
     def _resolve_subscription_creds(self):
         """Lazy resolve + cache subscription credentials, checking expiration."""
@@ -1114,7 +1055,7 @@ Respond with ONLY a valid JSON tool call in this format:
             )
             return None
 
-    def _handle_retry_exception(self, e, attempt, kwargs, refreshed_creds=None, active_profile=None):
+    def _handle_retry_exception(self, e, attempt, kwargs, refreshed_creds=None):
         """Decide retry vs raise from a failover decision. No sleep/await.
 
         Shared decision logic used by both the sync (`_call_with_retry`) and
@@ -1128,34 +1069,21 @@ Respond with ONLY a valid JSON tool call in this format:
         blocks the event loop. The already-refreshed credentials (if any) are
         passed in via ``refreshed_creds``.
 
-        The active failover profile is a *per-call* value threaded in via
-        ``active_profile`` and returned back in the result tuple. It is never
-        read from or written to ``self._current_profile`` here, so concurrent
-        requests sharing one ``LLM`` instance cannot corrupt each other's
-        failover bookkeeping or cost attribution (issue #3613 gap 2).
-
         Args:
             e: The exception raised by the wrapped call.
             attempt: Zero-based attempt index for the current iteration.
             kwargs: Keyword arguments for the wrapped call (may be updated).
             refreshed_creds: Credentials already refreshed by the caller (off
                 the event loop for async), or ``None`` if no refresh was done.
-            active_profile: The profile this call is currently using, or
-                ``None``. Defaults to the initial profile for backward compat.
 
         Returns:
-            Tuple of (should_raise, category, retry_delay, error_str, kwargs,
-            active_profile):
+            Tuple of (should_raise, category, retry_delay, error_str, kwargs):
                 should_raise: Whether the caller should re-raise immediately.
                 category: The error category/reason from the decision.
                 retry_delay: Seconds to wait before the next attempt.
                 error_str: String form of the exception.
                 kwargs: The (possibly updated) keyword arguments.
-                active_profile: The (possibly rotated) profile for the next
-                    attempt.
         """
-        if active_profile is None:
-            active_profile = self._current_profile
         # A turn is "side-effecting" when it exposes tools the model may call:
         # a post-dispatch failure on such a turn could have already run a
         # side-effecting tool, so it must not be silently replayed. A turn with
@@ -1207,48 +1135,55 @@ Respond with ONLY a valid JSON tool call in this format:
         # immediately with fresh credentials and skip profile rotation so we
         # neither mark the current profile failed nor overwrite the new creds.
         if refreshed_auth:
-            return False, category, retry_delay, error_str, kwargs, active_profile
+            return False, category, retry_delay, error_str, kwargs
 
-        # Handle different failover decision actions. Rotation is a per-call
-        # concern: the active profile is a local threaded in/out of this method,
-        # never self._current_profile, so concurrent calls on one shared LLM
-        # cannot mark each other's profiles failed/healthy (issue #3613 gap 2).
+        # Handle different failover decision actions
         if decision.action == "rotate_profile" and self._failover_manager:
-            if active_profile:
+            if self._current_profile:
                 is_rate_limit = (category == "rate_limit")
                 self._failover_manager.mark_failure(
-                    active_profile, error_str, is_rate_limit=is_rate_limit
+                    self._current_profile, error_str, is_rate_limit=is_rate_limit
                 )
             next_profile = self._failover_manager.get_next_profile()
-            if next_profile and next_profile != active_profile:
-                active_profile = next_profile
-                # Thread the active profile through the per-call kwargs so the
-                # shared instance state is never mutated (issue #3613 gap 2).
-                kwargs = self._apply_profile_to_kwargs(next_profile, kwargs)
+            if next_profile and next_profile != self._current_profile:
+                self._switch_to_profile(next_profile)
+                self._current_profile = next_profile
+                # Update the kwargs with new profile values for the next retry
+                if "api_key" in kwargs:
+                    kwargs["api_key"] = self.api_key
+                if "base_url" in kwargs:
+                    kwargs["base_url"] = self.base_url
+                if "model" in kwargs:
+                    kwargs["model"] = self.model
                 logging.info(f"Failover: switched to profile '{next_profile.name}'")
             else:
                 # No alternate profile available - retrying would just hit the
                 # same failing profile, so surface the error instead.
                 can_retry = False
         # Legacy failover for compatibility (when decision is retry but failover is configured)
-        elif self._failover_manager and active_profile and decision.action == "retry":
+        elif self._failover_manager and self._current_profile and decision.action == "retry":
             is_rate_limit = (category == "rate_limit")
             self._failover_manager.mark_failure(
-                active_profile, error_str, is_rate_limit=is_rate_limit
+                self._current_profile, error_str, is_rate_limit=is_rate_limit
             )
             next_profile = self._failover_manager.get_next_profile()
-            if next_profile and next_profile != active_profile:
-                active_profile = next_profile
-                # Thread the active profile through the per-call kwargs so the
-                # shared instance state is never mutated (issue #3613 gap 2).
-                kwargs = self._apply_profile_to_kwargs(next_profile, kwargs)
+            if next_profile and next_profile != self._current_profile:
+                self._switch_to_profile(next_profile)
+                self._current_profile = next_profile
+                # Update the kwargs with new profile values for the next retry
+                if "api_key" in kwargs:
+                    kwargs["api_key"] = self.api_key
+                if "base_url" in kwargs:
+                    kwargs["base_url"] = self.base_url
+                if "model" in kwargs:
+                    kwargs["model"] = self.model
                 # Enable retry for profile switch even if originally non-retryable
                 can_retry = True
                 retry_delay = 0.0
                 logging.info(f"Failover: switched to profile '{next_profile.name}'")
 
         should_raise = decision.action == "surface_error" or not can_retry
-        return should_raise, category, retry_delay, error_str, kwargs, active_profile
+        return should_raise, category, retry_delay, error_str, kwargs
 
     def _call_with_retry(self, func, *args, **kwargs):
         """Call a function with automatic retry on rate limit errors and failover support.
@@ -1265,10 +1200,6 @@ Respond with ONLY a valid JSON tool call in this format:
             The original exception if max retries exceeded
         """
         last_error = None
-        # Track the failover profile per call (never self._current_profile) so
-        # concurrent calls on one shared LLM cannot corrupt each other's
-        # failover bookkeeping (issue #3613 gap 2).
-        active_profile = self._current_profile
 
         for attempt in range(self._max_retries + 1):
             try:
@@ -1279,8 +1210,8 @@ Respond with ONLY a valid JSON tool call in this format:
                 result = func(*args, **kwargs)
                 
                 # Mark success if failover is configured
-                if self._failover_manager and active_profile:
-                    self._failover_manager.mark_success(active_profile)
+                if self._failover_manager and self._current_profile:
+                    self._failover_manager.mark_success(self._current_profile)
                 
                 # Reset idle timeout circuit breaker on success
                 self._idle_timeout_breaker.reset()
@@ -1295,12 +1226,8 @@ Respond with ONLY a valid JSON tool call in this format:
                 if self._should_attempt_auth_refresh(e, attempt):
                     refreshed_creds = self._try_refresh_subscription_creds()
 
-                should_raise, category, retry_delay, error_str, kwargs, active_profile = (
-                    self._handle_retry_exception(
-                        e, attempt, kwargs,
-                        refreshed_creds=refreshed_creds,
-                        active_profile=active_profile,
-                    )
+                should_raise, category, retry_delay, error_str, kwargs = (
+                    self._handle_retry_exception(e, attempt, kwargs, refreshed_creds=refreshed_creds)
                 )
 
                 if should_raise:
@@ -1349,10 +1276,6 @@ Respond with ONLY a valid JSON tool call in this format:
             The original exception if max retries exceeded
         """
         last_error = None
-        # Track the failover profile per call (never self._current_profile) so
-        # concurrent coroutines on one shared LLM cannot corrupt each other's
-        # failover bookkeeping (issue #3613 gap 2).
-        active_profile = self._current_profile
 
         for attempt in range(self._max_retries + 1):
             try:
@@ -1363,8 +1286,8 @@ Respond with ONLY a valid JSON tool call in this format:
                 result = await func(*args, **kwargs)
                 
                 # Mark success if failover is configured
-                if self._failover_manager and active_profile:
-                    self._failover_manager.mark_success(active_profile)
+                if self._failover_manager and self._current_profile:
+                    self._failover_manager.mark_success(self._current_profile)
                 
                 # Reset idle timeout circuit breaker on success
                 self._idle_timeout_breaker.reset()
@@ -1382,12 +1305,8 @@ Respond with ONLY a valid JSON tool call in this format:
                         self._try_refresh_subscription_creds
                     )
 
-                should_raise, category, retry_delay, error_str, kwargs, active_profile = (
-                    self._handle_retry_exception(
-                        e, attempt, kwargs,
-                        refreshed_creds=refreshed_creds,
-                        active_profile=active_profile,
-                    )
+                should_raise, category, retry_delay, error_str, kwargs = (
+                    self._handle_retry_exception(e, attempt, kwargs, refreshed_creds=refreshed_creds)
                 )
 
                 if should_raise:
@@ -1437,10 +1356,7 @@ Respond with ONLY a valid JSON tool call in this format:
             The completion response from litellm
         """
         import litellm
-        response = self._call_with_retry(litellm.completion, **completion_params)
-        if not completion_params.get("stream"):
-            self._track_token_usage(response, self._response_model_for_tracking(response))
-        return response
+        return self._call_with_retry(litellm.completion, **completion_params)
 
     async def _acompletion_with_retry(self, **completion_params):
         """Execute litellm.acompletion with automatic retry on rate limit errors.
@@ -1455,13 +1371,7 @@ Respond with ONLY a valid JSON tool call in this format:
             The completion response from litellm
         """
         import litellm
-        response = await self._call_with_retry_async(
-            litellm.acompletion,
-            **completion_params,
-        )
-        if not completion_params.get("stream"):
-            self._track_token_usage(response, self._response_model_for_tracking(response))
-        return response
+        return await self._call_with_retry_async(litellm.acompletion, **completion_params)
 
     def _supports_web_search(self) -> bool:
         """
@@ -1847,15 +1757,8 @@ Respond with ONLY a valid JSON tool call in this format:
                 
         except (KeyError, json.JSONDecodeError, TypeError) as e:
             logging.error(f"Error parsing tool call arguments: {e}")
-            function_name = (
-                tool_call.get("function", {}).get("name")
-                if isinstance(tool_call.get("function"), dict)
-                else None
-            ) or tool_call.get("name", "unknown_function")
-            # A parse failure is NOT "no arguments". Returning {} here would run
-            # the tool with the wrong arguments and report success. Signal the
-            # failure so callers surface a tool-error instead of dispatching.
-            arguments = _TOOL_ARGUMENTS_PARSE_FAILED
+            function_name = tool_call.get("name", "unknown_function")
+            arguments = {}
             tool_call_id = tool_call.get("id", f"tool_{id(tool_call)}")
             
         return function_name, arguments, tool_call_id
@@ -2520,7 +2423,7 @@ Respond with ONLY a valid JSON tool call in this format:
         prompt: Union[str, List[Dict]],
         system_prompt: Optional[str] = None,
         chat_history: Optional[List[Dict]] = None,
-        temperature: Optional[float] = None,
+        temperature: float = 1.0,
         tools: Optional[List[Any]] = None,
         output_json: Optional[BaseModel] = None,
         output_pydantic: Optional[BaseModel] = None,
@@ -2743,11 +2646,7 @@ Respond with ONLY a valid JSON tool call in this format:
                             resp = self._call_responses_api(**responses_params)
                             response_text, tool_calls, _reasoning = self._extract_from_responses_output(resp)
 
-                            # Usage accounting is independent from metrics display.
-                            # Quiet/default agents must still update the public
-                            # token collector after a paid model call.
-                            self._track_token_usage(resp, self.model)
-
+                            # Track token usage
                             if self.metrics and hasattr(resp, 'usage') and resp.usage:
                                 usage = resp.usage
                                 tokens_in = getattr(usage, 'input_tokens', 0) or 0
@@ -2837,17 +2736,10 @@ Respond with ONLY a valid JSON tool call in this format:
                             # Execute tool calls using ToolCallExecutor (Gap 2: parallel or sequential)
                             is_ollama = self._is_ollama_provider()
                             tool_calls_batch = []
-                            parse_error_messages = []
                             
                             # Prepare batch of ToolCall objects
                             for tool_call in tool_calls:
                                 function_name, arguments, tool_call_id = self._extract_tool_call_info(tool_call, is_ollama=is_ollama)
-                                if self._tool_arguments_parse_failed(arguments):
-                                    # Do NOT dispatch with {}: surface a retryable error.
-                                    parse_error_messages.append(
-                                        self._tool_parse_error_message(function_name, tool_call_id)
-                                    )
-                                    continue
                                 tool_calls_batch.append(ToolCall(
                                     function_name=function_name,
                                     arguments=arguments,
@@ -2921,11 +2813,6 @@ Respond with ONLY a valid JSON tool call in this format:
                                     "content": content,
                                 })
 
-                            # Report any unparseable tool-call arguments so the
-                            # model can re-emit them (never dispatched with {}).
-                            for _err_msg in parse_error_messages:
-                                messages.append(_err_msg)
-
                             # Safety: break after max_iter iterations
                             if iteration_count + 1 >= max_iterations:
                                 self._last_stop_reason = "max_steps"
@@ -2982,6 +2869,10 @@ Respond with ONLY a valid JSON tool call in this format:
                                 is_reasoning=False
                             ))
                         
+                        # Track token usage
+                        if self.metrics:
+                            self._track_token_usage(final_response, self.model)
+                        
                         # Trigger llm_end callback with metrics for debug output
                         llm_latency_ms = (time.time() - current_time) * 1000
                         
@@ -3195,6 +3086,9 @@ Respond with ONLY a valid JSON tool call in this format:
                                             response_content = final_response["choices"][0]["message"].get("content")
                                             response_text = response_content if response_content is not None else ""
                                             
+                                            # Track token usage
+                                            if self.metrics:
+                                                self._track_token_usage(final_response, self.model)
                                         
                                         # Execute callbacks and display based on verbose setting
                                         if verbose and not interaction_displayed:
@@ -3384,6 +3278,9 @@ Respond with ONLY a valid JSON tool call in this format:
                                 response_content = final_response["choices"][0]["message"].get("content")
                                 response_text = response_content if response_content is not None else ""
                                 
+                                # Track token usage
+                                if self.metrics:
+                                    self._track_token_usage(final_response, self.model)
                             
                             # Execute callbacks and display based on verbose setting
                             if verbose and not interaction_displayed:
@@ -3629,11 +3526,6 @@ Respond with ONLY a valid JSON tool call in this format:
                             is_ollama = self._is_ollama_provider()
                             function_name, arguments, tool_call_id = self._extract_tool_call_info(tool_call, is_ollama)
 
-                            if self._tool_arguments_parse_failed(arguments):
-                                # Do NOT dispatch with {}: surface a retryable error.
-                                messages.append(self._tool_parse_error_message(function_name, tool_call_id))
-                                continue
-
                             # Validate and filter arguments for Ollama provider
                             if is_ollama and tools:
                                 # First check if any argument references a previous tool result
@@ -4193,7 +4085,7 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
         prompt: Union[str, List[Dict]],
         system_prompt: Optional[str] = None,
         chat_history: Optional[List[Dict]] = None,
-        temperature: Optional[float] = None,
+        temperature: float = 1.0,
         tools: Optional[List[Any]] = None,
         output_json: Optional[BaseModel] = None,
         output_pydantic: Optional[BaseModel] = None,
@@ -4378,17 +4270,10 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                         # Execute tool calls using ToolCallExecutor (Gap 2: parallel or sequential)
                         is_ollama = self._is_ollama_provider()
                         tool_calls_batch = []
-                        parse_error_messages = []
                         
                         # Prepare batch of ToolCall objects
                         for tool_call in tool_calls:
                             function_name, arguments, tool_call_id = self._extract_tool_call_info(tool_call, is_ollama)
-                            if self._tool_arguments_parse_failed(arguments):
-                                # Do NOT dispatch with {}: surface a retryable error.
-                                parse_error_messages.append(
-                                    self._tool_parse_error_message(function_name, tool_call_id)
-                                )
-                                continue
                             tool_calls_batch.append(ToolCall(
                                 function_name=function_name,
                                 arguments=arguments, 
@@ -4428,11 +4313,6 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                                     tool_result.is_ollama
                                 )
                             messages.append(tool_message)
-
-                        # Report any unparseable tool-call arguments so the
-                        # model can re-emit them (never dispatched with {}).
-                        for _err_msg in parse_error_messages:
-                            messages.append(_err_msg)
                         
                         # Continue conversation after tool execution - get follow-up response
                         try:
@@ -4540,7 +4420,7 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
         prompt: Union[str, List[Dict]],
         system_prompt: Optional[str] = None,
         chat_history: Optional[List[Dict]] = None,
-        temperature: Optional[float] = None,
+        temperature: float = 1.0,
         tools: Optional[List[Any]] = None,
         output_json: Optional[BaseModel] = None,
         output_pydantic: Optional[BaseModel] = None,
@@ -4770,10 +4650,6 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                         
                         for tool_call in tool_calls:
                             function_name, arguments, tool_call_id = self._extract_tool_call_info(tool_call)
-                            if self._tool_arguments_parse_failed(arguments):
-                                # Do NOT dispatch with {}: surface a retryable error.
-                                messages.append(self._tool_parse_error_message(function_name, tool_call_id))
-                                continue
                             logging.debug(f"[RESPONSES_API_ASYNC] Executing tool {function_name}")
                             tool_result = await _dispatch_async_tool(
                                 execute_tool_fn,
@@ -5023,11 +4899,6 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                         is_ollama = self._is_ollama_provider()
                         function_name, arguments, tool_call_id = self._extract_tool_call_info(tool_call, is_ollama)
 
-                        if self._tool_arguments_parse_failed(arguments):
-                            # Do NOT dispatch with {}: surface a retryable error.
-                            messages.append(self._tool_parse_error_message(function_name, tool_call_id))
-                            continue
-
                         # Validate and filter arguments for Ollama provider
                         if is_ollama and tools:
                             arguments = self._validate_and_filter_ollama_arguments(function_name, arguments, tools)
@@ -5543,66 +5414,27 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                 litellm.callbacks.append(event)
         self._registered_callbacks = list(events)
 
-    def _track_token_usage(self, response: Any, model: str) -> Optional[TokenMetrics]:
+    def _track_token_usage(self, response: Dict[str, Any], model: str) -> Optional[TokenMetrics]:
         """Extract and track token usage from LLM response."""
         if not TokenMetrics or not get_token_collector:
             return None
-
+        
+        # Note: metrics check moved to call sites for performance
+        # This method should only be called when self.metrics=True
+        
         try:
-            if isinstance(response, dict):
-                usage = response.get("usage", {})
-            else:
-                usage = getattr(response, "usage", None)
+            usage = response.get("usage", {})
             if not usage:
                 return None
-
-            def _usage_value(*names: str) -> int:
-                for name in names:
-                    if isinstance(usage, dict):
-                        value = usage.get(name)
-                    else:
-                        value = getattr(usage, name, None)
-                    if value is not None:
-                        return int(value or 0)
-                return 0
-
-            def _detail_value(detail_names: tuple[str, ...], name: str) -> int:
-                for detail_name in detail_names:
-                    details = (
-                        usage.get(detail_name)
-                        if isinstance(usage, dict)
-                        else getattr(usage, detail_name, None)
-                    )
-                    if details:
-                        value = (
-                            details.get(name)
-                            if isinstance(details, dict)
-                            else getattr(details, name, None)
-                        )
-                        if value is not None:
-                            return int(value or 0)
-                return 0
-
+            
             # Extract token counts
             metrics = TokenMetrics(
-                input_tokens=_usage_value("prompt_tokens", "input_tokens"),
-                output_tokens=_usage_value("completion_tokens", "output_tokens"),
-                cached_tokens=_usage_value("cached_tokens") or _detail_value(
-                    ("prompt_tokens_details", "input_tokens_details"),
-                    "cached_tokens",
-                ),
-                reasoning_tokens=_usage_value("reasoning_tokens") or _detail_value(
-                    ("completion_tokens_details", "output_tokens_details"),
-                    "reasoning_tokens",
-                ),
-                audio_input_tokens=_usage_value("audio_input_tokens") or _detail_value(
-                    ("prompt_tokens_details", "input_tokens_details"),
-                    "audio_tokens",
-                ),
-                audio_output_tokens=_usage_value("audio_output_tokens") or _detail_value(
-                    ("completion_tokens_details", "output_tokens_details"),
-                    "audio_tokens",
-                ),
+                input_tokens=usage.get("prompt_tokens", 0),
+                output_tokens=usage.get("completion_tokens", 0),
+                cached_tokens=usage.get("cached_tokens", 0),
+                reasoning_tokens=usage.get("reasoning_tokens", 0),
+                audio_input_tokens=usage.get("audio_input_tokens", 0),
+                audio_output_tokens=usage.get("audio_output_tokens", 0)
             )
             
             # Store metrics
@@ -5738,16 +5570,6 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
         
         # Override with any provided parameters
         params.update(override_params)
-
-        # Resolve temperature from the instance when the caller did not specify
-        # one. Public entry points now default temperature to None so a value
-        # configured via Agent(llm={'temperature': ...}) actually reaches the
-        # request instead of being silently overridden by a hardcoded 1.0.
-        if params.get("temperature") is None:
-            if self.temperature is not None:
-                params["temperature"] = self.temperature
-            else:
-                params.pop("temperature", None)
         
         # Handle structured output parameters
         output_json = override_params.get('output_json')
@@ -6023,16 +5845,7 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                         "output": msg.get("content", ""),
                     })
                 else:
-                    # Translate Chat Completions multimodal content parts
-                    # (type=text / image_url) into Responses API parts
-                    # (input_text / input_image); local image paths become
-                    # data URLs. Plain-string content is passed through.
-                    from .openai_client import OpenAIClient
-                    item = dict(msg)
-                    item["content"] = OpenAIClient._build_responses_content(
-                        msg.get("content", "")
-                    )
-                    input_items.append(item)
+                    input_items.append(msg)
 
         if instructions:
             params["instructions"] = instructions
@@ -6080,19 +5893,6 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
         if self.timeout:
             params["timeout"] = self.timeout
 
-        # ── Subscription credentials ────────────────────────────────────
-        # Mirror _build_completion_params: without this the Responses API
-        # transport silently ignores auth= and bills the plain API key.
-        creds = self._resolve_subscription_creds()
-        if creds:
-            params["api_key"] = creds.api_key
-            if creds.base_url:
-                params["base_url"] = creds.base_url
-            if creds.headers:
-                extra_headers = dict(params.get("extra_headers") or {})
-                extra_headers.update(creds.headers)
-                params["extra_headers"] = extra_headers
-
         # ── Structured output ───────────────────────────────────────────
         output_json = kwargs.pop("output_json", None)
         output_pydantic = kwargs.pop("output_pydantic", None)
@@ -6142,9 +5942,7 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
         Returns a ``ResponsesAPIResponse`` object.
         """
         import litellm
-        response = await self._call_with_retry_async(litellm.aresponses, **params)
-        self._track_token_usage(response, self._response_model_for_tracking(response))
-        return response
+        return await self._call_with_retry_async(litellm.aresponses, **params)
 
     def _extract_from_responses_output(self, response) -> tuple:
         """
@@ -6382,17 +6180,6 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                         is_reasoning=False,
                     ))
 
-            elif evt_type == "response.reasoning_summary_text.delta":
-                delta_text = (event.get("delta", "") if isinstance(event, dict)
-                              else getattr(event, "delta", ""))
-                if _emit and delta_text:
-                    stream_callback(StreamEvent(
-                        type=StreamEventType.DELTA_TEXT,
-                        timestamp=time.perf_counter(),
-                        content=delta_text,
-                        is_reasoning=True,
-                    ))
-
             elif evt_type == "response.function_call_arguments.delta":
                 idx = (event.get("output_index", 0) if isinstance(event, dict)
                        else getattr(event, "output_index", 0))
@@ -6505,41 +6292,17 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                 tool_call_id = tool_call.id
             except (json.JSONDecodeError, AttributeError) as e:
                 logging.error(f"Error parsing object-style tool call: {e}")
-                function_name = getattr(getattr(tool_call, 'function', None), 'name', None) or "unknown_function"
-                # See _parse_tool_call_arguments: a parse failure is not {}.
-                arguments = _TOOL_ARGUMENTS_PARSE_FAILED
-                tool_call_id = getattr(tool_call, 'id', None) or f"tool_{id(tool_call)}"
+                function_name = "unknown_function"
+                arguments = {}
+                tool_call_id = f"tool_{id(tool_call)}"
             return function_name, arguments, tool_call_id
 
-    @staticmethod
-    def _tool_arguments_parse_failed(arguments) -> bool:
-        """True when tool-call arguments could not be parsed (vs. legitimately empty)."""
-        return arguments is _TOOL_ARGUMENTS_PARSE_FAILED
-
-    @staticmethod
-    def _tool_parse_error_message(function_name: str, tool_call_id: str) -> Dict[str, str]:
-        """Build a tool-role message telling the model its arguments were lost.
-
-        Surfacing this instead of dispatching with {} converts a silent
-        wrong-action-reported-as-success into a visible, retryable error.
-        """
-        return {
-            "role": "tool",
-            "tool_call_id": tool_call_id,
-            "content": (
-                f"Error: arguments for tool '{function_name}' could not be parsed "
-                f"(the argument string was invalid or truncated). "
-                f"The tool was NOT executed. Please re-emit the tool call with "
-                f"complete, valid JSON arguments."
-            ),
-        }
-
     # Response without tool calls
     def response(
         self,
         prompt: Union[str, List[Dict]],
         system_prompt: Optional[str] = None,
-        temperature: Optional[float] = None,
+        temperature: float = 1.0,
         stream: bool = True,
         verbose: bool = True,
         markdown: bool = True,
@@ -6633,7 +6396,7 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
         self,
         prompt: Union[str, List[Dict]],
         system_prompt: Optional[str] = None,
-        temperature: Optional[float] = None,
+        temperature: float = 1.0,
         stream: bool = True,
         verbose: bool = True,
         markdown: bool = True,
@@ -6728,23 +6491,6 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
         if callable(function_or_name):
             # Function object passed directly
             func = function_or_name
-            # If it's a BaseTool/FunctionTool instance, honour its declared schema
-            # (respects @tool name= override and excludes Injected[T] params) instead
-            # of re-deriving from the raw wrapped function's signature.
-            if hasattr(func, 'get_schema'):
-                tool_def = func.get_schema()
-                if (
-                    isinstance(tool_def, dict)
-                    and isinstance(tool_def.get("function"), dict)
-                    and isinstance(tool_def["function"].get("parameters"), dict)
-                ):
-                    tool_def = tool_def.copy()
-                    tool_def["function"] = tool_def["function"].copy()
-                    tool_def["function"]["parameters"] = self._fix_array_schemas(
-                        tool_def["function"]["parameters"]
-                    )
-                logging.debug(f"Generated tool definition from get_schema(): {tool_def}")
-                return tool_def
             function_name = func.__name__
             logging.debug(f"Generating tool definition for callable: {function_name}")
         else:

src/praisonai-agents/praisonaiagents/llm/openai_client.py

@@ -6,9 +6,7 @@ supporting both synchronous and asynchronous operations.
 """
 
 import os
-import base64
 import logging
-import mimetypes
 from praisonaiagents._logging import get_logger
 import time
 import json
@@ -18,7 +16,6 @@ from typing import Any, Dict, List, Optional, Union, AsyncIterator, Iterator, Ca
 from pydantic import BaseModel
 from dataclasses import dataclass
 import inspect
-from pathlib import Path
 
 from ..errors import ToolExecutionError
 
@@ -37,54 +34,6 @@ def _durable_iteration_kwargs(execute_tool_fn: Callable, index: int) -> Dict[str
         return {"_durable_iteration_index": index}
     return {}
 
-
-def _handle_native_deferred_result(
-    tool_result: Any,
-    messages: List[Dict],
-    tool_call_id: Optional[str],
-    function_name: str,
-    history_sink: Optional[List[Dict]] = None,
-) -> Any:
-    """Register a directly-returned ``DeferredToolResult`` on the native path.
-
-    Parity with the LiteLLM loop (``llm.py:_register_deferred_if_any``): a tool
-    may return a ``DeferredToolResult`` to signal "started; will resolve later".
-    On the native OpenAI-SDK loop the value was previously stringified and the
-    handle lost, so the eventual background result was never re-injected. Here
-    we register the handle on the shared resolver so a later
-    ``resolve_deferred(handle_id, value)`` appends a follow-up tool message that
-    a subsequent turn will replay, and surface the ``note`` to the model now.
-
-    The re-injection target is ``history_sink`` when provided — this must be the
-    caller's *durable* conversation history (e.g. the agent's ``chat_history``),
-    since the background job typically completes after this native loop has
-    already returned and its per-call ``messages`` copy has been discarded. When
-    no durable sink is given we fall back to ``messages`` (correct only if the
-    handle resolves while the loop is still open), preserving prior behaviour.
-
-    Returns the value to record for this turn (the deferred ``note`` string when
-    deferred, otherwise the unchanged ``tool_result``). Never raises.
-    """
-    from ..tools.call_executor import DeferredToolResult
-    if not isinstance(tool_result, DeferredToolResult):
-        return tool_result
-    try:
-        from ..tools.call_executor import get_deferred_resolver
-        resolver = get_deferred_resolver()
-        sink = history_sink if history_sink is not None else messages
-
-        def _reinject(handle_id: str, value: Any, session_id: Optional[str]) -> None:
-            sink.append({
-                "role": "tool",
-                "tool_call_id": tool_call_id,
-                "content": f"[deferred:{function_name}] {value}",
-            })
-
-        resolver.register_if_absent(tool_result.handle_id, _reinject)
-    except Exception as e:  # noqa: BLE001 — registration must never break the turn
-        logging.debug("Native deferred registration skipped (non-fatal): %s", e)
-    return tool_result.note
-
 # Lazy imports for optional dependencies
 _openai_module = None
 _rich_console = None
@@ -200,26 +149,6 @@ class ToolCall:
     type: str
     function: Dict[str, Any]
 
-def _extract_tool_call_name_and_args(tool_call):
-    """Parse a tool call's function name and JSON arguments.
-
-    Handles both the ToolCall dataclass and OpenAI-SDK objects. Returns a
-    tuple of (name, args, tool_call_id, err); err is None on success and the
-    caught exception otherwise. Callers keep their own failure handling.
-    """
-    tool_call_id = tool_call.id if hasattr(tool_call, 'id') else tool_call.get('id')
-    function_name = None
-    try:
-        if isinstance(tool_call, ToolCall):
-            function_name = tool_call.function["name"]
-            raw_arguments = tool_call.function["arguments"]
-        else:
-            function_name = tool_call.function.name
-            raw_arguments = tool_call.function.arguments
-        return function_name, json.loads(raw_arguments), tool_call_id, None
-    except (json.JSONDecodeError, KeyError, AttributeError, TypeError) as e:
-        return function_name, None, tool_call_id, e
-
 def process_stream_chunks(chunks):
     """Process streaming chunks into combined response"""
     if not chunks:
@@ -397,11 +326,6 @@ class OpenAIClient:
         self._formatted_tools_cache = {}
         self._fixed_schema_cache = {}
         self._max_cache_size = 100
-
-        # Token usage from the most recent completion (Issue #3933). Populated
-        # regardless of any display/metrics flag so headless callers and CLI
-        # envelopes can read real spend after a successful run.
-        self.last_token_metrics = None
     
     @property
     def console(self):
@@ -751,11 +675,7 @@ class OpenAIClient:
                         "output": msg.get("content", ""),
                     })
                 else:
-                    item = dict(msg)
-                    item["content"] = self._build_responses_content(
-                        msg.get("content", "")
-                    )
-                    input_items.append(item)
+                    input_items.append(msg)
 
         if instructions:
             params["instructions"] = instructions
@@ -789,65 +709,6 @@ class OpenAIClient:
 
         return params
 
-    @staticmethod
-    def _normalise_responses_image_url(image_url: Any) -> str:
-        """Return an API-fetchable URL, encoding local image files as data URLs."""
-        if isinstance(image_url, dict):
-            image_url = image_url.get("url", "")
-        if not isinstance(image_url, str) or not image_url:
-            raise ValueError("Image content must include a non-empty URL or local path")
-        if image_url.startswith(("http://", "https://", "data:")):
-            return image_url
-
-        image_path = Path(image_url).expanduser()
-        if not image_path.is_file():
-            raise FileNotFoundError(
-                f"Local image file does not exist: {image_path}"
-            )
-        mime_type = mimetypes.guess_type(image_path.name)[0]
-        if not mime_type or not mime_type.startswith("image/"):
-            raise ValueError(f"Unsupported local image type: {image_path}")
-        encoded = base64.b64encode(image_path.read_bytes()).decode("ascii")
-        return f"data:{mime_type};base64,{encoded}"
-
-    @classmethod
-    def _build_responses_content(cls, content: Any) -> Any:
-        """Translate Chat Completions content parts to Responses API parts."""
-        if not isinstance(content, list):
-            return content
-
-        responses_content: List[Any] = []
-        for part in content:
-            if not isinstance(part, dict):
-                responses_content.append(part)
-                continue
-            part_type = part.get("type")
-            if part_type == "text":
-                responses_content.append({
-                    "type": "input_text",
-                    "text": part.get("text", ""),
-                })
-            elif part_type == "image_url":
-                image_item = {
-                    "type": "input_image",
-                    "image_url": cls._normalise_responses_image_url(
-                        part.get("image_url")
-                    ),
-                }
-                image_value = part.get("image_url")
-                if isinstance(image_value, dict) and image_value.get("detail"):
-                    image_item["detail"] = image_value["detail"]
-                responses_content.append(image_item)
-            elif part_type == "input_image":
-                item = dict(part)
-                item["image_url"] = cls._normalise_responses_image_url(
-                    part.get("image_url")
-                )
-                responses_content.append(item)
-            else:
-                responses_content.append(part)
-        return responses_content
-
     def _responses_to_chat_completion(self, response) -> ChatCompletion:
         """
         Wrap a Responses API response into a ChatCompletion dataclass
@@ -1029,8 +890,6 @@ class OpenAIClient:
                         ))
                     
                     return final_response
-                except (FileNotFoundError, ValueError):
-                    raise
                 except Exception as e:
                     self.logger.warning(f"Responses API streaming failed, falling back: {e}")
                     # Fall through to Chat Completions streaming
@@ -1298,8 +1157,6 @@ class OpenAIClient:
                         ))
                     
                     return final_response
-                except (FileNotFoundError, ValueError):
-                    raise
                 except Exception as e:
                     self.logger.warning(f"Responses API async streaming failed, falling back: {e}")
                     # Fall through to Chat Completions streaming
@@ -1460,81 +1317,7 @@ class OpenAIClient:
         except Exception as e:
             self.logger.error(f"Error in async stream processing: {e}")
             return None
-
-    def _track_token_usage(self, response: Any, model: str, agent_name: Optional[str] = None) -> None:
-        """Record token usage from a response into the global collector.
-
-        Usage accounting is independent from any metrics/verbose display flag:
-        a quiet default agent must still populate the public token collector
-        after a paid model call (Issue #3933). This is a cheap dict/attr read
-        plus a collector add — the expensive HTTP call is already paid.
-        """
-        try:
-            from ..telemetry.token_collector import get_token_collector, TokenMetrics
-        except Exception:
-            return
-        try:
-            usage = response.get("usage") if isinstance(response, dict) else getattr(response, "usage", None)
-            if not usage:
-                # No usage on this response (e.g. assembled stream chunks): clear
-                # any stale per-call metrics so envelopes never report a prior
-                # completion's spend as this call's usage.
-                self.last_token_metrics = None
-                return
-
-            def _val(*names: str) -> int:
-                for name in names:
-                    value = usage.get(name) if isinstance(usage, dict) else getattr(usage, name, None)
-                    if value is not None:
-                        return int(value or 0)
-                return 0
-
-            def _detail(detail_names: tuple, name: str) -> int:
-                for detail_name in detail_names:
-                    details = (
-                        usage.get(detail_name)
-                        if isinstance(usage, dict)
-                        else getattr(usage, detail_name, None)
-                    )
-                    if details:
-                        value = (
-                            details.get(name)
-                            if isinstance(details, dict)
-                            else getattr(details, name, None)
-                        )
-                        if value is not None:
-                            return int(value or 0)
-                return 0
-
-            metrics = TokenMetrics(
-                input_tokens=_val("prompt_tokens", "input_tokens"),
-                output_tokens=_val("completion_tokens", "output_tokens"),
-                cached_tokens=_val("cached_tokens") or _detail(
-                    ("prompt_tokens_details", "input_tokens_details"), "cached_tokens"
-                ),
-                reasoning_tokens=_val("reasoning_tokens") or _detail(
-                    ("completion_tokens_details", "output_tokens_details"), "reasoning_tokens"
-                ),
-                audio_input_tokens=_val("audio_input_tokens") or _detail(
-                    ("prompt_tokens_details", "input_tokens_details"), "audio_tokens"
-                ),
-                audio_output_tokens=_val("audio_output_tokens") or _detail(
-                    ("completion_tokens_details", "output_tokens_details"), "audio_tokens"
-                ),
-            )
-            if metrics.total_tokens == 0:
-                self.last_token_metrics = None
-                return
-            self.last_token_metrics = metrics
-            get_token_collector().track_tokens(
-                model=model,
-                agent=agent_name,
-                metrics=metrics,
-                metadata={"provider": "openai", "stream": False},
-            )
-        except Exception:
-            pass
-
+    
     def create_completion(
         self,
         messages: List[Dict[str, Any]],
@@ -1569,8 +1352,6 @@ class OpenAIClient:
                 )
                 raw = self.sync_client.responses.create(**resp_params)
                 return self._responses_to_chat_completion(raw)
-            except (FileNotFoundError, ValueError):
-                raise
             except Exception as e:
                 self.logger.warning(f"Responses API failed, falling back to Chat Completions: {e}")
                 # Fall through to Chat Completions
@@ -1579,13 +1360,10 @@ class OpenAIClient:
         params = {
             "model": model,
             "messages": messages,
+            "temperature": temperature,
             "stream": stream,
             **kwargs
         }
-        # Omit temperature when unset so the provider default applies rather
-        # than sending an explicit None.
-        if temperature is not None:
-            params["temperature"] = temperature
         
         # Add tools if provided
         if tools:
@@ -1633,8 +1411,6 @@ class OpenAIClient:
                 )
                 raw = await self.async_client.responses.create(**resp_params)
                 return self._responses_to_chat_completion(raw)
-            except (FileNotFoundError, ValueError):
-                raise
             except Exception as e:
                 self.logger.warning(f"Responses API failed, falling back to Chat Completions: {e}")
                 # Fall through to Chat Completions
@@ -1643,13 +1419,10 @@ class OpenAIClient:
         params = {
             "model": model,
             "messages": messages,
+            "temperature": temperature,
             "stream": stream,
             **kwargs
         }
-        # Omit temperature when unset so the provider default applies rather
-        # than sending an explicit None.
-        if temperature is not None:
-            params["temperature"] = temperature
         
         # Add tools if provided
         if tools:
@@ -1678,7 +1451,6 @@ class OpenAIClient:
         max_iterations: int = 10,
         stream_callback: Optional[Callable] = None,
         emit_events: bool = False,
-        agent_name: Optional[str] = None,
         **kwargs
     ) -> Optional[ChatCompletion]:
         """
@@ -1715,11 +1487,6 @@ class OpenAIClient:
         # path so /stop and live steering work on the OpenAI-native loop too.
         cancel_token = kwargs.pop("cancel_token", None)
         steering_drain = kwargs.pop("steering_drain", None)
-        # Durable sink for deferred tool re-injection: the caller's persistent
-        # conversation history (e.g. the agent's ``chat_history``). Background
-        # jobs usually complete after this loop returns, so late results must
-        # land in a list a subsequent turn replays — not the per-call copy below.
-        deferred_history_sink = kwargs.pop("deferred_history_sink", None)
 
         def _is_cancelled() -> bool:
             return cancel_token is not None and getattr(cancel_token, "is_set", lambda: False)()
@@ -1849,13 +1616,7 @@ class OpenAIClient:
             
             if not final_response:
                 return None
-
-            # Record usage for THIS billed completion. Every tool-loop iteration
-            # is a separate paid call, so accounting must happen per iteration —
-            # not once after the loop — or intermediate completions are dropped
-            # from session totals and by_model/by_agent rollups (Issue #3933).
-            self._track_token_usage(final_response, model, agent_name)
-
+            
             # Trigger llm_end callback with metrics for debug output
             llm_end_time = time.perf_counter()
             llm_latency_ms = (llm_end_time - start_time) * 1000
@@ -1932,19 +1693,13 @@ class OpenAIClient:
                 # replies for this turn (keeps tool replies consecutive).
                 _deferred_media_followups = []
                 for tool_call in tool_calls:
-                    # Handle both ToolCall dataclass and OpenAI object.
-                    # Guard the parse itself so malformed/truncated argument
-                    # JSON is reported back to the model instead of aborting
-                    # the whole run (matches chat_completion_with_tools_stream).
-                    function_name, arguments, _tool_call_id, err = _extract_tool_call_name_and_args(tool_call)
-                    if err is not None:
-                        logging.warning(f"Failed to parse tool call arguments: {err}")
-                        messages.append({
-                            "role": "tool",
-                            "tool_call_id": _tool_call_id,
-                            "content": json.dumps({"error": f"Invalid arguments JSON: {err}"}),
-                        })
-                        continue
+                    # Handle both ToolCall dataclass and OpenAI object
+                    if isinstance(tool_call, ToolCall):
+                        function_name = tool_call.function["name"]
+                        arguments = json.loads(tool_call.function["arguments"])
+                    else:
+                        function_name = tool_call.function.name
+                        arguments = json.loads(tool_call.function.arguments)
                     
                     # Always trigger callback for tool call tracking (even when verbose=False)
                     display_tool_call_fn = _get_display_tool_call()
@@ -1953,6 +1708,7 @@ class OpenAIClient:
                     # Capture failures and report them back to the model instead of
                     # aborting the whole run (safe-by-default, matching the streaming
                     # path chat_completion_with_tools_stream).
+                    _tool_call_id = tool_call.id if hasattr(tool_call, 'id') else tool_call.get('id')
                     try:
                         tool_result = execute_tool_fn(
                             function_name,
@@ -1967,12 +1723,6 @@ class OpenAIClient:
                     except Exception as tool_error:
                         logging.warning(f"Tool '{function_name}' failed: {tool_error}")
                         tool_result = {"error": str(tool_error)}
-                    # Parity with the LiteLLM loop: register a deferred handle so
-                    # its eventual background value is re-injected, not lost.
-                    tool_result = _handle_native_deferred_result(
-                        tool_result, messages, _tool_call_id, function_name,
-                        history_sink=deferred_history_sink,
-                    )
                     try:
                         results_str = json.dumps(tool_result) if tool_result else "Function returned an empty output"
                     except (TypeError, ValueError):
@@ -2014,9 +1764,7 @@ class OpenAIClient:
             else:
                 # No tool calls, we're done
                 break
-
-        # Usage is recorded per iteration inside the loop above so every billed
-        # completion (including intermediate tool-call rounds) is accounted for.
+        
         return final_response
     
     async def achat_completion_with_tools(
@@ -2034,7 +1782,6 @@ class OpenAIClient:
         max_iterations: int = 10,
         stream_callback: Optional[Callable] = None,
         emit_events: bool = False,
-        agent_name: Optional[str] = None,
         **kwargs
     ) -> Optional[ChatCompletion]:
         """
@@ -2065,8 +1812,6 @@ class OpenAIClient:
         # path so /stop and live steering work on the OpenAI-native loop too.
         cancel_token = kwargs.pop("cancel_token", None)
         steering_drain = kwargs.pop("steering_drain", None)
-        # Durable sink for deferred tool re-injection (see sync counterpart).
-        deferred_history_sink = kwargs.pop("deferred_history_sink", None)
 
         def _is_cancelled() -> bool:
             return cancel_token is not None and getattr(cancel_token, "is_set", lambda: False)()
@@ -2184,12 +1929,6 @@ class OpenAIClient:
             if not final_response:
                 return None
 
-            # Record usage for THIS billed completion. Every tool-loop iteration
-            # is a separate paid call, so accounting must happen per iteration —
-            # not once after the loop — or intermediate completions are dropped
-            # from session totals and by_model/by_agent rollups (Issue #3933).
-            self._track_token_usage(final_response, model, agent_name)
-
             # Check for tool calls
             if not final_response.choices or final_response.choices[0].message is None:
                 raise ValueError("LLM returned empty or filtered response")
@@ -2240,19 +1979,13 @@ class OpenAIClient:
                 # replies for this turn (keeps tool replies consecutive).
                 _deferred_media_followups = []
                 for tool_call in tool_calls:
-                    # Handle both ToolCall dataclass and OpenAI object.
-                    # Guard the parse itself so malformed/truncated argument
-                    # JSON is reported back to the model instead of aborting
-                    # the whole run (matches chat_completion_with_tools_stream).
-                    function_name, arguments, _tool_call_id, err = _extract_tool_call_name_and_args(tool_call)
-                    if err is not None:
-                        logging.warning(f"Failed to parse tool call arguments: {err}")
-                        messages.append({
-                            "role": "tool",
-                            "tool_call_id": _tool_call_id,
-                            "content": json.dumps({"error": f"Invalid arguments JSON: {err}"}),
-                        })
-                        continue
+                    # Handle both ToolCall dataclass and OpenAI object
+                    if isinstance(tool_call, ToolCall):
+                        function_name = tool_call.function["name"]
+                        arguments = json.loads(tool_call.function["arguments"])
+                    else:
+                        function_name = tool_call.function.name
+                        arguments = json.loads(tool_call.function.arguments)
                     
                     # Always trigger callback for tool call tracking (even when verbose=False)
                     display_tool_call_fn = _get_display_tool_call()
@@ -2265,6 +1998,7 @@ class OpenAIClient:
                     # Capture failures and report them back to the model instead of
                     # aborting the whole run (safe-by-default, matching the streaming
                     # path chat_completion_with_tools_stream).
+                    _tool_call_id = tool_call.id if hasattr(tool_call, 'id') else tool_call.get('id')
                     try:
                         if asyncio.iscoroutinefunction(execute_tool_fn):
                             tool_result = await execute_tool_fn(
@@ -2298,12 +2032,6 @@ class OpenAIClient:
                         logging.warning(f"Tool '{function_name}' failed: {tool_error}")
                         tool_result = {"error": str(tool_error)}
 
-                    # Parity with the LiteLLM loop: register a deferred handle so
-                    # its eventual background value is re-injected, not lost.
-                    tool_result = _handle_native_deferred_result(
-                        tool_result, messages, _tool_call_id, function_name,
-                        history_sink=deferred_history_sink,
-                    )
                     try:
                         results_str = json.dumps(tool_result) if tool_result else "Function returned an empty output"
                     except (TypeError, ValueError):
@@ -2337,9 +2065,7 @@ class OpenAIClient:
             else:
                 # No tool calls, we're done
                 break
-
-        # Usage is recorded per iteration inside the loop above so every billed
-        # completion (including intermediate tool-call rounds) is accounted for.
+        
         return final_response
         
     def chat_completion_with_tools_stream(
@@ -2378,8 +2104,6 @@ class OpenAIClient:
         Yields:
             String chunks of the response as they are generated
         """
-        # Durable sink for deferred tool re-injection (see sync counterpart).
-        deferred_history_sink = kwargs.pop("deferred_history_sink", None)
         # Format tools for OpenAI API
         formatted_tools = self.format_tools(tools)
         
@@ -2487,14 +2211,16 @@ class OpenAIClient:
                     _deferred_media_followups = []
                     for tool_call in tool_calls:
                         # Handle both ToolCall dataclass and OpenAI object
-                        function_name, arguments, _, err = _extract_tool_call_name_and_args(tool_call)
-                        if err is not None:
-                            # Preserve original behaviour: only malformed JSON is
-                            # reported to the caller; other errors propagate.
-                            if not isinstance(err, json.JSONDecodeError):
-                                raise err
+                        try:
+                            if isinstance(tool_call, ToolCall):
+                                function_name = tool_call.function["name"]
+                                arguments = json.loads(tool_call.function["arguments"])
+                            else:
+                                function_name = tool_call.function.name
+                                arguments = json.loads(tool_call.function.arguments)
+                        except json.JSONDecodeError as e:
                             if verbose:
-                                yield f"\n[Error parsing arguments for {function_name if function_name is not None else 'unknown function'}: {str(err)}]"
+                                yield f"\n[Error parsing arguments for {function_name if 'function_name' in locals() else 'unknown function'}: {str(e)}]"
                             continue
                         
                         # Always trigger callback for tool call tracking (even when verbose=False)
@@ -2515,12 +2241,6 @@ class OpenAIClient:
                                     execute_tool_fn, iteration_count
                                 ),
                             )
-                            # Parity with the LiteLLM loop: register a deferred
-                            # handle so its eventual value is re-injected.
-                            tool_result = _handle_native_deferred_result(
-                                tool_result, messages, _tool_call_id, function_name,
-                                history_sink=deferred_history_sink,
-                            )
                             results_str = json.dumps(tool_result) if tool_result else "Function returned an empty output"
                         except ToolExecutionError:
                             raise

src/praisonai-agents/praisonaiagents/llm/quota.py

@@ -1,137 +0,0 @@
-"""
-Provider Quota Coordination for PraisonAI Agents.
-
-Provides a lightweight, protocol-driven seam so provider-quota state
-(credential cooldowns / benches) can be coordinated *fleet-wide* when a
-shared backend is configured, while defaulting to today's in-process,
-in-memory behaviour with zero new dependencies and no hot-path change.
-
-Design:
-- ``QuotaCoordinatorProtocol`` is a pure contract (stdlib + typing only).
-- ``LocalQuotaCoordinator`` is the default in-memory implementation used
-  when no shared backend is selected — single-replica deployments behave
-  exactly as before.
-- A concrete shared backend (e.g. Redis, reusing the gateway's existing
-  connection) implements the same protocol in the wrapper/bot package and
-  is selected via ``QuotaCoordinatorConfig``. Core keeps only the protocol
-  and the in-memory default.
-
-Fail-open by contract: implementations MUST degrade to local behaviour on
-backend errors rather than wedge a healthy request path, and bench entries
-carry TTLs so a dead replica's benches self-expire.
-"""
-
-from __future__ import annotations
-
-import time
-from dataclasses import dataclass
-from typing import Dict, Optional, Protocol, runtime_checkable
-
-
-@runtime_checkable
-class QuotaCoordinatorProtocol(Protocol):
-    """Contract for coordinating provider-quota state across replicas.
-
-    A coordinator tracks per-credential cooldowns ("benches"). When a shared
-    backend is configured, a credential benched by any replica is treated as
-    benched by all replicas until its cooldown expires.
-    """
-
-    def bench(self, cred_id: str, *, until: float, reason: str = "") -> None:
-        """Bench a credential until ``until`` (an epoch timestamp, TTL-based)."""
-        ...
-
-    def is_benched(self, cred_id: str, *, now: Optional[float] = None) -> bool:
-        """Return True if the credential is currently benched."""
-        ...
-
-    def benched_until(self, cred_id: str, *, now: Optional[float] = None) -> Optional[float]:
-        """Return the epoch timestamp the credential is benched until, or None."""
-        ...
-
-    def clear(self, cred_id: str) -> None:
-        """Clear any bench for the credential (e.g. on recovery)."""
-        ...
-
-
-@dataclass
-class QuotaCoordinatorConfig:
-    """Configuration for provider-quota coordination.
-
-    Attributes:
-        backend: ``"local"`` (in-memory, default) or a shared backend name
-            such as ``"redis"`` provided by the wrapper/bot package.
-        url: Optional backend URL; when omitted a shared backend reuses the
-            already-established connection (e.g. gateway ``RedisConfig``).
-    """
-
-    backend: str = "local"
-    url: Optional[str] = None
-
-    def to_dict(self) -> Dict[str, Optional[str]]:
-        return {"backend": self.backend, "url": self.url}
-
-    @classmethod
-    def from_dict(cls, data: Dict[str, Optional[str]]) -> "QuotaCoordinatorConfig":
-        return cls(
-            backend=(data.get("backend") or "local"),
-            url=data.get("url"),
-        )
-
-
-class LocalQuotaCoordinator:
-    """In-memory ``QuotaCoordinatorProtocol`` (default, zero-dependency).
-
-    Thread-safe via a lightweight lock. Bench entries carry an expiry so
-    they self-clear once the cooldown passes — mirroring the TTL semantics a
-    shared backend uses so behaviour is identical across implementations.
-    """
-
-    def __init__(self) -> None:
-        import threading
-
-        self._benches: Dict[str, float] = {}
-        self._lock = threading.Lock()
-
-    def bench(self, cred_id: str, *, until: float, reason: str = "") -> None:
-        with self._lock:
-            existing = self._benches.get(cred_id)
-            # Keep the longest cooldown if a longer one is already set.
-            if existing is None or until > existing:
-                self._benches[cred_id] = until
-
-    def is_benched(self, cred_id: str, *, now: Optional[float] = None) -> bool:
-        return self.benched_until(cred_id, now=now) is not None
-
-    def benched_until(self, cred_id: str, *, now: Optional[float] = None) -> Optional[float]:
-        current = time.time() if now is None else now
-        with self._lock:
-            until = self._benches.get(cred_id)
-            if until is None:
-                return None
-            if current >= until:
-                # Expired — self-clear.
-                self._benches.pop(cred_id, None)
-                return None
-            return until
-
-    def clear(self, cred_id: str) -> None:
-        with self._lock:
-            self._benches.pop(cred_id, None)
-
-
-def build_quota_coordinator(
-    config: Optional[QuotaCoordinatorConfig] = None,
-) -> QuotaCoordinatorProtocol:
-    """Build a coordinator from config, defaulting to the local in-memory one.
-
-    Only the ``"local"`` backend is resolvable from core. Shared backends
-    (e.g. ``"redis"``) are provided by the wrapper/bot package, which passes
-    an already-constructed coordinator instance to ``FailoverManager``; this
-    helper falls back to local for unknown backends so core never grows a
-    heavy optional dependency.
-    """
-    if config is None or config.backend == "local":
-        return LocalQuotaCoordinator()
-    # Unknown/heavy backend not resolvable in core: fail open to local.
-    return LocalQuotaCoordinator()

src/praisonai-agents/praisonaiagents/llm/unified_adapters.py

@@ -221,7 +221,6 @@ class OpenAIAdapter:
             reasoning_steps=kwargs.get('reasoning_steps', False),
             verbose=kwargs.get('verbose', True),
             max_iterations=kwargs.get('max_iterations', 10),
-            agent_name=kwargs.get('agent_name'),
             **{k: v for k, v in kwargs.items() if k not in {
                 'max_tokens', 'execute_tool_fn', 'console', 'display_fn',
                 'reasoning_steps', 'verbose', 'max_iterations',

src/praisonai-agents/praisonaiagents/lsp/__init__.py

@@ -41,11 +41,6 @@ __all__ = [
     "Range",
     # Configuration
     "LSPConfig",
-    # Auto-detection / availability helpers
-    "detect_language",
-    "detect_root_uri",
-    "probe",
-    "DEFAULT_SERVERS",
 ]
 
 
@@ -63,9 +58,8 @@ def __getattr__(name: str):
         )
         return locals()[name]
     
-    if name in ("LSPConfig", "detect_language", "detect_root_uri", "probe",
-                "DEFAULT_SERVERS"):
-        from . import config
-        return getattr(config, name)
+    if name == "LSPConfig":
+        from .config import LSPConfig
+        return LSPConfig
     
     raise AttributeError(f"module {__name__!r} has no attribute {name!r}")

src/praisonai-agents/praisonaiagents/lsp/client.py

@@ -16,9 +16,7 @@ from .types import (
     Position, Range, TextDocumentItem, TextDocumentIdentifier,
     TextDocumentPositionParams
 )
-import shutil
-
-from .config import LSPConfig, detect_root_uri, probe, path_to_uri
+from .config import LSPConfig
 
 logger = get_logger(__name__)
 
@@ -49,8 +47,7 @@ class LSPClient:
         language: str,
         command: Optional[str] = None,
         args: Optional[List[str]] = None,
-        root_uri: Optional[str] = None,
-        workspace_file: Optional[str] = None
+        root_uri: Optional[str] = None
     ):
         """
         Initialize the LSP client.
@@ -60,10 +57,6 @@ class LSPClient:
             command: Language server command (uses default if not specified)
             args: Command arguments
             root_uri: Workspace root URI
-            workspace_file: Optional file used to auto-detect the workspace root
-                from the nearest root marker (e.g. ``pyproject.toml``,
-                ``go.mod``) when ``root_uri`` is not given, so multi-root and
-                monorepo setups initialise against the correct project root.
         """
         self.config = LSPConfig(
             language=language,
@@ -71,18 +64,13 @@ class LSPClient:
             args=args or [],
             root_uri=root_uri
         )
-        self._workspace_file = workspace_file
-
+        
         self._process: Optional[asyncio.subprocess.Process] = None
         self._request_id = 0
         self._pending_requests: Dict[int, asyncio.Future] = {}
         self._diagnostics: Dict[str, List[Diagnostic]] = {}
         self._initialized = False
         self._reader_task: Optional[asyncio.Task] = None
-        # Populated with a structured, actionable message when the server
-        # binary is not on PATH, so callers can surface an explicit
-        # "unavailable + how to install" notice rather than a silent no-op.
-        self.last_error: Optional[str] = None
     
     @property
     def is_running(self) -> bool:
@@ -99,26 +87,6 @@ class LSPClient:
         if self.is_running:
             return True
         
-        # Availability pre-flight: check the *actual* configured command on
-        # PATH before spawning so a missing binary yields a single structured,
-        # actionable message instead of a raw FileNotFoundError. ``last_error``
-        # lets the caller surface an explicit "install X" notice rather than
-        # degrading silently. We gate on ``self.config.command`` (which may be a
-        # user-supplied custom server), and only surface the registry's install
-        # hint when it matches the default server for the language.
-        if not shutil.which(self.config.command):
-            _, default_command, install_hint = probe(self.config.language)
-            hint = (
-                f"; install with `{install_hint}`"
-                if install_hint and self.config.command == default_command
-                else ""
-            )
-            self.last_error = (
-                f"language server `{self.config.command}` not found on PATH{hint}"
-            )
-            logger.warning(self.last_error)
-            return False
-        
         try:
             cmd = [self.config.command] + self.config.args
             
@@ -132,15 +100,8 @@ class LSPClient:
             # Start reader task
             self._reader_task = asyncio.create_task(self._read_responses())
             
-            # Initialize the server. Prefer an explicit root_uri, then a root
-            # detected from the workspace file's nearest root marker (so
-            # monorepos/multi-root setups initialise against the real project
-            # root), falling back to the CWD only when neither is available.
-            root_uri = self.config.root_uri
-            if root_uri is None and self._workspace_file is not None:
-                root_uri = detect_root_uri(self._workspace_file, self.config.language)
-            if root_uri is None:
-                root_uri = path_to_uri(os.getcwd())
+            # Initialize the server
+            root_uri = self.config.root_uri or f"file://{os.getcwd()}"
             
             result = await self._send_request("initialize", {
                 "processId": os.getpid(),
@@ -226,7 +187,7 @@ class LSPClient:
                 logger.error(f"Failed to read file: {e}")
                 return False
         
-        uri = path_to_uri(file_path)
+        uri = f"file://{os.path.abspath(file_path)}"
         
         await self._send_notification("textDocument/didOpen", {
             "textDocument": TextDocumentItem(
@@ -244,7 +205,7 @@ class LSPClient:
         if not self._initialized:
             return
         
-        uri = path_to_uri(file_path)
+        uri = f"file://{os.path.abspath(file_path)}"
         
         await self._send_notification("textDocument/didClose", {
             "textDocument": TextDocumentIdentifier(uri=uri).to_dict()
@@ -260,7 +221,7 @@ class LSPClient:
         Returns:
             List of diagnostics
         """
-        uri = path_to_uri(file_path)
+        uri = f"file://{os.path.abspath(file_path)}"
         return self._diagnostics.get(uri, [])
     
     async def get_completions(
@@ -283,7 +244,7 @@ class LSPClient:
         if not self._initialized:
             return []
         
-        uri = path_to_uri(file_path)
+        uri = f"file://{os.path.abspath(file_path)}"
         
         result = await self._send_request("textDocument/completion", {
             "textDocument": {"uri": uri},
@@ -320,7 +281,7 @@ class LSPClient:
         if not self._initialized:
             return []
         
-        uri = path_to_uri(file_path)
+        uri = f"file://{os.path.abspath(file_path)}"
         
         result = await self._send_request("textDocument/definition", {
             "textDocument": {"uri": uri},
@@ -359,7 +320,7 @@ class LSPClient:
         if not self._initialized:
             return []
         
-        uri = path_to_uri(file_path)
+        uri = f"file://{os.path.abspath(file_path)}"
         
         result = await self._send_request("textDocument/references", {
             "textDocument": {"uri": uri},
@@ -392,7 +353,7 @@ class LSPClient:
         if not self._initialized:
             return None
         
-        uri = path_to_uri(file_path)
+        uri = f"file://{os.path.abspath(file_path)}"
         
         result = await self._send_request("textDocument/hover", {
             "textDocument": {"uri": uri},
@@ -429,7 +390,7 @@ class LSPClient:
         if not self._initialized:
             return []
         
-        uri = path_to_uri(file_path)
+        uri = f"file://{os.path.abspath(file_path)}"
         
         result = await self._send_request("textDocument/documentSymbol", {
             "textDocument": {"uri": uri}

src/praisonai-agents/praisonaiagents/lsp/config.py

@@ -2,124 +2,35 @@
 LSP Configuration for PraisonAI Agents.
 """
 
-import os
-import shutil
 from dataclasses import dataclass, field
-from pathlib import Path
-from typing import Optional, Dict, List, Tuple
+from typing import Optional, Dict, List
 
 
-# Data-driven language server registry.  Each entry carries the spawn command
-# plus enough metadata for zero-config auto-detection:
-#   - command / args: how to start the server
-#   - extensions: file extensions that map to this language
-#   - root_markers: files/dirs that mark a workspace root (nearest wins), so
-#     ``rootUri`` is the real project root rather than ``os.getcwd()``
-#   - install_hint: an actionable "how to install" string surfaced when the
-#     server binary is absent, so degradation is explicit instead of silent
+# Default language server commands
 DEFAULT_SERVERS = {
     "python": {
         "command": "pylsp",
         "args": [],
-        "extensions": [".py", ".pyi"],
-        "root_markers": ["pyproject.toml", "setup.py", "setup.cfg", "requirements.txt", ".git"],
-        "install_hint": "pip install python-lsp-server",
     },
     "javascript": {
         "command": "typescript-language-server",
         "args": ["--stdio"],
-        "extensions": [".js", ".jsx", ".mjs", ".cjs"],
-        "root_markers": ["package.json", "tsconfig.json", "jsconfig.json", ".git"],
-        "install_hint": "npm install -g typescript-language-server typescript",
     },
     "typescript": {
         "command": "typescript-language-server",
         "args": ["--stdio"],
-        "extensions": [".ts", ".tsx"],
-        "root_markers": ["tsconfig.json", "package.json", "jsconfig.json", ".git"],
-        "install_hint": "npm install -g typescript-language-server typescript",
     },
     "rust": {
         "command": "rust-analyzer",
         "args": [],
-        "extensions": [".rs"],
-        "root_markers": ["Cargo.toml", "Cargo.lock", ".git"],
-        "install_hint": "rustup component add rust-analyzer",
     },
     "go": {
         "command": "gopls",
         "args": [],
-        "extensions": [".go"],
-        "root_markers": ["go.mod", "go.sum", ".git"],
-        "install_hint": "go install golang.org/x/tools/gopls@latest",
     },
 }
 
 
-def _extension_map() -> Dict[str, str]:
-    """Return a ``{extension: language}`` map derived from the registry."""
-    mapping: Dict[str, str] = {}
-    for language, server in DEFAULT_SERVERS.items():
-        for ext in server.get("extensions", []):
-            mapping.setdefault(ext.lower(), language)
-    return mapping
-
-
-def detect_language(file_path: str) -> Optional[str]:
-    """Resolve the LSP language id for ``file_path`` by extension, else ``None``."""
-    return _extension_map().get(os.path.splitext(file_path)[1].lower())
-
-
-def path_to_uri(path: str) -> str:
-    """Convert an absolute filesystem *path* to a valid ``file://`` URI.
-
-    Uses :meth:`pathlib.Path.as_uri`, which percent-encodes reserved characters
-    (spaces, ``#`` …) so paths with such characters produce a valid, non-truncated
-    URI that language servers accept.
-    """
-    return Path(os.path.abspath(path)).as_uri()
-
-
-def detect_root_uri(file_path: str, language: Optional[str] = None) -> Optional[str]:
-    """Discover the workspace root for ``file_path`` from the nearest root marker.
-
-    Walks up from the file's directory looking for a language-appropriate root
-    marker (``pyproject.toml``, ``go.mod``, ``Cargo.toml``, ``tsconfig.json``,
-    ``.git`` …).  Returns a ``file://`` URI for the nearest matching directory,
-    or ``None`` when no marker is found so the caller can fall back to the CWD.
-    """
-    language = language or detect_language(file_path)
-    server = DEFAULT_SERVERS.get(language) if language else None
-    markers = server.get("root_markers", []) if server else [".git"]
-    start = os.path.dirname(os.path.abspath(file_path))
-    current = start
-    while True:
-        for marker in markers:
-            if os.path.exists(os.path.join(current, marker)):
-                return path_to_uri(current)
-        parent = os.path.dirname(current)
-        if parent == current:
-            return None
-        current = parent
-
-
-def probe(language: str) -> Tuple[bool, Optional[str], Optional[str]]:
-    """Check whether the language server for ``language`` is on ``PATH``.
-
-    Returns ``(available, command, install_hint)``.  ``available`` is ``True``
-    when the configured server binary is found via ``shutil.which``; otherwise
-    ``command`` and ``install_hint`` describe what is missing and how to install
-    it so the degradation can be surfaced instead of silently swallowed.
-    """
-    server = DEFAULT_SERVERS.get(language)
-    if not server:
-        return False, None, None
-    command = server["command"]
-    if shutil.which(command):
-        return True, command, server.get("install_hint")
-    return False, command, server.get("install_hint")
-
-
 @dataclass
 class LSPConfig:
     """Configuration for LSP client."""
@@ -136,6 +47,6 @@ class LSPConfig:
             if self.language in DEFAULT_SERVERS:
                 server = DEFAULT_SERVERS[self.language]
                 self.command = server["command"]
-                self.args = list(server["args"])
+                self.args = server["args"]
             else:
                 raise ValueError(f"No default server for language: {self.language}")

src/praisonai-agents/praisonaiagents/main.py

@@ -742,8 +742,36 @@ class ReflectionOutput(BaseModel):
     reflection: str
     satisfactory: Literal["yes", "no"]
 
-# Re-export the single canonical TaskOutput so main.TaskOutput and
-# output.models.TaskOutput are the SAME class. Previously two near-identical
-# classes both named TaskOutput existed, which broke guardrail validation
-# (GuardrailResult expected one class while agents produced the other).
-from .output.models import TaskOutput
+class TaskOutput(BaseModel):
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    description: str
+    summary: Optional[str] = None
+    raw: str
+    pydantic: Optional[BaseModel] = None
+    json_dict: Optional[Dict[str, Any]] = None
+    agent: str
+    output_format: Literal["RAW", "JSON", "Pydantic"] = "RAW"
+    token_metrics: Optional['TokenMetrics'] = None  # Add token metrics field
+    callback_error: Optional[str] = None
+    non_fatal_errors: Optional[list[str]] = None
+
+    def json(self) -> Optional[str]:
+        if self.output_format == "JSON" and self.json_dict:
+            return json.dumps(self.json_dict)
+        return None
+
+    def to_dict(self) -> dict:
+        output_dict = {}
+        if self.json_dict:
+            output_dict.update(self.json_dict)
+        if self.pydantic:
+            output_dict.update(self.pydantic.model_dump())
+        return output_dict
+
+    def __str__(self):
+        if self.pydantic:
+            return str(self.pydantic)
+        elif self.json_dict:
+            return json.dumps(self.json_dict)
+        else:
+            return self.raw 

src/praisonai-agents/praisonaiagents/managed/_compute_bridge.py

@@ -11,83 +11,30 @@ from __future__ import annotations
 import importlib
 from typing import Any, Optional
 
-_INSTALL_HINT = "Remote compute requires: pip install praisonai-sandbox"
+_INSTALL_HINT = "Remote compute requires the wrapper package: pip install praisonai"
 
 # name -> (module, attribute). Kept in sync with
 # praisonai.integrations.managed_local._resolve_compute
 _PROVIDERS = {
-    "local": ("praisonai_sandbox.compute.local", "LocalCompute"),
-    "docker": ("praisonai_sandbox.compute.docker", "DockerCompute"),
-    "e2b": ("praisonai_sandbox.compute.e2b", "E2BCompute"),
-    "modal": ("praisonai_sandbox.compute.modal_compute", "ModalCompute"),
-    "daytona": ("praisonai_sandbox.compute.daytona", "DaytonaCompute"),
-    "flyio": ("praisonai_sandbox.compute.flyio", "FlyioCompute"),
-    "tenki": ("praisonai_sandbox.compute.tenki", "TenkiCompute"),
+    "local": ("praisonai.integrations.compute.local", "LocalCompute"),
+    "docker": ("praisonai.integrations.compute.docker", "DockerCompute"),
+    "e2b": ("praisonai.integrations.compute.e2b", "E2BCompute"),
+    "modal": ("praisonai.integrations.compute.modal_compute", "ModalCompute"),
+    "daytona": ("praisonai.integrations.compute.daytona", "DaytonaCompute"),
+    "flyio": ("praisonai.integrations.compute.flyio", "FlyioCompute"),
+    "tenki": ("praisonai.integrations.compute.tenki", "TenkiCompute"),
 }
 
-# What to actually type when a provider is missing. Every name here must point
-# at an extra that EXISTS and installs something -- three of these used to name
-# extras that were absent or empty, so a user followed the official hint, waited
-# for the install, and hit the identical failure again.
-#
-# The providers in _PROVIDERS now live in praisonai-sandbox, so the failing
-# import is `praisonai_sandbox.compute.*`: point the hint at the lightweight
-# package that owns the module, not the heavy wrapper. Reaching E2B through
-# praisonai-sandbox[e2b] resolves 58 packages against 143 through praisonai.
-# Sandbox-only places (novita/sandlock/ssh) resolve through the
-# SandboxComputeAdapter and only need `praisonai-sandbox`.
 _EXTRA_HINTS = {
-    "e2b": "pip install 'praisonai-sandbox[e2b]'",
-    "modal": "pip install 'praisonai-sandbox[modal]'",
-    "daytona": "pip install 'praisonai-sandbox[daytona]'",
-    "docker": "pip install 'praisonai-sandbox[docker]'",
-    "novita": "pip install 'praisonai-sandbox[novita]'",
-    "sandlock": "pip install 'praisonai-sandbox[sandlock]'",
-    "ssh": "pip install 'praisonai-sandbox[ssh]'",
-    # flyio and tenki need a credential rather than an SDK; flyio speaks plain
-    # HTTP through aiohttp, which praisonaiagents already requires. Export the
-    # variable so a child process inherits it -- a bare assignment would not.
-    "flyio": "export FLY_API_TOKEN=... (see https://fly.io/docs/flyctl/auth-token)",
-    "tenki": "pip install 'praisonai-sandbox[tenki]'",
+    "e2b": "pip install praisonai[e2b]",
+    "modal": "pip install praisonai[modal]",
+    "daytona": "pip install praisonai[daytona]",
 }
 
 
-# Places that live only in praisonai-sandbox. They speak SandboxProtocol
-# (one object IS one environment) rather than ComputeProviderProtocol (one
-# object hands out many), so an adapter supplies the missing half.
-from ._sandbox_adapter import NEEDS_INSTANCE, SANDBOX_ONLY  # noqa: E402
-
-# Spellings users already have in their code, mapped to the canonical name.
-_ALIASES = {"native": "sandlock"}
-
-
-def _entry_point_providers() -> dict:
-    """Places contributed by other installed packages.
-
-    The sandbox and managed-backend registries already discover plugins this
-    way (``praisonai.sandbox``, ``praisonai.managed_backends``); the compute
-    registry was the one hardcoded dict, so adding a place meant editing core.
-    A provider can now ship in its own distribution:
-
-        [project.entry-points."praisonai.compute"]
-        runpod = "praisonai_compute_runpod:RunpodCompute"
-    """
-    found = {}
-    try:
-        from importlib.metadata import entry_points
-
-        for ep in entry_points(group="praisonai.compute"):
-            found[ep.name.lower()] = ep
-    except Exception:  # pragma: no cover - discovery must never break resolution
-        pass
-    return found
-
-
 def available_providers() -> list:
-    """Every place ``tools_run_on=`` / ``run_in=`` accepts, from all registries."""
-    return sorted(
-        set(_PROVIDERS) | set(SANDBOX_ONLY) | set(_entry_point_providers())
-    )
+    """Return the compute provider names this bridge can resolve."""
+    return sorted(_PROVIDERS)
 
 
 def compute_package_available() -> bool:
@@ -111,44 +58,15 @@ def resolve_compute(compute: Optional[Any]) -> Optional[Any]:
     if not isinstance(compute, str):
         if hasattr(compute, "provision") and hasattr(compute, "execute"):
             return compute
-        # A SandboxProtocol instance -- e.g. SSHSandbox(host=...) -- is adapted,
-        # which is the only way to pass connection details.
-        if hasattr(compute, "run_command") and hasattr(compute, "start"):
-            from ._sandbox_adapter import wrap_sandbox_instance
-
-            return wrap_sandbox_instance(compute)
         raise TypeError(
             f"compute= expects a provider name or a ComputeProviderProtocol "
             f"instance, got {type(compute).__name__}"
         )
 
     name = compute.lower().strip()
-    name = _ALIASES.get(name, name)
-
-    # A sandbox-only place: adapt it to the compute-provider shape.
-    if name in SANDBOX_ONLY:
-        if name in NEEDS_INSTANCE:
-            raise ValueError(
-                f"{name!r} needs connection details a bare name cannot carry. "
-                f"Instead, {NEEDS_INSTANCE[name]}"
-            )
-        from ._sandbox_adapter import SandboxComputeAdapter
-
-        return SandboxComputeAdapter(name)
-
-    external = _entry_point_providers()
-    if name in external and name not in _PROVIDERS:
-        # Let a contributed place describe itself. Without this the repr falls
-        # back to the bare name, because the phrase table is a literal that
-        # cannot know about packages installed later.
-        _remember_display_name(name, external[name])
-        # A place contributed by another package. Loaded on demand, so an
-        # installed-but-broken plugin cannot break anything that never names it.
-        return external[name].load()()
-
     if name not in _PROVIDERS:
         raise ValueError(
-            f"Unknown place {name!r}. "
+            f"Unknown compute provider {name!r}. "
             f"Available: {', '.join(available_providers())}"
         )
 
@@ -160,23 +78,3 @@ def resolve_compute(compute: Optional[Any]) -> Optional[Any]:
         raise ImportError(f"compute={name!r} requires {module_name}. {hint}") from exc
 
     return getattr(module, attr)()
-
-
-#: Display phrases contributed by external providers, filled in on resolve.
-_DISPLAY_NAMES: dict = {}
-
-
-def _remember_display_name(name: str, entry_point) -> None:
-    """Record a contributed provider's own phrase, if it declares one."""
-    try:
-        cls = entry_point.load()
-        phrase = getattr(cls, "display_name", None)
-        if isinstance(phrase, str) and phrase:
-            _DISPLAY_NAMES[name] = phrase
-    except Exception:  # pragma: no cover - naming must never break resolution
-        pass
-
-
-def contributed_display_name(name: str):
-    """The phrase a contributed place declared for itself, if any."""
-    return _DISPLAY_NAMES.get((name or "").lower())

src/praisonai-agents/praisonaiagents/managed/_sandbox_adapter.py

@@ -1,254 +0,0 @@
-"""Expose a single sandbox environment as a one-instance compute provider.
-
-There are two execution stacks in this project and they are *not* duplicates:
-
-* ``SandboxProtocol`` (praisonai-sandbox) -- one object **is** one environment:
-  ``start / stop / execute / run_command / reset``.
-* ``ComputeProviderProtocol`` -- one object **hands out** many environments:
-  ``provision / execute(instance_id, ...) / shutdown / list_instances``.
-
-``tools_run_on=`` speaks the second protocol, so four backends that only exist
-as sandboxes -- ``subprocess``, ``sandlock``, ``ssh``, ``novita`` -- were
-unreachable through it. This adapter is the missing half: it holds exactly one
-environment and presents the manager-shaped API over it.
-
-Deliberate limitation: ``list_instances()`` can only report what *this process*
-provisioned, so adapter-backed places never appear in ``praisonai managed ps``.
-A single environment has no cross-process registry to consult, and pretending
-otherwise would be worse than saying so.
-"""
-
-from __future__ import annotations
-
-import logging
-import uuid
-from typing import Any, Dict, List, Optional
-
-logger = logging.getLogger(__name__)
-
-# Backends that exist only as SandboxProtocol implementations. The literal is
-# the floor, not the ceiling: the sandbox registry accepts plugins by entry
-# point, so a hardcoded tuple silently withheld contributed backends from
-# tools_run_on=. `capsule` was the live example -- it ships from
-# praisonai-plugins, worked with run_in=, and was invisible to tools_run_on=.
-_SANDBOX_ONLY_FLOOR = ("subprocess", "sandlock", "ssh", "novita")
-
-
-def sandbox_only_names() -> tuple:
-    """Sandbox backends with no compute-registry equivalent.
-
-    Anything the compute registry already provides is excluded, so a name that
-    exists in both (docker, e2b, modal, daytona) keeps its richer compute
-    implementation rather than being downgraded to the one-instance adapter.
-    """
-    names = set(_SANDBOX_ONLY_FLOOR)
-    try:
-        from ..sandbox._sandbox_bridge import get_sandbox_registry
-
-        registry = get_sandbox_registry()
-        registry = registry.default() if isinstance(registry, type) else registry
-        names |= {str(n).lower() for n in registry.list_all_names()}
-    except Exception:  # pragma: no cover - discovery must never break resolution
-        pass
-
-    try:
-        from ._compute_bridge import _PROVIDERS
-
-        names -= set(_PROVIDERS)
-    except Exception:
-        pass
-    return tuple(sorted(names))
-
-
-class _SandboxOnly(tuple):
-    """A tuple that re-reads the registry, so `in` sees plugins installed later.
-
-    Kept as a tuple subclass because SANDBOX_ONLY is imported and iterated in
-    several places that predate this.
-    """
-
-    def __contains__(self, item):
-        return item in sandbox_only_names()
-
-    def __iter__(self):
-        return iter(sandbox_only_names())
-
-    def __len__(self):
-        return len(sandbox_only_names())
-
-
-SANDBOX_ONLY = _SandboxOnly(_SANDBOX_ONLY_FLOOR)
-
-# Names that need connection details no bare string can carry.
-NEEDS_INSTANCE = {
-    "ssh": (
-        "run on a remote machine over SSH by passing the object, so it can "
-        "carry the host: SSHSandbox(host='...', user='...')"
-    ),
-}
-
-
-class SandboxComputeAdapter:
-    """One ``SandboxProtocol`` environment, wearing the compute-provider shape."""
-
-    def __init__(self, sandbox_type: str, config: Optional[Any] = None,
-                 sandbox: Optional[Any] = None):
-        self._type = sandbox_type
-        self._config = config
-        self._sandbox = sandbox          # pre-built instance, if supplied
-        self._owns_sandbox = sandbox is None
-        self._instance_id: Optional[str] = None
-
-    # ── identity ─────────────────────────────────────────────────────────────
-    @property
-    def provider_name(self) -> str:
-        return self._type
-
-    @property
-    def is_available(self) -> bool:
-        if self._sandbox is not None:
-            return bool(getattr(self._sandbox, "is_available", True))
-        try:
-            from ..sandbox._sandbox_bridge import resolve_sandbox_class
-
-            cls = resolve_sandbox_class(self._type)
-            probe = cls() if self._type not in NEEDS_INSTANCE else None
-            return bool(getattr(probe, "is_available", False)) if probe else False
-        except Exception:
-            return False
-
-    # ── lifecycle ────────────────────────────────────────────────────────────
-    async def provision(self, config: Any) -> Any:
-        from .protocols import InstanceInfo, InstanceStatus
-
-        if self._sandbox is None:
-            from ..sandbox import SandboxConfig
-            from ..sandbox.manager import SandboxManager
-
-            cfg = self._config
-            if cfg is None:
-                # "/workspace" is the convention for *container* sandboxes and
-                # does not exist on a Mac or a bare Linux box -- creating it
-                # fails with "Read-only file system". Local backends pick their
-                # own private temp dir, so only pass a working_dir through when
-                # the caller actually chose one.
-                wanted_dir = getattr(config, "working_dir", None)
-                local_place = self._type in ("subprocess", "sandlock")
-                if local_place and wanted_dir in (None, "", "/workspace"):
-                    wanted_dir = None
-                cfg = SandboxConfig(
-                    sandbox_type=self._type,
-                    env=dict(getattr(config, "env", None) or {}),
-                    **({"working_dir": wanted_dir} if wanted_dir else {}),
-                )
-                # This sandbox exists to back the model's execute_command tool,
-                # which IS a shell. The default policy sets allow_subprocess=
-                # False, which makes `sh -c` -- and therefore every pipe,
-                # redirect and && the model writes -- fail as "disabled by
-                # security policy". Blocking the shell inside a shell tool is a
-                # contradiction, not a protection; blocked_commands and
-                # blocked_paths still apply.
-                if getattr(cfg, "security_policy", None) is not None:
-                    cfg.security_policy.allow_subprocess = True
-            if getattr(config, "image", None):
-                cfg.image = config.image
-            self._manager = SandboxManager(cfg)
-            self._sandbox = await self._manager.__aenter__()
-        else:
-            self._manager = None
-            starter = getattr(self._sandbox, "start", None)
-            if starter is not None:
-                await starter()
-
-        self._instance_id = f"{self._type}_{uuid.uuid4().hex[:12]}"
-        logger.info("[sandbox_adapter] provisioned %s as %s", self._type, self._instance_id)
-        return InstanceInfo(
-            instance_id=self._instance_id,
-            status=InstanceStatus.RUNNING,
-            endpoint=f"{self._type}://local",
-            provider=self._type,
-            metadata={"adapter": True, "discoverable": False},
-        )
-
-    async def execute(self, instance_id: str, command: str,
-                      timeout: Optional[int] = 300) -> Dict[str, Any]:
-        if self._sandbox is None:
-            raise RuntimeError(
-                f"{self._type} sandbox is not running; provision() was not called"
-            )
-        # The bridged execute_command tool hands us a shell command string, and
-        # models write pipes, redirects and && constantly. Without shell=True
-        # `echo x > f` is argv-split and "> f" arrives as a literal argument.
-        try:
-            result = await self._sandbox.run_command(command, shell=True)
-        except TypeError:
-            # Backends predating the shell= parameter.
-            result = await self._sandbox.run_command(command)
-        # A policy denial arrives as result.error with exit_code=None. Dropping
-        # it would turn "blocked by security policy" into a silent success --
-        # the caller would see exit 0 and empty output.
-        error = getattr(result, "error", None)
-        exit_code = getattr(result, "exit_code", None)
-        stderr = getattr(result, "stderr", "") or ""
-        if error:
-            stderr = f"{stderr}\n{error}".strip() if stderr else str(error)
-            if exit_code in (None, 0):
-                exit_code = 1
-        return {
-            "stdout": getattr(result, "stdout", "") or "",
-            "stderr": stderr,
-            "exit_code": exit_code or 0,
-        }
-
-    async def shutdown(self, instance_id: str) -> None:
-        try:
-            if getattr(self, "_manager", None) is not None:
-                await self._manager.__aexit__(None, None, None)
-            elif self._sandbox is not None:
-                stopper = getattr(self._sandbox, "stop", None)
-                if stopper is not None:
-                    await stopper()
-        finally:
-            if self._owns_sandbox:
-                self._sandbox = None
-            self._manager = None
-            self._instance_id = None
-
-    async def get_status(self, instance_id: str) -> Any:
-        from .protocols import InstanceInfo, InstanceStatus
-
-        running = self._sandbox is not None and instance_id == self._instance_id
-        return InstanceInfo(
-            instance_id=instance_id,
-            status=InstanceStatus.RUNNING if running else InstanceStatus.STOPPED,
-            provider=self._type,
-        )
-
-    async def list_instances(self) -> List[Any]:
-        """Only what this process provisioned -- see the module docstring."""
-        from .protocols import InstanceInfo, InstanceStatus
-
-        if self._instance_id is None:
-            return []
-        return [InstanceInfo(
-            instance_id=self._instance_id,
-            status=InstanceStatus.RUNNING,
-            provider=self._type,
-            metadata={"adapter": True, "discoverable": False},
-        )]
-
-    # ── file transfer ────────────────────────────────────────────────────────
-    async def upload_file(self, instance_id: str, local_path: str, remote_path: str) -> None:
-        with open(local_path, "r") as handle:
-            await self._sandbox.write_file(remote_path, handle.read())
-
-    async def download_file(self, instance_id: str, remote_path: str, local_path: str) -> None:
-        content = await self._sandbox.read_file(remote_path)
-        with open(local_path, "w") as handle:
-            handle.write(content if isinstance(content, str) else str(content))
-
-
-def wrap_sandbox_instance(sandbox: Any) -> SandboxComputeAdapter:
-    """Adapt an already-constructed sandbox (e.g. ``SSHSandbox(host=...)``)."""
-    name = getattr(sandbox, "sandbox_type", None) or type(sandbox).__name__.lower()
-    return SandboxComputeAdapter(str(name), sandbox=sandbox)

src/praisonai-agents/praisonaiagents/managed/shared_compute.py

@@ -17,7 +17,6 @@ import logging
 import shlex
 import threading
 import uuid
-import weakref
 from typing import Any, Dict, List, Optional
 
 from ._compute_bridge import resolve_compute
@@ -119,13 +118,8 @@ class SharedCompute:
 
     def shutdown(self) -> None:
         """Tear down the instance and restore any agents we patched."""
-        for ref, original_tools, original_backstory in self._patched:
-            agent = ref()
-            if agent is None:
-                continue          # already collected; nothing left to restore
+        for agent, original_tools, original_backstory in self._patched:
             try:
-                if getattr(agent, "_tools_sandbox", None) is self:
-                    agent._tools_sandbox = None
                 agent.tools = original_tools
                 agent.backstory = original_backstory
                 cache = getattr(agent, "_system_prompt_cache", None)
@@ -142,8 +136,6 @@ class SharedCompute:
             logger.info("[shared_compute] shut down instance %s", self.instance_id)
         except Exception as exc:  # pragma: no cover - teardown must not mask errors
             logger.warning("[shared_compute] shutdown failed for %s: %s", self.instance_id, exc)
-            self.instance_id = None
-            raise            # the caller logs whether the sandbox was released
         finally:
             self.instance_id = None
 
@@ -195,14 +187,9 @@ class SharedCompute:
             # heredoc early (which would truncate the file and run the remainder
             # as shell commands). Guard against the astronomically-unlikely case
             # where the token still appears in the body.
-            # Uppercase hex on purpose. uuid4().hex is lowercase, and the
-            # security policy substring-matches blocked_commands against the
-            # whole command -- "dd" is one of them, and appears in 9.6% of
-            # random lowercase hex strings. One write in ten failed with
-            # "Blocked command pattern: dd" for no reason the caller could see.
-            delimiter = f"__PRAISON_EOF_{uuid.uuid4().hex.upper()}__"
+            delimiter = f"__PRAISON_EOF_{uuid.uuid4().hex}__"
             while delimiter in content:
-                delimiter = f"__PRAISON_EOF_{uuid.uuid4().hex.upper()}__"
+                delimiter = f"__PRAISON_EOF_{uuid.uuid4().hex}__"
             heredoc = (
                 f"mkdir -p $(dirname {quoted}) && "
                 f"cat > {quoted} <<'{delimiter}'\n{content}\n{delimiter}"
@@ -216,25 +203,13 @@ class SharedCompute:
             """List files in a directory on the shared remote sandbox."""
             return self._format(self.run_command(f"ls -la {shlex.quote(path)}"))
 
-        bridged = [execute_command, read_file, write_file, list_files]
-        # Tag them so Agent.clone_for_channel() drops them: each closes over
-        # THIS sandbox, so a clone inheriting them would talk to the original
-        # agent's instance and then attach a second sandbox of its own --
-        # duplicating the capability prompt and splitting its work across two
-        # machines. The clone regenerates its own on first use.
-        for tool in bridged:
-            tool._praison_sandbox_tool = True
-        return bridged
+        return [execute_command, read_file, write_file, list_files]
 
-    def attach(self, agents: List[Any], *, override_declared: bool = False) -> None:
+    def attach(self, agents: List[Any]) -> None:
         """Give each agent the shared tools and tell it they exist.
 
         Agents that already carry their own managed ``backend`` are skipped --
         they have deliberately been pointed at their own runtime.
-
-        ``override_declared`` is set only by the agent's *own* placement, which
-        is this sandbox's whole reason for existing. A run-level sandbox leaves
-        it False so an agent that named its own place keeps it.
         """
         tools = self.build_tools()
         by_name = {t.__name__: t for t in tools}
@@ -242,31 +217,6 @@ class SharedCompute:
         for agent in agents:
             if agent is None or getattr(agent, "backend", None) is not None:
                 continue
-            # An agent that named its own place, or already has a sandbox, must
-            # not be attached again. A second attach appends CAPABILITY_PROMPT
-            # twice and, if the two teardowns do not happen in LIFO order,
-            # permanently restores the wrong tools: the agent is left holding
-            # four tools bound to a shut-down instance.
-            #
-            # `tools_run_on` is checked as well as `_tools_sandbox` because of
-            # ordering: a flow attaches at the start of the run, before the
-            # agent's first chat() has created its own sandbox. Checking only
-            # the live sandbox would attach here and let the agent attach again
-            # on its first turn. An explicit per-agent choice outranks the run's
-            # default, so the flow leaves it alone.
-            declared_own = (
-                not override_declared
-                and getattr(agent, "tools_run_on", None) is not None
-            )
-            if getattr(agent, "_tools_sandbox", None) is not None or declared_own:
-                logger.debug(
-                    "[shared_compute] %r already runs its tools on %s; leaving it alone",
-                    getattr(agent, "name", agent),
-                    getattr(agent, "tools_run_on", "its own sandbox"),
-                )
-                continue
-            if any(agent is ref() for ref, _, _ in self._patched):
-                continue
 
             original_tools = list(getattr(agent, "tools", None) or [])
             # Agent.__init__ copies `instructions` into role/goal/backstory and
@@ -298,18 +248,4 @@ class SharedCompute:
                 logger.warning("[shared_compute] could not attach tools to %r: %s", agent, exc)
                 continue
 
-            # Mark where this agent's tools now run, so a nested attach (or a
-            # later ensure_tools_placed) can see it is already bound.
-            try:
-                agent._tools_sandbox = self
-            except Exception:  # pragma: no cover - exotic agent objects
-                pass
-            # Weakly: an agent points at its SharedCompute and the SharedCompute
-            # pointed back, so a dropped agent was reclaimed as a cycle and its
-            # sandbox was never shut down. Holding the agent weakly lets
-            # weakref.finalize see the agent die and release the sandbox.
-            try:
-                ref = weakref.ref(agent)
-            except TypeError:  # pragma: no cover - non-weakrefable agent
-                ref = lambda _agent=agent: _agent
-            self._patched.append((ref, original_tools, original_backstory))
+            self._patched.append((agent, original_tools, original_backstory))

src/praisonai-agents/praisonaiagents/mcp/__init__.py

@@ -11,62 +11,94 @@ using different transport methods:
 Protocol Revision: 2025-11-25
 """
 from .mcp import MCP
-from .._lazy import create_lazy_getattr
-
-
-def _t(module_path: str, attr_name: str):
-    """Build a (module_path, attr_name) lazy-import target.
-
-    Using a helper instead of bare 2-string tuple literals keeps secret
-    scanners from misclassifying the auth/oauth import targets below as
-    hardcoded "Authentication Tuple" credentials (they are import paths,
-    not secrets).
-    """
-    return (module_path, attr_name)
-
 
 # Lazy imports for optional components
-_LAZY_IMPORTS = {
-    "WebSocketMCPClient": _t("praisonaiagents.mcp.mcp_websocket", "WebSocketMCPClient"),
-    "SessionManager": _t("praisonaiagents.mcp.mcp_session", "SessionManager"),
-    "SecurityConfig": _t("praisonaiagents.mcp.mcp_security", "SecurityConfig"),
-    "BaseTransport": _t("praisonaiagents.mcp.mcp_transport", "BaseTransport"),
-    "TransportConfig": _t("praisonaiagents.mcp.mcp_transport", "TransportConfig"),
-    "ToolsMCPServer": _t("praisonaiagents.mcp.mcp_server", "ToolsMCPServer"),
-    "launch_tools_mcp_server": _t("praisonaiagents.mcp.mcp_server", "launch_tools_mcp_server"),
-    "function_to_mcp_schema": _t("praisonaiagents.mcp.mcp_utils", "function_to_mcp_schema"),
-    "get_tool_metadata": _t("praisonaiagents.mcp.mcp_utils", "get_tool_metadata"),
-    "python_type_to_json_schema": _t("praisonaiagents.mcp.mcp_utils", "python_type_to_json_schema"),
-    "fix_array_schemas": _t("praisonaiagents.mcp.mcp_schema_utils", "fix_array_schemas"),
-    "ThreadLocalEventLoop": _t("praisonaiagents.mcp.mcp_schema_utils", "ThreadLocalEventLoop"),
-    "get_thread_local_event_loop": _t("praisonaiagents.mcp.mcp_schema_utils", "get_thread_local_event_loop"),
-    # Auth storage (lazy loaded) — import targets, not credentials.
-    "MCPAuthStorage": _t("praisonaiagents.mcp.mcp_auth_storage", "MCPAuthStorage"),
-    "get_default_auth_filepath": _t("praisonaiagents.mcp.mcp_auth_storage", "get_default_auth_filepath"),
-    # OAuth callback utilities (lazy loaded) — import targets, not credentials.
-    "OAuthCallbackHandler": _t("praisonaiagents.mcp.mcp_oauth_callback", "OAuthCallbackHandler"),
-    "generate_state": _t("praisonaiagents.mcp.mcp_oauth_callback", "generate_state"),
-    "generate_code_verifier": _t("praisonaiagents.mcp.mcp_oauth_callback", "generate_code_verifier"),
-    "generate_code_challenge": _t("praisonaiagents.mcp.mcp_oauth_callback", "generate_code_challenge"),
-    "get_redirect_url": _t("praisonaiagents.mcp.mcp_oauth_callback", "get_redirect_url"),
-    "OAUTH_CALLBACK_PORT": _t("praisonaiagents.mcp.mcp_oauth_callback", "OAUTH_CALLBACK_PORT"),
-    "OAUTH_CALLBACK_PATH": _t("praisonaiagents.mcp.mcp_oauth_callback", "OAUTH_CALLBACK_PATH"),
-    # Zero-config OAuth: discovery, dynamic registration, orchestration.
-    "discover_oauth_metadata": _t("praisonaiagents.mcp.oauth_discovery", "discover_oauth_metadata"),
-    "parse_www_authenticate": _t("praisonaiagents.mcp.oauth_discovery", "parse_www_authenticate"),
-    "register_client": _t("praisonaiagents.mcp.oauth_registration", "register_client"),
-    "MCPOAuthProvider": _t("praisonaiagents.mcp.oauth_provider", "MCPOAuthProvider"),
-    "InteractiveAuthRequired": _t("praisonaiagents.mcp.oauth_provider", "InteractiveAuthRequired"),
+def __getattr__(name):
+    """Lazy import for optional modules."""
+    if name == "WebSocketMCPClient":
+        from .mcp_websocket import WebSocketMCPClient
+        return WebSocketMCPClient
+    elif name == "SessionManager":
+        from .mcp_session import SessionManager
+        return SessionManager
+    elif name == "SecurityConfig":
+        from .mcp_security import SecurityConfig
+        return SecurityConfig
+    elif name == "BaseTransport":
+        from .mcp_transport import BaseTransport
+        return BaseTransport
+    elif name == "TransportConfig":
+        from .mcp_transport import TransportConfig
+        return TransportConfig
+    elif name == "ToolsMCPServer":
+        from .mcp_server import ToolsMCPServer
+        return ToolsMCPServer
+    elif name == "launch_tools_mcp_server":
+        from .mcp_server import launch_tools_mcp_server
+        return launch_tools_mcp_server
+    elif name == "function_to_mcp_schema":
+        from .mcp_utils import function_to_mcp_schema
+        return function_to_mcp_schema
+    elif name == "get_tool_metadata":
+        from .mcp_utils import get_tool_metadata
+        return get_tool_metadata
+    elif name == "python_type_to_json_schema":
+        from .mcp_utils import python_type_to_json_schema
+        return python_type_to_json_schema
+    elif name == "fix_array_schemas":
+        from .mcp_schema_utils import fix_array_schemas
+        return fix_array_schemas
+    elif name == "ThreadLocalEventLoop":
+        from .mcp_schema_utils import ThreadLocalEventLoop
+        return ThreadLocalEventLoop
+    elif name == "get_thread_local_event_loop":
+        from .mcp_schema_utils import get_thread_local_event_loop
+        return get_thread_local_event_loop
+    # Auth storage (lazy loaded)
+    elif name == "MCPAuthStorage":
+        from .mcp_auth_storage import MCPAuthStorage
+        return MCPAuthStorage
+    elif name == "get_default_auth_filepath":
+        from .mcp_auth_storage import get_default_auth_filepath
+        return get_default_auth_filepath
+    # OAuth callback utilities (lazy loaded)
+    elif name == "OAuthCallbackHandler":
+        from .mcp_oauth_callback import OAuthCallbackHandler
+        return OAuthCallbackHandler
+    elif name == "generate_state":
+        from .mcp_oauth_callback import generate_state
+        return generate_state
+    elif name == "generate_code_verifier":
+        from .mcp_oauth_callback import generate_code_verifier
+        return generate_code_verifier
+    elif name == "generate_code_challenge":
+        from .mcp_oauth_callback import generate_code_challenge
+        return generate_code_challenge
+    elif name == "get_redirect_url":
+        from .mcp_oauth_callback import get_redirect_url
+        return get_redirect_url
+    elif name == "OAUTH_CALLBACK_PORT":
+        from .mcp_oauth_callback import OAUTH_CALLBACK_PORT
+        return OAUTH_CALLBACK_PORT
+    elif name == "OAUTH_CALLBACK_PATH":
+        from .mcp_oauth_callback import OAUTH_CALLBACK_PATH
+        return OAUTH_CALLBACK_PATH
     # Protocols (lazy loaded)
-    "MCPClientProtocol": _t("praisonaiagents.mcp.protocols", "MCPClientProtocol"),
+    elif name == "MCPClientProtocol":
+        from .protocols import MCPClientProtocol
+        return MCPClientProtocol
     # Loader (lazy loaded)
-    "load_mcp_tools": _t("praisonaiagents.mcp.loader", "load_mcp_tools"),
+    elif name == "load_mcp_tools":
+        from .loader import load_mcp_tools
+        return load_mcp_tools
     # Resource/prompt normalisation helpers (lazy loaded)
-    "normalize_resource_result": _t("praisonaiagents.mcp.resources", "normalize_resource_result"),
-    "normalize_prompt_result": _t("praisonaiagents.mcp.resources", "normalize_prompt_result"),
-}
-
-__getattr__ = create_lazy_getattr(_LAZY_IMPORTS, __name__)
+    elif name == "normalize_resource_result":
+        from .resources import normalize_resource_result
+        return normalize_resource_result
+    elif name == "normalize_prompt_result":
+        from .resources import normalize_prompt_result
+        return normalize_prompt_result
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
 
 __all__ = [
     # Client
@@ -106,10 +138,4 @@ __all__ = [
     "get_redirect_url",
     "OAUTH_CALLBACK_PORT",
     "OAUTH_CALLBACK_PATH",
-    # Zero-config OAuth (lazy loaded)
-    "discover_oauth_metadata",
-    "parse_www_authenticate",
-    "register_client",
-    "MCPOAuthProvider",
-    "InteractiveAuthRequired",
 ]

src/praisonai-agents/praisonaiagents/mcp/mcp.py

@@ -428,15 +428,9 @@ class MCP:
                 self.is_npx = False
                 return
             
-        # Handle the single string format for stdio client.
-        # Shell-split the command string first, then decide based on how many
-        # tokens it yields. This makes multi-word forms like
-        # MCP("npx -y pkg", args=["/tmp"]) work — the first token is the
-        # executable and the remaining tokens are prepended to any explicitly
-        # supplied args. Using shlex handles all whitespace (spaces, tabs,
-        # newlines) and lets an executable path that contains spaces be passed
-        # intact by quoting it, e.g. MCP('"/opt/my app"', args=["run"]).
-        if isinstance(command_or_string, str):
+        # Handle the single string format for stdio client
+        if isinstance(command_or_string, str) and args is None:
+            # Split the string into command and args using shell-like parsing
             if platform.system() == 'Windows':
                 # Use shlex with posix=False for Windows to handle quotes and paths with spaces
                 parts = shlex.split(command_or_string, posix=False)
@@ -444,19 +438,13 @@ class MCP:
                 parts = [part.strip('"') for part in parts]
             else:
                 parts = shlex.split(command_or_string)
-
-            if len(parts) > 1:
-                # Multi-token string: first token is the executable, the rest
-                # are prepended to any explicitly supplied args.
-                cmd = parts[0]
-                arguments = parts[1:] + (args or [])
-            else:
-                # Single token (or a quoted spaced path): treat the whole
-                # string as a bare executable and keep explicit args as-is.
-                cmd = parts[0] if parts else command_or_string
-                arguments = args or []
+            if not parts:
+                raise ValueError("Empty command string")
+            
+            cmd = parts[0]
+            arguments = parts[1:] if len(parts) > 1 else []
         else:
-            # Use the original format with a bare command and separate args
+            # Use the original format with separate command and args
             cmd = command_or_string
             arguments = args or []
         

src/praisonai-agents/praisonaiagents/mcp/oauth_discovery.py

@@ -1,231 +0,0 @@
-"""
-MCP OAuth Metadata Discovery.
-
-Implements the discovery half of zero-config OAuth for remote MCP servers:
-
-- Parse a ``WWW-Authenticate: Bearer resource_metadata="..."`` challenge from a
-  ``401`` response (RFC 9728 / MCP authorization spec).
-- Fetch protected-resource metadata (``/.well-known/oauth-protected-resource``).
-- Fetch authorization-server metadata
-  (``/.well-known/oauth-authorization-server`` with an OpenID configuration
-  fallback), yielding ``authorization_endpoint``, ``token_endpoint`` and
-  ``registration_endpoint``.
-
-Network access is HTTPS-only (except loopback) to preserve the SSRF-safe
-posture used elsewhere in the MCP transports. ``requests`` is imported lazily so
-this module stays additive and does not affect import time.
-"""
-
-import re
-from typing import Any, Dict, List, Optional
-from urllib.parse import urljoin, urlparse
-
-from praisonaiagents._logging import get_logger
-
-logger = get_logger("mcp-oauth-discovery")
-
-_LOCALHOST_HOSTS = {"localhost", "127.0.0.1", "::1"}
-
-
-def _require_https(url: str) -> None:
-    """Reject non-HTTPS metadata URLs (loopback HTTP is allowed for testing)."""
-    parsed = urlparse(url)
-    if parsed.scheme == "https":
-        return
-    if parsed.scheme == "http" and (parsed.hostname or "") in _LOCALHOST_HOSTS:
-        return
-    raise ValueError(
-        f"Refusing to fetch OAuth metadata over insecure transport: {url!r}"
-    )
-
-
-def parse_www_authenticate(header: Optional[str]) -> Dict[str, str]:
-    """
-    Parse a ``WWW-Authenticate`` challenge header into its parameters.
-
-    Only ``Bearer`` challenges are relevant here. Returns a dict of the
-    ``key="value"`` auth-params (e.g. ``resource_metadata``, ``scope``,
-    ``error``). Returns an empty dict when the header is missing or not a
-    Bearer challenge.
-    """
-    if not header:
-        return {}
-
-    # Strip the leading scheme (e.g. "Bearer ") if present.
-    stripped = header.strip()
-    if stripped.lower().startswith("bearer"):
-        stripped = stripped[len("bearer"):].lstrip()
-
-    params: Dict[str, str] = {}
-    for match in re.finditer(r'(\w+)\s*=\s*"([^"]*)"', stripped):
-        params[match.group(1).lower()] = match.group(2)
-    return params
-
-
-def _get_json(url: str, timeout: float = 10.0) -> Dict[str, Any]:
-    """Fetch and parse a JSON metadata document over HTTPS.
-
-    Redirects are followed but every hop — including the final destination — is
-    re-validated with :func:`_require_https` so a redirect cannot escape the
-    HTTPS/loopback guard to an internal or plaintext endpoint (SSRF-safe).
-    """
-    _require_https(url)
-    import requests  # lazy import — optional dependency
-
-    resp = requests.get(
-        url,
-        headers={"Accept": "application/json"},
-        timeout=timeout,
-        allow_redirects=True,
-    )
-    # Re-validate every redirect hop and the final URL: allow_redirects only
-    # checks the initial URL, so a 30x to http:// or an internal host would
-    # otherwise bypass the guard.
-    for previous in getattr(resp, "history", None) or []:
-        _require_https(previous.url)
-    _require_https(resp.url)
-    resp.raise_for_status()
-    return resp.json()
-
-
-def _wellknown_candidates(server_url: str) -> List[str]:
-    """Build ``.well-known`` metadata URL candidates for a server URL."""
-    parsed = urlparse(server_url)
-    origin = f"{parsed.scheme}://{parsed.netloc}"
-    return [
-        urljoin(origin + "/", ".well-known/oauth-protected-resource"),
-        urljoin(origin + "/", ".well-known/oauth-authorization-server"),
-        urljoin(origin + "/", ".well-known/openid-configuration"),
-    ]
-
-
-def discover_protected_resource(
-    server_url: str,
-    resource_metadata_url: Optional[str] = None,
-    timeout: float = 10.0,
-) -> Optional[Dict[str, Any]]:
-    """
-    Discover protected-resource metadata for an MCP server.
-
-    Args:
-        server_url: The MCP server URL that returned a 401.
-        resource_metadata_url: Optional explicit URL from the
-            ``WWW-Authenticate: resource_metadata="..."`` challenge.
-        timeout: Per-request timeout in seconds.
-
-    Returns:
-        The protected-resource metadata document, or None if unavailable.
-    """
-    url = resource_metadata_url or _wellknown_candidates(server_url)[0]
-    try:
-        return _get_json(url, timeout=timeout)
-    except Exception as exc:  # noqa: BLE001 - discovery is best-effort
-        logger.debug(f"Protected-resource metadata unavailable at {url}: {exc}")
-        return None
-
-
-def discover_authorization_server(
-    server_url: str,
-    authorization_servers: Optional[List[str]] = None,
-    timeout: float = 10.0,
-) -> Optional[Dict[str, Any]]:
-    """
-    Discover authorization-server metadata.
-
-    Tries, in order: any ``authorization_servers`` advertised by the
-    protected-resource metadata, then the server-origin
-    ``/.well-known/oauth-authorization-server`` and OpenID-configuration
-    fallbacks.
-
-    Returns the first metadata document that exposes at least an
-    ``authorization_endpoint`` and ``token_endpoint``, or None.
-    """
-    candidates: List[str] = []
-
-    for issuer in authorization_servers or []:
-        issuer = issuer.rstrip("/")
-        candidates.append(issuer + "/.well-known/oauth-authorization-server")
-        candidates.append(issuer + "/.well-known/openid-configuration")
-
-    # Fall back to the resource server's own origin.
-    for candidate in _wellknown_candidates(server_url)[1:]:
-        candidates.append(candidate)
-
-    for url in candidates:
-        try:
-            metadata = _get_json(url, timeout=timeout)
-        except Exception as exc:  # noqa: BLE001 - best-effort discovery
-            logger.debug(f"Auth-server metadata unavailable at {url}: {exc}")
-            continue
-        if metadata.get("authorization_endpoint") and metadata.get("token_endpoint"):
-            return metadata
-
-    return None
-
-
-def discover_oauth_metadata(
-    server_url: str,
-    www_authenticate: Optional[str] = None,
-    timeout: float = 10.0,
-) -> Optional[Dict[str, Any]]:
-    """
-    Full metadata discovery for an OAuth-protected MCP server.
-
-    Combines the ``WWW-Authenticate`` challenge (if any), protected-resource
-    metadata, and authorization-server metadata into a single normalised dict:
-
-        {
-            "authorization_endpoint": str,
-            "token_endpoint": str,
-            "registration_endpoint": str | None,
-            "scopes_supported": list[str] | None,
-            "resource": str | None,
-        }
-
-    Returns None if a usable authorization/token endpoint pair cannot be found.
-    """
-    challenge = parse_www_authenticate(www_authenticate)
-
-    resource_meta = discover_protected_resource(
-        server_url,
-        resource_metadata_url=challenge.get("resource_metadata"),
-        timeout=timeout,
-    )
-
-    authorization_servers = None
-    resource_id = None
-    if resource_meta:
-        authorization_servers = resource_meta.get("authorization_servers")
-        resource_id = resource_meta.get("resource")
-
-    auth_meta = discover_authorization_server(
-        server_url,
-        authorization_servers=authorization_servers,
-        timeout=timeout,
-    )
-    if not auth_meta:
-        return None
-
-    # Enforce the HTTPS/loopback guard on the advertised endpoints too: an
-    # HTTPS metadata document must not be able to smuggle a plaintext
-    # authorization/token/registration endpoint that would later receive
-    # authorization codes, PKCE verifiers, refresh tokens, or client secrets
-    # over an insecure transport.
-    authorization_endpoint = auth_meta["authorization_endpoint"]
-    token_endpoint = auth_meta["token_endpoint"]
-    registration_endpoint = auth_meta.get("registration_endpoint")
-    _require_https(authorization_endpoint)
-    _require_https(token_endpoint)
-    if registration_endpoint:
-        _require_https(registration_endpoint)
-
-    return {
-        "authorization_endpoint": authorization_endpoint,
-        "token_endpoint": token_endpoint,
-        "registration_endpoint": registration_endpoint,
-        "scopes_supported": (
-            auth_meta.get("scopes_supported")
-            or (resource_meta or {}).get("scopes_supported")
-        ),
-        "resource": resource_id,
-    }