model-router-cli 1.0.2__tar.gz → 1.1.0__tar.gz

model_router_cli-1.1.0/LICENSE

@@ -0,0 +1,209 @@
+MIT License
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+Copyright (c) 2026 Model Router Contributors
+Copyright (c) 2026 PicadoLabs
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+   1. Definitions.
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2026 Model Router Contributors
+   Copyright 2026 PicadoLabs
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

{model_router_cli-1.0.2/backend/model_router_cli.egg-info → model_router_cli-1.1.0}/PKG-INFO

@@ -1,17 +1,17 @@
 Metadata-Version: 2.4
 Name: model-router-cli
-Version: 1.0.2
+Version: 1.1.0
 Summary: Intelligent, explainable LLM request routing platform & AI Traffic Control Room
 Author-email: PicadoLabs <picadolabs@gmail.com>
-Maintainer-email: Kaap10 <picadolabs@gmail.com>
-License: MIT
+Maintainer-email: PicadoLabs <picadolabs@gmail.com>
+License: Apache-2.0
 Project-URL: Homepage, https://picadolabs.me
 Project-URL: Repository, https://github.com/PicadoLabs/ai-model-router
 Project-URL: Issues, https://github.com/PicadoLabs/ai-model-router/issues
 Keywords: llm,ai,router,fastapi,ollama,openai,cost-optimization
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
+Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
@@ -34,18 +34,34 @@ Requires-Dist: sse-starlette>=2.0.0
 Requires-Dist: python-multipart>=0.0.9
 Requires-Dist: python-dotenv>=1.0.1
 Requires-Dist: tiktoken>=0.6.0
+Requires-Dist: redis>=5.0.0
+Requires-Dist: asyncpg>=0.29.0
+Requires-Dist: alembic>=1.13.0
 Dynamic: license-file
 
 # Model Router
 
 [![PyPI - Version](https://img.shields.io/pypi/v/model-router-cli?logo=pypi&logoColor=white&color=blue)](https://pypi.org/project/model-router-cli/)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/model-router-cli?logo=python&logoColor=white)](https://pypi.org/project/model-router-cli/)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Downloads](https://static.pepy.tech/badge/model-router-cli)](https://pepy.tech/project/model-router-cli)
 
 Intelligent, explainable, cost- and latency-aware LLM request routing platform and AI Traffic Control Room.
 
 ---
 
+
+## The Real-World Problem
+Companies building AI applications face ballooning API costs, rate limits, and latency spikes. They want to use large models (like GPT-4 or Claude 3.5 Sonnet) for complex reasoning, but cheaper/faster models (like Llama 3 or Haiku) for simple tasks. Manually writing logic to route these requests is brittle and hard to maintain.
+
+## Why it's Unique (The "Edge")
+- **The "Traffic Control Room":** A stunning frontend UI that makes routing decisions transparent and explainable. You don't just route; you see *why* a request went to a specific model.
+- **100% Local & Self-Hosted:** No data leaves the user's infrastructure.
+- **A/B Policy Experimentation:** Built-in tools to test different routing policies (e.g., "lowest cost" vs "balanced") and see projected savings.
+- **Dual-Mode Analyzer:** Uses both fast heuristics (regex/length) and LLM-based complexity scoring to route requests efficiently.
+- **Production-Ready Scalability:** Database-agnostic (SQLite for local dev, PostgreSQL for production) with Redis Pub/Sub powering the real-time SSE traffic telemetry across distributed worker nodes.
+- **Resilient Execution:** Built-in sliding-window circuit breaker dynamically bypasses failing upstream providers to prevent cascading latency spikes.
+
 ## Overview
 
 Model Router intercepts incoming AI requests, analyzes their task type and continuous complexity, evaluates available models against a configurable multi-criteria scoring objective, selects the optimal candidate, and dispatches the request with automatic fallback handling and budget guards.
@@ -217,7 +233,8 @@ npm run dev
 
 ## CLI Usage
 
-The built-in Typer CLI provides terminal commands for inspection, diagnostics, and testing (use `modelrouter` if installed via pip, or `python backend/app/cli/main.py` from source):
+The built-in Typer CLI provides terminal commands for inspection, diagnostics, and testing (use `modelrouter` if installed via pip, or `python backend/app/cli/main.py` from source).
+You can append `--json` or `-j` to most commands to output raw, pipeable JSON instead of Rich formatted tables:
 
 ```bash
 # Launch the AI Traffic Control Room Web UI and API Gateway
@@ -327,7 +344,7 @@ AI-Model-Router/
 │   │   ├── providers/       # Decoupled adapters (Mock, Ollama, Cloud)
 │   │   ├── router/          # Core scoring matrix, pruner, and rules engine
 │   │   └── storage/         # SQLAlchemy models and SQLite async database
-│   ├── tests/               # Pytest test suite (15 passing tests)
+│   ├── tests/               # Pytest test suite (23 passing tests)
 │   ├── main.py              # FastAPI application entrypoint
 │   └── requirements.txt     # Python backend dependencies
 ├── frontend/
@@ -340,7 +357,8 @@ AI-Model-Router/
 ├── .gitignore               # Git exclusions
 ├── CODE_OF_CONDUCT.md       # Contributor Covenant Code of Conduct
 ├── CONTRIBUTING.md          # Contribution guidelines and workflow
-├── LICENSE                  # MIT License
+├── LICENSE                  # Apache 2.0 License
+├── milestone.md             # Development milestone roadmap & issue tracker
 ├── README.md                # Project documentation
 ├── requirements.txt         # Root Python dependencies
 └── SECURITY.md              # Vulnerability reporting and security policy
@@ -364,7 +382,7 @@ Security and privacy are core to Model Router. For vulnerability reporting proce
 
 ## License
 
-This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.
 
 ---
 

model_router_cli-1.0.2/PKG-INFO → model_router_cli-1.1.0/README.md

@@ -1,51 +1,26 @@
-Metadata-Version: 2.4
-Name: model-router-cli
-Version: 1.0.2
-Summary: Intelligent, explainable LLM request routing platform & AI Traffic Control Room
-Author-email: PicadoLabs <picadolabs@gmail.com>
-Maintainer-email: Kaap10 <picadolabs@gmail.com>
-License: MIT
-Project-URL: Homepage, https://picadolabs.me
-Project-URL: Repository, https://github.com/PicadoLabs/ai-model-router
-Project-URL: Issues, https://github.com/PicadoLabs/ai-model-router/issues
-Keywords: llm,ai,router,fastapi,ollama,openai,cost-optimization
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: fastapi>=0.110.0
-Requires-Dist: uvicorn[standard]>=0.28.0
-Requires-Dist: pydantic>=2.6.0
-Requires-Dist: pydantic-settings>=2.2.0
-Requires-Dist: sqlalchemy>=2.0.28
-Requires-Dist: aiosqlite>=0.20.0
-Requires-Dist: httpx>=0.27.0
-Requires-Dist: typer>=0.12.0
-Requires-Dist: rich>=13.7.0
-Requires-Dist: sse-starlette>=2.0.0
-Requires-Dist: python-multipart>=0.0.9
-Requires-Dist: python-dotenv>=1.0.1
-Requires-Dist: tiktoken>=0.6.0
-Dynamic: license-file
-
 # Model Router
 
 [![PyPI - Version](https://img.shields.io/pypi/v/model-router-cli?logo=pypi&logoColor=white&color=blue)](https://pypi.org/project/model-router-cli/)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/model-router-cli?logo=python&logoColor=white)](https://pypi.org/project/model-router-cli/)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Downloads](https://static.pepy.tech/badge/model-router-cli)](https://pepy.tech/project/model-router-cli)
 
 Intelligent, explainable, cost- and latency-aware LLM request routing platform and AI Traffic Control Room.
 
 ---
 
+
+## The Real-World Problem
+Companies building AI applications face ballooning API costs, rate limits, and latency spikes. They want to use large models (like GPT-4 or Claude 3.5 Sonnet) for complex reasoning, but cheaper/faster models (like Llama 3 or Haiku) for simple tasks. Manually writing logic to route these requests is brittle and hard to maintain.
+
+## Why it's Unique (The "Edge")
+- **The "Traffic Control Room":** A stunning frontend UI that makes routing decisions transparent and explainable. You don't just route; you see *why* a request went to a specific model.
+- **100% Local & Self-Hosted:** No data leaves the user's infrastructure.
+- **A/B Policy Experimentation:** Built-in tools to test different routing policies (e.g., "lowest cost" vs "balanced") and see projected savings.
+- **Dual-Mode Analyzer:** Uses both fast heuristics (regex/length) and LLM-based complexity scoring to route requests efficiently.
+- **Production-Ready Scalability:** Database-agnostic (SQLite for local dev, PostgreSQL for production) with Redis Pub/Sub powering the real-time SSE traffic telemetry across distributed worker nodes.
+- **Resilient Execution:** Built-in sliding-window circuit breaker dynamically bypasses failing upstream providers to prevent cascading latency spikes.
+
 ## Overview
 
 Model Router intercepts incoming AI requests, analyzes their task type and continuous complexity, evaluates available models against a configurable multi-criteria scoring objective, selects the optimal candidate, and dispatches the request with automatic fallback handling and budget guards.
@@ -217,7 +192,8 @@ npm run dev
 
 ## CLI Usage
 
-The built-in Typer CLI provides terminal commands for inspection, diagnostics, and testing (use `modelrouter` if installed via pip, or `python backend/app/cli/main.py` from source):
+The built-in Typer CLI provides terminal commands for inspection, diagnostics, and testing (use `modelrouter` if installed via pip, or `python backend/app/cli/main.py` from source).
+You can append `--json` or `-j` to most commands to output raw, pipeable JSON instead of Rich formatted tables:
 
 ```bash
 # Launch the AI Traffic Control Room Web UI and API Gateway
@@ -327,7 +303,7 @@ AI-Model-Router/
 │   │   ├── providers/       # Decoupled adapters (Mock, Ollama, Cloud)
 │   │   ├── router/          # Core scoring matrix, pruner, and rules engine
 │   │   └── storage/         # SQLAlchemy models and SQLite async database
-│   ├── tests/               # Pytest test suite (15 passing tests)
+│   ├── tests/               # Pytest test suite (23 passing tests)
 │   ├── main.py              # FastAPI application entrypoint
 │   └── requirements.txt     # Python backend dependencies
 ├── frontend/
@@ -340,7 +316,8 @@ AI-Model-Router/
 ├── .gitignore               # Git exclusions
 ├── CODE_OF_CONDUCT.md       # Contributor Covenant Code of Conduct
 ├── CONTRIBUTING.md          # Contribution guidelines and workflow
-├── LICENSE                  # MIT License
+├── LICENSE                  # Apache 2.0 License
+├── milestone.md             # Development milestone roadmap & issue tracker
 ├── README.md                # Project documentation
 ├── requirements.txt         # Root Python dependencies
 └── SECURITY.md              # Vulnerability reporting and security policy
@@ -364,7 +341,7 @@ Security and privacy are core to Model Router. For vulnerability reporting proce
 
 ## License
 
-This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.
 
 ---
 

{model_router_cli-1.0.2 → model_router_cli-1.1.0}/backend/app/api/routes.py

@@ -1,4 +1,4 @@
-import uuid
+import uuid
 import time
 import asyncio
 import csv
@@ -6,11 +6,13 @@ import io
 from typing import List, Optional, Dict, Any
 from fastapi import APIRouter, Depends, HTTPException, Query
 from fastapi.responses import JSONResponse, StreamingResponse
+from sse_starlette.sse import EventSourceResponse
 from pydantic import BaseModel, Field
 from sqlalchemy.ext.asyncio import AsyncSession
 from sqlalchemy import select, desc
 
 from app.storage.database import get_db
+from app.storage.redis_client import get_redis
 from app.storage.models import (
     ModelRecord,
     RoutingPolicyRecord,
@@ -36,6 +38,7 @@ from app.budgets.manager import check_budget_threshold
 from app.observability.events import log_router_event
 from app.analytics.service import get_system_analytics, calculate_cost_savings
 from app.providers.registry import provider_registry
+from app.fallback.circuit_breaker import circuit_breaker
 from app.config.settings import get_settings
 
 router = APIRouter()
@@ -56,6 +59,8 @@ class GenerateRequest(BaseModel):
     force_model: Optional[str] = None
     temperature: float = 0.7
     max_retries: int = 1
+    stream: bool = False
+    stream: bool = False
 
 
 class FeedbackSubmitRequest(BaseModel):
@@ -223,7 +228,122 @@ async def api_generate_response(req: GenerateRequest, db: AsyncSession = Depends
     target_meta = next((m for m in models if m.id == selected_model_id), None)
     selected_provider_id = target_meta.provider if target_meta else decision.provider
 
-    # 5. Provider Execution with Fallback & Retries
+    if req.stream:
+        from app.storage.database import AsyncSessionLocal
+        import json
+        
+        async def stream_generator():
+            p_id = selected_provider_id
+            m_id = selected_model_id
+            is_fallback = False
+            
+            if not circuit_breaker.is_available(p_id):
+                p_id = "mock"
+                m_id = "mock-balanced"
+                is_fallback = True
+
+            provider = provider_registry.get_provider(p_id) or provider_registry.get_provider("mock")
+            full_content = ""
+            first_token_ms = None
+            t_stream_start = time.perf_counter()
+            
+            yield {"event": "start", "data": json.dumps({"model": m_id, "provider": p_id})}
+            
+            try:
+                async for chunk in provider.stream(
+                    prompt=req.prompt,
+                    model_id=m_id,
+                    system_prompt=req.system_prompt,
+                    temperature=req.temperature,
+                ):
+                    if first_token_ms is None:
+                        first_token_ms = (time.perf_counter() - t_stream_start) * 1000.0
+                    full_content += chunk
+                    yield {"event": "chunk", "data": json.dumps({"chunk": chunk})}
+            except Exception as e:
+                yield {"event": "error", "data": json.dumps({"error": str(e)})}
+            
+            t_total = time.perf_counter() - t_start
+            
+            async with AsyncSessionLocal() as stream_db:
+                in_tok = max(1, len(req.prompt) // 4)
+                out_tok = max(1, len(full_content) // 4)
+                cost_in = target_meta.cost_per_input_token if target_meta else 0.0
+                cost_out = target_meta.cost_per_output_token if target_meta else 0.0
+                actual_cost = round((in_tok * cost_in) + (out_tok * cost_out), 6)
+                
+                res_base = await stream_db.execute(select(ModelRecord).filter_by(id=settings.BASELINE_MODEL_ID))
+                base_m = res_base.scalar_one_or_none()
+                base_cost = round((in_tok * base_m.cost_per_input_token) + (out_tok * base_m.cost_per_output_token), 6) if base_m else 0.0
+                saved_cost = max(0.0, round(base_cost - actual_cost, 6))
+
+                from app.budgets.manager import check_budget_threshold
+                await check_budget_threshold(stream_db, actual_cost)
+                
+                req_record = RequestRecord(
+                    request_id=req_id,
+                    prompt=req.prompt,
+                    task_type=analysis.task_type.value,
+                    complexity=analysis.complexity,
+                    context_size=analysis.context_size,
+                    reasoning_required=analysis.reasoning_required,
+                    coding_required=analysis.coding_required,
+                    routing_policy=policy_name,
+                    selected_model=m_id,
+                    provider=p_id,
+                    status="SUCCESS",
+                    fallback_used=is_fallback,
+                    input_tokens=in_tok,
+                    output_tokens=out_tok,
+                    total_tokens=in_tok + out_tok,
+                    estimated_cost=actual_cost,
+                    baseline_cost=base_cost,
+                    cost_saved=saved_cost,
+                    routing_latency_ms=round(routing_latency_ms, 2),
+                    provider_latency_ms=round((time.perf_counter() - t_stream_start) * 1000.0, 2),
+                    total_latency_ms=round(t_total * 1000.0, 2),
+                    time_to_first_token_ms=round(first_token_ms, 2) if first_token_ms else 0.0,
+                )
+                stream_db.add(req_record)
+
+                decision_record = RoutingDecisionRecord(
+                    decision_id=decision.decision_id,
+                    request_id=req_id,
+                    selected_model=decision.selected_model,
+                    confidence=decision.confidence,
+                    reasons=decision.reasons,
+                    candidate_scores=[s.model_dump() for s in decision.candidate_scores],
+                    rejected_candidates=decision.rejected_candidates,
+                    policy_used=policy_name,
+                )
+                stream_db.add(decision_record)
+
+                resp_record = ResponseRecord(
+                    response_id=f"resp_{uuid.uuid4().hex[:12]}",
+                    request_id=req_id,
+                    model_id=m_id,
+                    provider=p_id,
+                    content=full_content,
+                    finish_reason="stop",
+                    is_mock=(p_id == "mock"),
+                )
+                stream_db.add(resp_record)
+                await stream_db.commit()
+
+                log_router_event(
+                    event_name="request_completed_stream",
+                    request_id=req_id,
+                    model=m_id,
+                    provider=p_id,
+                    duration_ms=round(t_total * 1000.0, 2),
+                    metadata={"tokens": in_tok + out_tok, "cost": actual_cost, "fallback": is_fallback},
+                )
+            
+            yield {"event": "done", "data": "[DONE]"}
+
+        return EventSourceResponse(stream_generator())
+    
+    # 5. Provider Execution with Fallback & Retries (Non-stream)
     provider_resp, fallback_used, orig_model, fallback_reason = await execute_with_fallback(
         prompt=req.prompt,
         selected_model_id=selected_model_id,
@@ -334,6 +454,7 @@ async def api_generate_response(req: GenerateRequest, db: AsyncSession = Depends
     }
 
 
+
 # Models & Registry Endpoints
 @router.get("/api/models")
 async def list_models(db: AsyncSession = Depends(get_db)):
@@ -389,6 +510,26 @@ async def get_traffic_feed(limit: int = 50, db: AsyncSession = Depends(get_db)):
     return res.scalars().all()
 
 
+
+@router.get("/api/traffic/stream")
+async def traffic_stream():
+    redis = get_redis()
+    if not redis:
+        raise HTTPException(status_code=503, detail="Redis Pub/Sub not available")
+        
+    async def event_generator():
+        pubsub = redis.pubsub()
+        await pubsub.subscribe("traffic_stream")
+        try:
+            async for message in pubsub.listen():
+                if message["type"] == "message":
+                    yield {"event": "traffic", "data": message["data"]}
+        finally:
+            await pubsub.unsubscribe("traffic_stream")
+            await pubsub.close()
+            
+    return EventSourceResponse(event_generator())
+
 @router.get("/api/traffic/export")
 async def export_traffic(
     format: str = Query("json", pattern="^(csv|json)$"),