specsmith 0.7.0.dev236__tar.gz → 0.10.0.dev238__tar.gz

{specsmith-0.7.0.dev236/src/specsmith.egg-info → specsmith-0.10.0.dev238}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: specsmith
-Version: 0.7.0.dev236
+Version: 0.10.0.dev238
 Summary: Applied Epistemic Engineering toolkit — AEE agent sessions, execution profiles, FPGA/HDL governance, tool installer, 50+ CLI commands.
 Author: BitConcepts
 License-Expression: MIT

{specsmith-0.7.0.dev236 → specsmith-0.10.0.dev238}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "specsmith"
-version = "0.7.0.dev236"
+version = "0.10.0.dev238"
 description = "Applied Epistemic Engineering toolkit — AEE agent sessions, execution profiles, FPGA/HDL governance, tool installer, 50+ CLI commands."
 readme = "README.md"
 license = "MIT"
@@ -171,6 +171,9 @@ module = [
     "specsmith.importer",
     "specsmith.agent.providers.gemini",
     "specsmith.agent.runner",
+    "specsmith.agent.profiles",
+    "specsmith.agent.fallback",
+    "specsmith.agent.core",
     "specsmith.agent.cleanup",
     "specsmith.agent.orchestrator",
     "specsmith.agent.repl",

{specsmith-0.7.0.dev236 → specsmith-0.10.0.dev238}/src/specsmith/__init__.py

@@ -8,4 +8,4 @@ from importlib.metadata import version as _pkg_version
 try:
     __version__: str = _pkg_version("specsmith")
 except PackageNotFoundError:  # running from source without install
-    __version__ = "0.3.6"  # fallback: keep in sync with pyproject.toml
+    __version__ = "0.10.0"  # fallback: keep in sync with pyproject.toml

{specsmith-0.7.0.dev236 → specsmith-0.10.0.dev238}/src/specsmith/agent/chat_runner.py

@@ -80,11 +80,35 @@ def run_chat(
     history: list[dict[str, Any]] | None = None,
     confidence_target: float = 0.7,
     rules_prefix: str = "",
+    endpoint_id: str | None = None,
 ) -> ChatRunResult | None:
-    """Drive a real LLM turn. Return ``None`` if no provider is reachable."""
+    """Drive a real LLM turn. Return ``None`` if no provider is reachable.
+
+    When ``endpoint_id`` is set, the BYOE store (REQ-142) is consulted and
+    the resolved :class:`Endpoint` short-circuits the provider chain via
+    the new :func:`_run_openai_compat` driver. Any error during endpoint
+    resolution falls back to the legacy auto-detect chain so an offline
+    misconfigured endpoint never breaks `specsmith chat`.
+    """
     history = history or []
     messages = _build_messages(utterance, history, rules_prefix)
 
+    # REQ-142: explicit endpoint override.
+    if endpoint_id:
+        try:
+            from specsmith.agent.endpoints import EndpointStore
+
+            endpoint = EndpointStore.load().resolve(endpoint_id)
+        except Exception:  # noqa: BLE001 - any failure → fall back to auto-detect
+            endpoint = None
+        if endpoint is not None:
+            try:
+                full_text = _run_openai_compat(messages, emitter, msg_block, endpoint=endpoint)
+            except Exception:  # noqa: BLE001 - degrade to auto-detect
+                full_text = None
+            if full_text is not None:
+                return _finalize(full_text, "openai_compat", project_dir, confidence_target)
+
     # Order matters: Ollama first because it's local-first and free.
     for provider in (_run_ollama, _run_anthropic, _run_openai, _run_gemini):
         try:
@@ -228,6 +252,79 @@ def _run_openai(
     return "".join(pieces) if pieces else None
 
 
+def _run_openai_compat(
+    messages: list[dict[str, str]],
+    emitter: EventEmitter,
+    block_id: str,
+    *,
+    endpoint: Any,
+) -> str | None:
+    """Stream from a user-registered OpenAI-v1-compatible endpoint (REQ-142).
+
+    Uses raw stdlib HTTP so the openai SDK is not a hard dependency for
+    BYOE. Sends a streaming ``/chat/completions`` request, decodes the
+    Server-Sent-Events ``data:`` lines, and forwards each ``content``
+    delta as a ``token`` event on ``block_id``.
+    """
+    base_url = endpoint.base_url.rstrip("/")
+    url = f"{base_url}/chat/completions"
+    model = endpoint.default_model or os.environ.get("SPECSMITH_OPENAI_COMPAT_MODEL", "")
+    if not model:
+        # The endpoint did not pin a default model and the env override is
+        # absent. We cannot fabricate one; fall back to the auto-detect chain.
+        return None
+
+    headers: dict[str, str] = {
+        "Content-Type": "application/json",
+        "Accept": "text/event-stream",
+    }
+    try:
+        token = endpoint.resolve_token()
+    except Exception:  # noqa: BLE001 - fall back to auto-detect chain
+        return None
+    if token:
+        headers["Authorization"] = f"Bearer {token}"
+
+    body = json.dumps({"model": model, "messages": messages, "stream": True}).encode("utf-8")
+    req = Request(url, data=body, headers=headers, method="POST")  # noqa: S310 - user-supplied
+
+    ctx = None
+    if not endpoint.verify_tls and url.startswith("https://"):
+        import ssl
+
+        ctx = ssl.create_default_context()
+        ctx.check_hostname = False
+        ctx.verify_mode = ssl.CERT_NONE
+
+    pieces: list[str] = []
+    try:
+        with urlopen(req, timeout=120, context=ctx) as resp:  # noqa: S310 - user-supplied
+            for raw_line in resp:
+                line = raw_line.decode("utf-8", errors="replace").rstrip("\n\r")
+                if not line.startswith("data:"):
+                    continue
+                payload = line[len("data:") :].strip()
+                if not payload or payload == "[DONE]":
+                    if payload == "[DONE]":
+                        break
+                    continue
+                try:
+                    obj = json.loads(payload)
+                except ValueError:
+                    continue
+                choices = obj.get("choices") or []
+                if not choices:
+                    continue
+                delta = (choices[0] or {}).get("delta") or {}
+                chunk = str(delta.get("content") or "")
+                if chunk:
+                    emitter.token(block_id, chunk)
+                    pieces.append(chunk)
+    except (URLError, TimeoutError, OSError):
+        return None
+    return "".join(pieces) if pieces else None
+
+
 def _run_gemini(
     messages: list[dict[str, str]],
     emitter: EventEmitter,

specsmith-0.10.0.dev238/src/specsmith/agent/core.py

@@ -0,0 +1,98 @@
+# SPDX-License-Identifier: MIT
+# Copyright (c) 2026 BitConcepts, LLC. All rights reserved.
+"""Shared agent runtime primitives (REQ-145).
+
+Hosts low-level enums and dataclasses that span :mod:`specsmith.agent.runner`,
+:mod:`specsmith.serve`, :mod:`specsmith.agent.profiles`, and
+:mod:`specsmith.agent.fallback` without forcing them to import each other.
+
+The historical ``cli.py`` referenced ``ModelTier`` from this module before
+it existed in the source tree (the file was lost in an earlier refactor),
+which produced an ``ImportError`` the moment ``specsmith run`` was
+invoked. Restoring the symbol here is the prerequisite for the bridge
+``ready`` event handshake to land before the VS Code extension's 20 s
+startup timeout fires.
+"""
+
+from __future__ import annotations
+
+import enum
+from dataclasses import dataclass, field
+from typing import Any
+
+
+class ModelTier(str, enum.Enum):
+    """Capability tier for an LLM call.
+
+    Ordered cheapest → most capable so that a fallback chain can iterate
+    in declaration order without external metadata.
+    """
+
+    FAST = "fast"
+    BALANCED = "balanced"
+    POWERFUL = "powerful"
+
+    @classmethod
+    def parse(
+        cls,
+        value: str | ModelTier | None,
+        default: ModelTier | None = None,
+    ) -> ModelTier:
+        """Tolerant parser used by CLI option handlers."""
+        if value is None or value == "":
+            return default or cls.BALANCED
+        if isinstance(value, cls):
+            return value
+        try:
+            return cls(str(value).strip().lower())
+        except ValueError:
+            return default or cls.BALANCED
+
+
+@dataclass
+class AgentState:
+    """Mutable per-session metrics surfaced via ``specsmith serve``'s
+    ``GET /api/status`` endpoint and the VS Code TokenMeter chip.
+
+    Field names mirror what :class:`specsmith.serve._AgentThread` reads off
+    ``runner._state``; do not rename without updating that consumer.
+    """
+
+    provider_name: str = ""
+    model_name: str = ""
+    profile_id: str = ""
+    session_tokens: int = 0
+    tokens_in: int = 0
+    tokens_out: int = 0
+    total_cost_usd: float = 0.0
+    tool_calls_made: int = 0
+    elapsed_minutes: float = 0.0
+    by_profile: dict[str, dict[str, Any]] = field(default_factory=dict)
+
+    def credit(
+        self,
+        *,
+        profile_id: str,
+        tokens_in: int = 0,
+        tokens_out: int = 0,
+        cost_usd: float = 0.0,
+        tool_calls: int = 0,
+    ) -> None:
+        """Aggregate one turn's metrics into the running totals."""
+        self.tokens_in += int(tokens_in)
+        self.tokens_out += int(tokens_out)
+        self.session_tokens = self.tokens_in + self.tokens_out
+        self.total_cost_usd += float(cost_usd)
+        self.tool_calls_made += int(tool_calls)
+        bucket = self.by_profile.setdefault(
+            profile_id or "(default)",
+            {"tokens_in": 0, "tokens_out": 0, "cost_usd": 0.0, "tool_calls": 0, "turns": 0},
+        )
+        bucket["tokens_in"] += int(tokens_in)
+        bucket["tokens_out"] += int(tokens_out)
+        bucket["cost_usd"] = round(bucket["cost_usd"] + float(cost_usd), 6)
+        bucket["tool_calls"] += int(tool_calls)
+        bucket["turns"] += 1
+
+
+__all__ = ["AgentState", "ModelTier"]