democratize providers

scripts/generate_code_snippet_mdx.py

@@ -3,11 +3,191 @@
 Reads .snippet.*.py and .snippet.*.ts files from src/code-samples-generated/
 and creates corresponding MDX files in src/snippets/code-samples/ for use in docs.
 
+When a snippet uses a LangChain-style model argument (`model="…"` in Python or
+`model: "…"` in TypeScript), the generated MDX can be wrapped in <CodeGroup> with the same
+seven provider/model options as /oss/deepagents/quickstart (Google, OpenAI, Anthropic,
+OpenRouter, Fireworks, Baseten, Ollama). Both `provider:model-id` and bare model names
+(for example `claude-sonnet-4-5-20250929`) are recognized.
+
+Snippets are left as a single fenced block when no model argument is found, or when all
+model arguments are marked to keep.
+
+To keep a specific model line:
+
+- In Python, put `# KEEP MODEL` on the line immediately before the `model="..."` line.
+- In TypeScript, put `// KEEP MODEL` on the line immediately before the `model: "..."` line.
+
+The marker line is stripped during processing and that model occurrence is not
+replaced/expanded.
+
 Run as part of `make code-snippets` after Bluehawk extraction.
 """
 
+from __future__ import annotations
+
+import re
 from pathlib import Path
 
+# Python: keyword argument model="…" (init_chat_model / create_deep_agent / etc.).
+DEEPAGENTS_PY_MODEL_KWARG_RE = re.compile(r'\bmodel\s*=\s*"([^"]+)"')
+
+# TypeScript: object property model: "…" (ChatAnthropic, createDeepAgent, …).
+DEEPAGENTS_TS_MODEL_KWARG_RE = re.compile(r'\bmodel\s*:\s*"([^"]+)"')
+
+# Tab title and full `model=` / `model:` token for each variant (matches
+# src/oss/deepagents/quickstart.mdx Python tabs; JS uses google-genai spelling).
+DEEPAGENTS_QUICKSTART_PY_MODEL_TABS: list[tuple[str, str]] = [
+    ("Google", 'model="google_genai:gemini-3.1-pro-preview"'),
+    ("OpenAI", 'model="openai:gpt-5.4"'),
+    ("Anthropic", 'model="anthropic:claude-sonnet-4-6"'),
+    ("OpenRouter", 'model="openrouter:anthropic/claude-sonnet-4-6"'),
+    ("Fireworks", 'model="fireworks:accounts/fireworks/models/qwen3p5-397b-a17b"'),
+    ("Baseten", 'model="baseten:zai-org/GLM-5"'),
+    ("Ollama", 'model="ollama:devstral-2"'),
+]
+
+DEEPAGENTS_QUICKSTART_TS_MODEL_TABS: list[tuple[str, str]] = [
+    ("Google", 'model: "google-genai:gemini-3.1-pro-preview"'),
+    ("OpenAI", 'model: "openai:gpt-5.4"'),
+    ("Anthropic", 'model: "anthropic:claude-sonnet-4-6"'),
+    ("OpenRouter", 'model: "openrouter:anthropic/claude-sonnet-4-6"'),
+    ("Fireworks", 'model: "fireworks:accounts/fireworks/models/qwen3p5-397b-a17b"'),
+    ("Baseten", 'model: "baseten:zai-org/GLM-5"'),
+    ("Ollama", 'model: "ollama:devstral-2"'),
+]
+
+
+def _model_id_from_py_tab_token(tab_token: str) -> str:
+    m = re.match(r'model="([^"]+)"', tab_token)
+    if not m:
+        msg = f"expected model= tab token, got {tab_token!r}"
+        raise ValueError(msg)
+    return m.group(1)
+
+
+def _model_id_from_ts_tab_token(tab_token: str) -> str:
+    m = re.match(r'model:\s*"([^"]+)"', tab_token)
+    if not m:
+        msg = f"expected model: tab token, got {tab_token!r}"
+        raise ValueError(msg)
+    return m.group(1)
+
+
+DEEPAGENTS_PY_SKIP_EXPAND_MODEL_IDS: frozenset[str] = frozenset()
+DEEPAGENTS_TS_SKIP_EXPAND_MODEL_IDS: frozenset[str] = frozenset()
+
+
+def _id_after_first_colon(tab_id: str) -> str:
+    """For openai:gpt-5.4 return gpt-5.4; for bare ids return as-is."""
+    if ":" not in tab_id:
+        return tab_id
+    return tab_id.split(":", 1)[1]
+
+
+KEEP_MODEL_MARKER_PY = "# KEEP MODEL"
+KEEP_MODEL_MARKER_TS = "// KEEP MODEL"
+
+
+def _codegroup_fence(tab_title: str, fence_lang: str, code: str) -> str:
+    """One fenced code block inside a <CodeGroup> (indent matches docs conventions)."""
+    body = "\n".join("    " + line for line in code.splitlines())
+    return "\n".join(
+        [
+            f"    ```{fence_lang} {tab_title}",
+            body,
+            "    ```",
+        ]
+    )
+
+
+def _replace_span(text: str, start: int, end: int, replacement: str) -> str:
+    return text[:start] + replacement + text[end:]
+
+
+def _expand_to_deepagents_codegroup(
+    content: str,
+    *,
+    canonical_span: tuple[int, int],
+    tab_definitions: list[tuple[str, str]],
+    fence_lang: str,
+) -> str:
+    """Wrap `content` in a CodeGroup, one tab per quickstart model variant."""
+    start, end = canonical_span
+    parts = [
+        _codegroup_fence(
+            title, fence_lang, _replace_span(content, start, end, model_token)
+        )
+        for title, model_token in tab_definitions
+    ]
+    return "<CodeGroup>\n" + "\n\n".join(parts) + "\n</CodeGroup>\n"
+
+
+def maybe_expand_deepagents_quickstart_codegroup(
+    content: str,
+    *,
+    language: str,
+    fence_lang: str,
+) -> tuple[str | None, str]:
+    """Return (expanded_mdx_or_none, content_with_keep_markers_stripped)."""
+    model_re: re.Pattern[str]
+    tab_definitions: list[tuple[str, str]]
+    keep_marker: str
+    if language == "python":
+        model_re = DEEPAGENTS_PY_MODEL_KWARG_RE
+        tab_definitions = DEEPAGENTS_QUICKSTART_PY_MODEL_TABS
+        keep_marker = KEEP_MODEL_MARKER_PY
+    elif language == "ts":
+        model_re = DEEPAGENTS_TS_MODEL_KWARG_RE
+        tab_definitions = DEEPAGENTS_QUICKSTART_TS_MODEL_TABS
+        keep_marker = KEEP_MODEL_MARKER_TS
+    else:
+        return None, content
+
+    # Strip marker lines while recording which model occurrence to expand.
+    out_lines: list[str] = []
+    keep_next_model = False
+    canonical_span: tuple[int, int] | None = None
+
+    for line in content.splitlines(keepends=True):
+        if line.strip() == keep_marker:
+            keep_next_model = True
+            continue
+
+        out_offset = sum(len(l) for l in out_lines)
+        m = model_re.search(line)
+        if m is not None:
+            if keep_next_model:
+                keep_next_model = False
+            elif canonical_span is None:
+                canonical_span = (out_offset + m.start(), out_offset + m.end())
+
+        out_lines.append(line)
+
+    stripped = "".join(out_lines)
+    if canonical_span is None:
+        return None, stripped
+
+    return (
+        _expand_to_deepagents_codegroup(
+            stripped,
+            canonical_span=canonical_span,
+            tab_definitions=tab_definitions,
+            fence_lang=fence_lang,
+        ),
+        stripped,
+    )
+
+
+def format_snippet_mdx(content: str, *, language: str, fence_lang: str) -> str:
+    """Return final MDX body for a snippet file."""
+    content = content.rstrip() + "\n"
+    expanded, content = maybe_expand_deepagents_quickstart_codegroup(
+        content, language=language, fence_lang=fence_lang
+    )
+    if expanded is not None:
+        return expanded
+    return f"```{fence_lang}\n{content.rstrip()}\n```\n"
+
 
 def main() -> None:
     repo_root = Path(__file__).resolve().parent.parent
@@ -19,29 +199,24 @@ def main() -> None:
 
     snippets_dir.mkdir(parents=True, exist_ok=True)
 
-    # Mapping: (glob_pattern, language) for each snippet type
     snippet_configs = [
-        ("*.snippet.*.py", "python"),
-        ("*.snippet.*.ts", "ts"),
+        ("*.snippet.*.py", "python", "python"),
+        ("*.snippet.*.ts", "ts", "ts"),
     ]
 
-    # Only process snippets that already have language suffix to
-    # avoid Bluehawk duplicates
     lang_suffix = {"python": "-py", "ts": "-js"}
 
-    for glob_pattern, language in snippet_configs:
+    for glob_pattern, language, fence_lang in snippet_configs:
         for snippet_file in generated_dir.glob(glob_pattern):
             snippet_name = ".".join(snippet_file.stem.split(".")[2:])
             expected_suffix = lang_suffix[language]
-            # Only process language-specific snippets
-            # (tool-return-object-py, not tool-return-object) to avoid
-            # duplicates when Bluehawk emits both suffixed and unsuffixed versions
             if not snippet_name.endswith(expected_suffix):
                 continue
 
             content = snippet_file.read_text(encoding="utf-8")
-            # Create MDX with fenced code block
-            mdx_content = f"```{language}\n{content.rstrip()}\n```\n"
+            mdx_content = format_snippet_mdx(
+                content, language=language, fence_lang=fence_lang
+            )
             mdx_path = snippets_dir / f"{snippet_name}.mdx"
             mdx_path.write_text(mdx_content, encoding="utf-8")
             print(f"Generated {mdx_path.relative_to(repo_root)}")

src/code-samples/deepagents/content-builder.py

@@ -53,6 +53,7 @@ def generate_cover(prompt: str, slug: str) -> str:
 
         client = genai.Client()
         response = client.models.generate_content(
+            # KEEP MODEL
             model="gemini-2.5-flash-image",
             contents=[prompt],
         )
@@ -84,6 +85,7 @@ def generate_social_image(prompt: str, platform: str, slug: str) -> str:
 
         client = genai.Client()
         response = client.models.generate_content(
+            # KEEP MODEL
             model="gemini-2.5-flash-image",
             contents=[prompt],
         )

src/code-samples/deepagents/content-builder.ts

@@ -43,6 +43,7 @@ const generateCover = tool(
       const { GoogleGenerativeAI } = await import("@google/generative-ai");
       const genai = new GoogleGenerativeAI(process.env.GOOGLE_API_KEY ?? "");
       const model = genai.getGenerativeModel({
+        // KEEP MODEL
         model: "gemini-2.5-flash-image",
       });
       const result = await model.generateContent(prompt);
@@ -78,6 +79,7 @@ const generateSocialImage = tool(
       const { GoogleGenerativeAI } = await import("@google/generative-ai");
       const genai = new GoogleGenerativeAI(process.env.GOOGLE_API_KEY ?? "");
       const model = genai.getGenerativeModel({
+        // KEEP MODEL
         model: "gemini-2.5-flash-image",
       });
       const result = await model.generateContent(prompt);
@@ -100,9 +102,7 @@ const generateSocialImage = tool(
       prompt: z
         .string()
         .describe("Detailed description of the image to generate."),
-      platform: z
-        .string()
-        .describe('Either "linkedin" or "tweets"'),
+      platform: z.string().describe('Either "linkedin" or "tweets"'),
       slug: z
         .string()
         .describe("Post slug. Image saves to <platform>/<slug>/image.png"),
@@ -125,6 +125,7 @@ function createContentWriter() {
   };
 
   return createDeepAgent({
+    model: "anthropic:claude-sonnet-4-6",
     memory: ["./AGENTS.md"],
     skills: ["./skills/"],
     tools: [generateCover, generateSocialImage],

src/code-samples/langchain/nostream-tag.py

@@ -6,8 +6,10 @@
 from langchain_anthropic import ChatAnthropic
 from langgraph.graph import START, StateGraph
 
-stream_model = ChatAnthropic(model_name="claude-3-haiku-20240307")
-internal_model = ChatAnthropic(model_name="claude-3-haiku-20240307").with_config(
+# KEEP MODEL
+stream_model = ChatAnthropic(model_name="claude-haiku-4-5-20251001")
+# KEEP MODEL
+internal_model = ChatAnthropic(model_name="claude-haiku-4-5-20251001").with_config(
     {"tags": ["nostream"]}
 )
 

src/code-samples/langchain/nostream-tag.ts

@@ -7,9 +7,11 @@ import { ChatAnthropic } from "@langchain/anthropic";
 import { StateGraph, StateSchema, START } from "@langchain/langgraph";
 import * as z from "zod";
 
-const streamModel = new ChatAnthropic({ model: "claude-3-haiku-20240307" });
+// KEEP MODEL
+const streamModel = new ChatAnthropic({ model: "claude-haiku-4-5-20251001" });
 const internalModel = new ChatAnthropic({
-  model: "claude-3-haiku-20240307",
+  // KEEP MODEL
+  model: "claude-haiku-4-5-20251001",
 }).withConfig({
   tags: ["nostream"],
 });
@@ -42,7 +44,10 @@ const graph = new StateGraph(State)
   .addEdge("writeAnswer", "internal_notes")
   .compile();
 
-const stream = await graph.stream({ topic: "AI" }, { streamMode: "messages" });
+const stream = await graph.stream(
+  { topic: "AI", answer: "", notes: "" },
+  { streamMode: "messages" },
+);
 // :snippet-end:
 
 // :remove-start:

src/code-samples/langchain/streaming-reasoning-tokens.py

@@ -11,6 +11,7 @@ def get_weather(city: str) -> str:
 
 
 model = ChatAnthropic(
+    # KEEP MODEL
     model_name="claude-sonnet-4-6",
     timeout=None,
     stop=None,

src/code-samples/langchain/streaming-reasoning-tokens.ts

@@ -16,6 +16,7 @@ const getWeather = tool(
 
 const agent = createAgent({
   model: new ChatAnthropic({
+    // KEEP MODEL
     model: "claude-sonnet-4-6",
     thinking: { type: "enabled", budget_tokens: 5000 },
   }),