feat(ai): ecosysteme d'outils phase 2 - recherche a cle, cache/retry, Playwright, crawl, Gitea/GitHub, documents (#92)

backend/tools/connected.py

@@ -0,0 +1,239 @@
+"""Connected sources — Gitea & GitHub repositories (phase 2 #92).
+
+The assistant can query the source-hosting platforms the project actually
+uses (ObsiGate is hosted on Gitea): repositories, issues/pull requests and
+repository files. Everything is READ-risk, rate-limited through the shared
+registry and audited.
+
+Configuration (environment — injected by Infisical in production, never
+hard-coded):
+
+* ``OBSIGATE_GITEA_URL``    — base URL of the self-hosted instance (e.g.
+  ``https://git.example.net``); the ``gitea`` provider is only available when
+  this variable is set. Admin-controlled, so the SSRF guard does not apply
+  (unlike user-supplied URLs).
+* ``OBSIGATE_GITEA_TOKEN``  — optional personal access token (private repos).
+* ``OBSIGATE_GITHUB_TOKEN`` — optional token (raises the API rate limits and
+  unlocks private repositories).
+
+Cloud drives (Google Drive / OneDrive) deliberately stay out of the core:
+per the documented roadmap they are best served by an *external MCP server*
+(#79) so the OAuth surface remains outside ObsiGate.
+"""
+
+from __future__ import annotations
+
+import base64
+import binascii
+import logging
+import os
+from typing import Any
+
+import httpx
+
+from backend.tools.context import ToolError, ToolRisk
+from backend.tools.registry import tool
+from backend.tools.schemas import GitGetFileInput, GitProviderInput, GitSearchIssuesInput
+
+logger = logging.getLogger("obsigate.tools.connected")
+
+TIMEOUT = 10.0
+USER_AGENT = "ObsiGateAssistant/1.0 (+self-hosted vault AI)"
+MAX_FILE_BYTES = 300_000
+GITHUB_API = "https://api.github.com"
+
+
+def _provider_base(provider: str) -> tuple[str, str]:
+    """Return (base_url, auth_header_value) for the requested provider."""
+    if provider == "gitea":
+        base = os.environ.get("OBSIGATE_GITEA_URL", "").strip().rstrip("/")
+        if not base:
+            raise ToolError(
+                "Source Gitea non configurée (OBSIGATE_GITEA_URL absente).",
+                code="provider_not_configured",
+            )
+        token = os.environ.get("OBSIGATE_GITEA_TOKEN", "").strip()
+        return base, f"token {token}" if token else ""
+    if provider == "github":
+        token = os.environ.get("OBSIGATE_GITHUB_TOKEN", "").strip()
+        return GITHUB_API, f"Bearer {token}" if token else ""
+    raise ToolError(
+        f"Fournisseur inconnu : {provider} ('gitea' ou 'github')",
+        code="invalid_arguments",
+    )
+
+
+def _headers(auth: str) -> dict[str, str]:
+    headers = {"User-Agent": USER_AGENT, "Accept": "application/json"}
+    if auth:
+        headers["Authorization"] = auth
+    return headers
+
+
+def _request(method: str, url: str, auth: str, **kwargs: Any) -> httpx.Response:
+    try:
+        resp = httpx.request(
+            method, url, headers=_headers(auth), timeout=TIMEOUT, follow_redirects=False,
+            **kwargs,
+        )
+    except httpx.HTTPError as e:
+        logger.warning("connected source request failed %s: %s", url, e)
+        raise ToolError(
+            "Source connectée momentanément indisponible.",
+            code="connected_source_unavailable",
+        ) from e
+    if resp.status_code in (401, 403):
+        raise ToolError(
+            "Accès refusé par la source connectée (jeton manquant ou expiré).",
+            code="permission_denied",
+        )
+    if resp.status_code == 404:
+        raise ToolError("Ressource introuvable sur la source connectée.", code="not_found")
+    resp.raise_for_status()
+    return resp
+
+
+def _normalize_repo(item: dict[str, Any]) -> dict[str, Any]:
+    return {
+        "name": item.get("name") or "",
+        "full_name": item.get("full_name") or "",
+        "url": item.get("html_url") or item.get("clone_url") or "",
+        "description": item.get("description") or "",
+        "updated": item.get("updated_at") or "",
+        "private": bool(item.get("private", False)),
+    }
+
+
+@tool(
+    name="git_list_repos",
+    description=(
+        "List repositories on the connected Gitea instance or GitHub account "
+        "(name, url, description, last update). Use when the user asks about "
+        "their code projects."
+    ),
+    input_model=GitProviderInput,
+    risk=ToolRisk.READ,
+)
+def git_list_repos(ctx, params: GitProviderInput) -> dict[str, Any]:
+    """Query the configured source and return normalized repositories."""
+    base, auth = _provider_base(params.provider)
+    if params.provider == "gitea":
+        url = base + "/api/v1/repos/search"
+        query: dict[str, Any] = {"limit": params.limit}
+        if params.repo:
+            query["q"] = params.repo
+        resp = _request("GET", url, auth, params=query)
+        items = resp.json().get("data") or []
+    else:
+        if params.repo:
+            url = GITHUB_API + f"/repos/{params.repo.strip('/')}"
+            items = [_request("GET", url, auth).json()]
+        else:
+            resp = _request(
+                "GET", GITHUB_API + "/user/repos",
+                auth, params={"per_page": params.limit, "sort": "updated"},
+            )
+            items = resp.json()
+    repos = [_normalize_repo(item) for item in items if isinstance(item, dict)]
+    return {"provider": params.provider, "count": len(repos), "repos": repos}
+
+
+@tool(
+    name="git_search_issues",
+    description=(
+        "Search issues and pull requests on the connected Gitea instance or "
+        "GitHub (title/body keywords, optional repository scope, open/closed)."
+    ),
+    input_model=GitSearchIssuesInput,
+    risk=ToolRisk.READ,
+)
+def git_search_issues(ctx, params: GitSearchIssuesInput) -> dict[str, Any]:
+    """Query issues (and PRs) from the configured source."""
+    base, auth = _provider_base(params.provider)
+    state = params.state if params.state in ("open", "closed") else "open"
+    if params.provider == "gitea":
+        if params.repo:
+            url = base + f"/api/v1/repos/{params.repo.strip('/')}/issues"
+            query: dict[str, Any] = {"state": state, "limit": params.limit, "q": params.query}
+            resp = _request("GET", url, auth, params=query)
+            items = resp.json()
+        else:
+            url = base + "/api/v1/repos/issues/search"
+            resp = _request("GET", url, auth, params={
+                "q": params.query, "state": state, "limit": params.limit,
+            })
+            items = resp.json()
+    else:
+        clause = f"{params.query} is:issue is:{state}"
+        if params.repo:
+            clause += f" repo:{params.repo.strip('/')}"
+        resp = _request(
+            "GET", GITHUB_API + "/search/issues", auth,
+            params={"q": clause, "per_page": params.limit},
+        )
+        items = (resp.json().get("items") or [])
+    issues = [
+        {
+            "id": item.get("number") or item.get("id") or "",
+            "title": (item.get("title") or "")[:300],
+            "url": item.get("html_url") or "",
+            "state": item.get("state") or "",
+            "pull_request": bool(item.get("pull_request")),
+        }
+        for item in (items if isinstance(items, list) else [])
+        if isinstance(item, dict)
+    ]
+    return {
+        "provider": params.provider,
+        "query": params.query,
+        "count": len(issues),
+        "issues": issues,
+    }
+
+
+@tool(
+    name="git_get_file",
+    description=(
+        "Read a file's content from a connected Gitea or GitHub repository "
+        "(source code, docs, config). Text/JSON only, size-capped."
+    ),
+    input_model=GitGetFileInput,
+    risk=ToolRisk.READ,
+)
+def git_get_file(ctx, params: GitGetFileInput) -> dict[str, Any]:
+    """Fetch one repository file and return its decoded text content."""
+    base, auth = _provider_base(params.provider)
+    repo = params.repo.strip("/")
+    path = params.path.strip("/")
+    if not repo or not path:
+        raise ToolError(
+            "'repo' (owner/nom) et 'path' sont obligatoires", code="invalid_arguments"
+        )
+    if params.provider == "gitea":
+        url = base + f"/api/v1/repos/{repo}/contents/{path}"
+    else:
+        url = GITHUB_API + f"/repos/{repo}/contents/{path}"
+    if params.ref:
+        url += f"?ref={params.ref}"
+    resp = _request("GET", url, auth)
+    data = resp.json()
+    encoded = data.get("content") or ""
+    if (data.get("encoding") or "") == "base64" and encoded:
+        try:
+            content = base64.b64decode(encoded).decode("utf-8", errors="replace")
+        except (ValueError, binascii.Error) as e:
+            raise ToolError(
+                "Contenu du fichier illisible (encodage inattendu).",
+                code="file_decode_error",
+            ) from e
+    else:
+        content = encoded
+    truncated = len(content) > MAX_FILE_BYTES
+    return {
+        "provider": params.provider,
+        "repo": repo,
+        "path": data.get("path") or path,
+        "size": data.get("size") or len(content),
+        "content": content[:MAX_FILE_BYTES],
+        "truncated": truncated,
+    }