test(pdf): helper d'ouverture robuste au vault replie (BUG-060)

.env.example

@@ -74,3 +74,19 @@ DEEPSEEK_MODEL=deepseek-chat
 # Chaîne de repli sans clé (DuckDuckGo puis Bing) si SearXNG ne remonte rien
 # OBSIGATE_WEB_FALLBACK=1
 # OBSIGATE_WEB_TIMEOUT=10
+# Fournisseurs à clé (#92), essayés avant SearXNG — injecter via Infisical en prod
+# OBSIGATE_TAVILY_API_KEY=
+# OBSIGATE_BRAVE_API_KEY=
+# OBSIGATE_SERPAPI_API_KEY=
+# OBSIGATE_EXA_API_KEY=
+# Ordre des fournisseurs (sinon : clés présentes puis SearXNG puis replis)
+# OBSIGATE_WEB_PROVIDERS=brave,searxng
+# Réessais réseau (backoff maison) + cache SQLite des résultats web
+# OBSIGATE_WEB_RETRY=1
+# OBSIGATE_WEB_CACHE_TTL=900          # secondes ; 0 = cache désactivé
+# Rendu dynamique (pages SPA) — dépendance optionnelle :
+#   pip install playwright && playwright install chromium
+# ── Assistant IA — sources connectées (Gitea / GitHub) ──
+# OBSIGATE_GITEA_URL=https://git.example.net
+# OBSIGATE_GITEA_TOKEN=
+# OBSIGATE_GITHUB_TOKEN=

.gitea/workflows/ci.yml

@@ -38,6 +38,7 @@ jobs:
       - name: Frontend unit tests
         run: |
           node tests/frontend/unit.test.mjs
+          node tests/frontend/pdf-viewer.test.mjs
           node tests/frontend/forge-completion.test.mjs
 
       - name: Frontend JSDOM tests (PaneManager + Excalidraw + Plugins + AI + SW + Collab + Mobile + Semantic + Desktop + Inline edition)

CHANGELOG.md

@@ -6,7 +6,7 @@ Format basé sur [Keep a Changelog](https://keepachangelog.com/fr/1.1.0/),
 et [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 > **En cours de développement** : les changements à venir sont listés dans la section
-> [Unreleased](#unreleased). La dernière version livrée est **2.9.1**.
+> [Unreleased](#unreleased). La dernière version livrée est **2.11.2**.
 
 ---
 
@@ -14,6 +14,98 @@ et [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ---
 
+## [2.11.2] — 2026-09-17
+
+### Modifié
+
+- **Tests E2E PDF (BUG-060)** : le helper d'ouverture de fichier de
+  `tests/e2e/pdf-viewer.spec.js` étend désormais le vault dans l'arborescence s'il est replié
+  (cas d'une instance avec authentification activée) au lieu de supposer le vault déjà déplié.
+
+---
+
+## [2.11.1] — 2026-09-17
+
+### Corrigé
+
+- **BUG-060 — Viewer PDF : l'affichage des pages ne fonctionnait pas** : au clic sur un fichier
+  `.pdf`, seule la barre d'outils « PDF — N pages » s'affichait, le corps restant vide. La CSP
+  durcie en BUG-034 pose `object-src 'none'`, directive qui gouverne `<embed>`/`<object>`, alors
+  que le viewer rendait le PDF via `<embed type="application/pdf">` : le lecteur natif était
+  bloqué. Le rendu passe désormais par une `<iframe>` (autorisée par `frame-src 'self'`, le stream
+  `/api/file/{vault}/pdf/stream` étant same-origin) ; `object-src 'none'` est conservé. Fichiers :
+  `frontend/js/viewer.js`, `tests/frontend/pdf-viewer.test.mjs` (nouveau),
+  `tests/e2e/pdf-viewer.spec.js` (nouveau, fixture `test_vault/sample-pdf.pdf`).
+
+---
+
+## [2.11.0] — 2026-09-17
+
+### Ajouté
+
+- **#103 — Clés des sources connectées configurables depuis la page Configurations** : nouvelle
+  section « 🔗 Sources connectées & recherche » (admin) permettant de saisir ses propres jetons
+  sans toucher aux variables d'environnement : clés de recherche web à clé (Tavily, Brave,
+  SerpAPI, Exa), URL Gitea + token, token GitHub. Stockage dans `data/api_keys.json` (même
+  fichier que les clés des fournisseurs IA) via les endpoints
+  `GET/POST/DELETE /api/config/tool-keys` (GET masque les secrets, URLs en clair ; liste
+  blanche stricte ; admin requis). Les outils lisent la valeur stockée **en priorité** puis
+  l'environnement (Infisical) — `backend/tools/secrets.py`. Fichiers :
+  `backend/tools/{secrets,web,connected}.py`, `backend/main.py`, `frontend/index.html`,
+  `frontend/js/config.js`, `frontend/locales/{fr,en}.json`, `tests/test_tool_keys.py` (nouveau),
+  `tests/test_connected_tools.py`.
+
+---
+
+## [2.10.1] — 2026-09-17
+
+### Corrigé
+
+- **BUG-059 — Assistant IA : un clic dans la conversation faisait sauter le texte au bas de la
+  fenêtre** : dans une conversation ouverte (post ancré en haut), tout clic — lien de fichier,
+  étapes, sélection de texte — dépinait l'ancre via le gestionnaire `mousedown` et retirait le
+  padding d'ancre, bornant le scroll à la nouvelle hauteur max (saut au bas). Le dépintage est
+  désormais réservé aux vrais gestes de scroll : molette, tactile et poignée de scroll
+  uniquement (`isScrollbarPress`). Fichiers : `frontend/js/bookslm.js`,
+  `tests/frontend/ai.test.mjs`.
+- **#92 — `create_pdf` de l'Assistant : tableaux mal formatés** : l'outil `create_pdf`
+  (génération PDF via l'assistant) utilisait un rendu reportlab simplifié sans support des
+  tableaux. Il passe désormais par le même pipeline que le bouton « Télécharger PDF » de la
+  page document (mistune + plugin `table` + WeasyPrint), avec repli automatique sur le rendu
+  simple si WeasyPrint n'est pas disponible (GTK absent). Fichiers :
+  `backend/tools/documents.py`, `tests/test_document_tools.py`.
+
+---
+
+## [2.10.0] — 2026-09-17
+
+### Ajouté
+
+- **#92 — Assistant IA : écosystème d'outils phase 2 (web étendu, sources connectées, documents)** :
+  - **Recherche web à clé** : fournisseurs optionnels essayés avant SearXNG — Tavily, Brave
+    Search, SerpAPI (Google) et Exa (`OBSIGATE_TAVILY_API_KEY`, `OBSIGATE_BRAVE_API_KEY`,
+    `OBSIGATE_SERPAPI_API_KEY`, `OBSIGATE_EXA_API_KEY`), avec ordre personnalisable via
+    `OBSIGATE_WEB_PROVIDERS`.
+  - **Transverse** : réessais réseau avec backoff maison (`OBSIGATE_WEB_RETRY`) et cache SQLite
+  des résultats web avec TTL (`OBSIGATE_WEB_CACHE_TTL`, 900 s par défaut, `OBSIGATE_WEB_CACHE_PATH`).
+  - **Rendu dynamique** : `fetch_url(render=True)` délègue les pages SPA à un worker Playwright
+    isolé (dépendance optionnelle, dégradation propre si non installée).
+  - **Crawl de site** : `crawl_site` (WRITE, confirmation) capture jusqu'à 20 pages d'un même
+    hôte et enregistre un condensé Markdown dans un vault.
+  - **Sources connectées** : Gitea (`OBSIGATE_GITEA_URL`/`OBSIGATE_GITEA_TOKEN`) et GitHub
+    (`OBSIGATE_GITHUB_TOKEN`) — `git_list_repos`, `git_search_issues`, `git_get_file` (READ,
+    rate-limités, audités). Les drives cloud (Google Drive / OneDrive) restent orientés serveur
+    MCP externe (#79), conformément à la feuille de route.
+  - **Production de documents** : `create_xlsx` (openpyxl), `create_docx` (python-docx),
+    `create_csv`, `create_pdf` (reportlab) — outils WRITE avec confirmation et sauvegarde
+    dans le vault (backup avant écrasement).
+  - Chaque outil : libellé `labels.py` + clés i18n `ai.step.*` FR/EN + tests unitaires mockés
+    (httpx). Dépendances ajoutées : `openpyxl`, `python-docx`, `reportlab`.
+    Fichiers : `backend/tools/{webcache,webrender,connected,crawler,documents,web,schemas,labels}.py`,
+    `backend/services/mutations.py`, `tests/test_{web_cache,web_search_providers,webrender,connected_tools,document_tools,crawler}.py`.
+
+---
+
 ## [2.9.1] — 2026-09-17
 
 ### Corrigé

README.fr.md

@@ -4,7 +4,7 @@
 
 **Porte d'entrée web ultra-léger pour vos vaults Obsidian** — Accédez, naviguez et recherchez dans toutes vos notes Obsidian depuis n'importe quel appareil via une interface web moderne et responsive.
 
-[![Version](https://img.shields.io/badge/Version-2.9.1-blue.svg)]()
+[![Version](https://img.shields.io/badge/Version-2.11.2-blue.svg)]()
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Docker](https://img.shields.io/badge/Docker-Ready-blue.svg)](https://www.docker.com/)
 [![Python](https://img.shields.io/badge/Python-3.11+-green.svg)](https://www.python.org/)
@@ -282,6 +282,16 @@ Un compte **admin** connecté voit une icône 🛡️ dans le header : liste, cr
 | `OBSIGATE_WEBHOOK_ALLOW_PRIVATE` | Autoriser les webhooks vers des adresses privées/boucle | `false` |
 | `OBSIGATE_PDF_MAX_SIZE_MB` | Taille max des PDF extraits (text indexation) | `50` |
 | `OBSIGATE_PDF_EXTRACT_TIMEOUT` | Timeout extraction PDF (secondes) | `30` |
+| `OBSIGATE_TAVILY_API_KEY` / `OBSIGATE_BRAVE_API_KEY` / `OBSIGATE_SERPAPI_API_KEY` / `OBSIGATE_EXA_API_KEY` | Fournisseurs de recherche web à clé (essayés avant SearXNG) | — |
+| `OBSIGATE_WEB_PROVIDERS` | Ordre des fournisseurs de recherche (ex. `brave,searxng`) | — |
+| `OBSIGATE_WEB_RETRY` | Réessais réseau des outils web (backoff maison) | `1` |
+| `OBSIGATE_WEB_CACHE_TTL` | Durée du cache SQLite des résultats web (secondes, `0` = off) | `900` |
+| `OBSIGATE_GITEA_URL` / `OBSIGATE_GITEA_TOKEN` | Source connectée Gitea (outil `git_list_repos`…) | — |
+| `OBSIGATE_GITHUB_TOKEN` | Jeton GitHub (outil `git_list_repos`…) | — |
+
+> Ces clés peuvent aussi être saisies **depuis l'interface** (menu → Configurations →
+> « Sources connectées & recherche ») : la valeur saisie est stockée dans `data/api_keys.json`
+> et prime sur la variable d'environnement.
 
 ### Volume pour la persistance
 
@@ -916,8 +926,8 @@ Ce projet est sous licence **MIT** — voir le fichier [LICENSE](LICENSE) pour l
 
 ## 📝 Changelog
 
-Consultez le [CHANGELOG.md](./CHANGELOG.md) pour l'historique complet de toutes les versions (v1.0.0 → v2.9.1).
+Consultez le [CHANGELOG.md](./CHANGELOG.md) pour l'historique complet de toutes les versions (v1.0.0 → v2.11.2).
 
 ---
 
-*Projet : ObsiGate | Version : 2.9.1 | Dernière mise à jour : Juin 2026*
+*Projet : ObsiGate | Version : 2.11.2 | Dernière mise à jour : Juin 2026*

README.md

@@ -2,7 +2,7 @@
 
 **Ultra-light web gateway for your Obsidian vaults** — Access, browse, and search all your Obsidian notes from any device via a modern, responsive web interface.
 
-[![Version](https://img.shields.io/badge/Version-2.9.1-blue.svg)]()
+[![Version](https://img.shields.io/badge/Version-2.11.2-blue.svg)]()
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Docker](https://img.shields.io/badge/Docker-Ready-blue.svg)](https://www.docker.com/)
 [![Python](https://img.shields.io/badge/Python-3.11+-green.svg)](https://www.python.org/)
@@ -320,6 +320,16 @@ When an **admin** account is logged in, a 🛡️ icon appears in the header. Cl
 | `OBSIGATE_WEBHOOK_ALLOW_PRIVATE` | Allow webhooks to private/loopback addresses | `false` |
 | `OBSIGATE_PDF_MAX_SIZE_MB` | Max PDF size for text extraction | `50` |
 | `OBSIGATE_PDF_EXTRACT_TIMEOUT` | PDF extraction timeout (seconds) | `30` |
+| `OBSIGATE_TAVILY_API_KEY` / `OBSIGATE_BRAVE_API_KEY` / `OBSIGATE_SERPAPI_API_KEY` / `OBSIGATE_EXA_API_KEY` | Keyed web-search providers (tried before SearXNG) | — |
+| `OBSIGATE_WEB_PROVIDERS` | Search provider order (e.g. `brave,searxng`) | — |
+| `OBSIGATE_WEB_RETRY` | Web tools network retries (house-made backoff) | `1` |
+| `OBSIGATE_WEB_CACHE_TTL` | SQLite cache TTL for web results (seconds, `0` = off) | `900` |
+| `OBSIGATE_GITEA_URL` / `OBSIGATE_GITEA_TOKEN` | Gitea connected source (`git_list_repos`…) | — |
+| `OBSIGATE_GITHUB_TOKEN` | GitHub token (`git_list_repos`…) | — |
+
+> These keys can also be entered **from the UI** (menu → Configurations →
+> "Connected sources & search"): the stored value goes to `data/api_keys.json`
+> and takes precedence over the environment variable.
 
 >All these variables are documented in `.env.example`.
 
@@ -1085,8 +1095,8 @@ This project is licensed under the **MIT License** - see the [LICENSE](LICENSE)
 
 ## 📝 Changelog
 
-See [CHANGELOG.md](./CHANGELOG.md) for the complete version history (v1.0.0 → v2.9.1).
+See [CHANGELOG.md](./CHANGELOG.md) for the complete version history (v1.0.0 → v2.11.2).
 
 ---
 
-*Project: ObsiGate | Version: 2.9.1 | Last updated: May 2026*
+*Project: ObsiGate | Version: 2.11.2 | Last updated: May 2026*

VERSION

@@ -1 +1 @@
-2.9.1
+2.11.2

backend/main.py

@@ -3679,6 +3679,68 @@ async def api_delete_ai_key(provider_env: str, current_user=Depends(require_admi
     return {"status": "deleted", "key": key_name}
 
 
+# ---------------------------------------------------------------------------
+# Tool & connected-source keys (#103) — same store as the AI provider keys
+# ---------------------------------------------------------------------------
+
+from backend.tools.secrets import (
+    TOOL_KEY_NAMES as _TOOL_KEY_NAMES,
+)
+from backend.tools.secrets import (
+    delete_tool_key as _delete_tool_key,
+)
+from backend.tools.secrets import (
+    get_tool_key as _get_tool_key,
+)
+from backend.tools.secrets import (
+    mask_value as _mask_tool_value,
+)
+from backend.tools.secrets import (
+    set_tool_key as _set_tool_key,
+)
+
+
+@app.get("/api/config/tool-keys", response_model=AIKeysResponse)
+async def api_get_tool_keys(current_user=Depends(require_admin)):
+    """Return tool/connected-source configuration (tokens masked, URLs clear)."""
+    masked = {}
+    for name in _TOOL_KEY_NAMES:
+        masked[name] = _mask_tool_value(name, _get_tool_key(name))
+    return masked
+
+
+@app.post("/api/config/tool-keys", response_model=StatusResponse)
+async def api_set_tool_keys(body: dict = Body(...), current_user=Depends(require_admin)):
+    """Save tool/connected-source keys.
+
+    Only whitelisted names (``backend.tools.secrets.TOOL_KEY_NAMES``) are
+    accepted: Tavily/Brave/SerpAPI/Exa API keys, Gitea URL + token, GitHub
+    token. Empty values delete the stored entry.
+    """
+    updated = []
+    for name, value in body.items():
+        if name not in _TOOL_KEY_NAMES:
+            raise HTTPException(status_code=400, detail=f"Clé inconnue: {name}")
+        if value is not None and not isinstance(value, str):
+            raise HTTPException(status_code=400, detail=f"Type invalide pour {name}")
+        _set_tool_key(name, value or "")
+        updated.append(name)
+    logger.info(f"Tool keys updated: {updated}")
+    return {"status": "ok"}
+
+
+@app.delete("/api/config/tool-keys/{name}", response_model=AIKeyDeleteResponse)
+async def api_delete_tool_key(name: str, current_user=Depends(require_admin)):
+    """Delete a stored tool key (the environment fallback still applies)."""
+    key_name = name.upper()
+    try:
+        existed = _delete_tool_key(key_name)
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    logger.info(f"Tool key deleted: {key_name} (existed={existed})")
+    return {"status": "deleted", "key": key_name}
+
+
 @app.post("/api/config/ai-keys/test", response_model=AITestResponse)
 async def api_test_ai_keys(current_user=Depends(require_admin)):
     """Test which AI providers are configured.

backend/requirements.txt

@@ -20,3 +20,6 @@ psutil>=5.9
 pywebpush>=2.3.0
 mcp==1.9.4
 sse-starlette==2.1.3
+openpyxl>=3.1
+python-docx>=1.1
+reportlab>=4.0

backend/services/mutations.py

@@ -44,7 +44,7 @@ def _ensure_writable(root: Path) -> None:
         raise ServiceError("Vault is read-only", code="read_only", status=403)
 
 
-def _validate_extension(file_path: Path, *, allow_images: bool = False) -> None:
+def _validate_extension(file_path: Path, *, allow_images: bool = False, allow_docs: bool = False) -> None:
     """Reject unsupported file extensions (400)."""
     from backend.indexer import SUPPORTED_EXTENSIONS
 
@@ -53,6 +53,9 @@ def _validate_extension(file_path: Path, *, allow_images: bool = False) -> None:
     if allow_images:
         from backend.attachment_indexer import IMAGE_EXTENSIONS
         allowed = allowed | IMAGE_EXTENSIONS
+    if allow_docs:
+        # Office documents produced by the AI tool layer (#92).
+        allowed = allowed | {".xlsx", ".docx"}
 
     if ext not in allowed and file_path.name.lower() not in ("dockerfile", "makefile"):
         raise ServiceError(
@@ -715,17 +718,20 @@ def save_raw_file(
     content: bytes,
     *,
     overwrite: bool = True,
+    allow_docs: bool = False,
 ) -> dict[str, Any]:
     """Save a binary or text file to a vault (e.g. from upload / drag-and-drop).
 
     Creates parent directories automatically and safely validates the path.
-    Supports supported text extensions, images and Excalidraw files.
+    Supports supported text extensions, images, Excalidraw files and — with
+    ``allow_docs`` — Office documents (.xlsx/.docx) produced by the AI tools.
 
     Args:
         vault_name: Name of the vault.
         path: Vault-relative path.
         content: Raw bytes to write.
         overwrite: When True, replace existing files (with backup).
+        allow_docs: Also accept .xlsx/.docx extensions (AI document tools).
 
     Returns:
         Dict with ``success``, ``vault``, ``path``, and ``size``.
@@ -733,7 +739,7 @@ def save_raw_file(
     root = get_vault_root(vault_name)
     _ensure_writable(root)
     file_path = resolve_safe_path(root, path)
-    _validate_extension(file_path, allow_images=True)
+    _validate_extension(file_path, allow_images=True, allow_docs=allow_docs)
 
     rel_path = _rel(root, file_path)
 

backend/tools/api.py

@@ -9,6 +9,9 @@ Note: ObsiGate uses implicit namespace packages (no tracked ``__init__.py``,
 which ``.gitignore`` excludes via ``_*.py``), hence this explicit facade.
 """
 
+from backend.tools import connected as _connected  # noqa: F401  (registers connected-source tools)
+from backend.tools import crawler as _crawler  # noqa: F401  (registers the site crawler)
+from backend.tools import documents as _documents  # noqa: F401  (registers document tools)
 from backend.tools import service as _service  # noqa: F401  (registers tools)
 from backend.tools import web as _web  # noqa: F401  (registers web tools)
 from backend.tools.context import (

backend/tools/connected.py

@@ -0,0 +1,241 @@
+"""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). Both the URL and the tokens can also be set
+  from the configuration page (stored in ``data/api_keys.json``, #103) —
+  the stored value takes precedence over the environment.
+* ``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
+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
+from backend.tools.secrets import get_tool_key
+
+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 = get_tool_key("OBSIGATE_GITEA_URL").rstrip("/")
+        if not base:
+            raise ToolError(
+                "Source Gitea non configurée (OBSIGATE_GITEA_URL absente).",
+                code="provider_not_configured",
+            )
+        token = get_tool_key("OBSIGATE_GITEA_TOKEN")
+        return base, f"token {token}" if token else ""
+    if provider == "github":
+        token = get_tool_key("OBSIGATE_GITHUB_TOKEN")
+        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,
+    }

backend/tools/crawler.py

@@ -0,0 +1,197 @@
+"""Multi-page site crawl — ``crawl_site`` (phase 2 #92, WRITE + confirmation).
+
+The assistant can digest a small public site (documentation, docs portal) and
+store a Markdown summary inside a vault: one section per page, title, URL and
+readable text. The crawl is bounded and same-host only:
+
+* max 20 pages (``max_pages``), same hostname, breadth-first from the entry URL;
+* SSRF guard on every URL (scheme + private-address rejection), size caps;
+* no third-party crawler dependency (scrapy deliberately avoided — a bounded
+  httpx BFS keeps the surface small and the runtime predictable; the task is
+  executed as a single background-style tool run instead of a web request
+  pipeline).
+
+Risk is WRITE: the digest is written into a vault, so the two-step
+confirmation applies (Apply card in the UI, propose/apply over MCP).
+"""
+
+from __future__ import annotations
+
+import logging
+import re
+import time
+from typing import Any
+from urllib.parse import urljoin, urlparse
+
+import httpx
+
+from backend.tools.context import ToolContext, ToolError, ToolRisk
+from backend.tools.registry import tool
+from backend.tools.schemas import CrawlSiteInput
+from backend.tools.web import (
+    USER_AGENT,
+    _assert_public_http_url,
+    _html_to_text,
+    _response_text,
+)
+
+logger = logging.getLogger("obsigate.tools.crawler")
+
+MAX_PAGE_BYTES = 800_000
+MAX_TOTAL_BYTES = 6_000_000
+MAX_TEXT_PER_PAGE = 12_000
+PAGE_TIMEOUT = 10.0
+_LINK_RE = re.compile(r'<a[^>]*href="([^"#]+)"', re.IGNORECASE)
+_TITLE_RE = re.compile(r"<title[^>]*>(.*?)</title>", re.IGNORECASE | re.DOTALL)
+
+
+def _same_host(url: str, host: str) -> bool:
+    return (urlparse(url).hostname or "") == host
+
+
+def _extract_links(raw: str, base_url: str) -> list[str]:
+    import html as html_lib
+
+    links: list[str] = []
+    for match in _LINK_RE.finditer(raw):
+        href = html_lib.unescape(match.group(1)).strip()
+        if not href or href.lower().startswith(("javascript:", "mailto:", "tel:")):
+            continue
+        absolute = urljoin(base_url, href)
+        if absolute.lower().endswith((".png", ".jpg", ".jpeg", ".gif", ".svg", ".webp", ".pdf", ".zip")):
+            continue
+        links.append(absolute.split("#", 1)[0])
+    return links
+
+
+def _fetch_page(url: str) -> tuple[str, str]:
+    """Fetch one page (SSRF-guarded, manual redirects) → (title, text)."""
+    current = _assert_public_http_url(url)
+    resp = None
+    for _hop in range(5):
+        resp = httpx.get(
+            current,
+            headers={"User-Agent": USER_AGENT, "Accept": "text/html,*/*"},
+            timeout=PAGE_TIMEOUT,
+            follow_redirects=False,
+        )
+        if resp.status_code in (301, 302, 303, 307, 308):
+            location = resp.headers.get("location") or ""
+            if not location:
+                break
+            current = _assert_public_http_url(str(httpx.URL(current).join(location)))
+            continue
+        break
+    assert resp is not None
+    resp.raise_for_status()
+    ctype = (resp.headers.get("content-type") or "").lower()
+    if "html" not in ctype and "text" not in ctype:
+        raise ToolError(
+            f"Type de contenu non pris en charge: {ctype.split(';')[0] or 'inconnu'}",
+            code="unsupported_content_type",
+        )
+    raw = (resp.content[:MAX_PAGE_BYTES]).decode(resp.encoding or "utf-8", errors="replace")
+    title_match = _TITLE_RE.search(raw)
+    import html as html_lib
+
+    title = html_lib.unescape(title_match.group(1)).strip()[:300] if title_match else ""
+    return title, _html_to_text(raw)[:MAX_TEXT_PER_PAGE]
+
+
+@tool(
+    name="crawl_site",
+    description=(
+        "Crawl a small public site (same-host only, max 20 pages) starting at "
+        "a URL and save a Markdown digest (title, url, readable text per page) "
+        "into a vault. Use to capture an online documentation for offline use."
+    ),
+    input_model=CrawlSiteInput,
+    risk=ToolRisk.WRITE,
+    requires_vault=True,
+)
+def crawl_site(ctx: ToolContext, params: CrawlSiteInput) -> dict[str, Any]:
+    """Bounded BFS crawl; writes the digest file and returns a summary."""
+    from backend.services.errors import ServiceError
+    from backend.services.mutations import save_raw_file
+
+    start = _assert_public_http_url(params.url.strip())
+    host = urlparse(start).hostname or ""
+    if not host:
+        raise ToolError("URL sans hôte", code="invalid_url")
+
+    queue: list[str] = [start]
+    seen: set[str] = {start}
+    pages: list[dict[str, Any]] = []
+    total_bytes = 0
+    failures: list[str] = []
+
+    while queue and len(pages) < params.max_pages and total_bytes < MAX_TOTAL_BYTES:
+        url = queue.pop(0)
+        try:
+            title, text = _fetch_page(url)
+        except ToolError as e:
+            failures.append(url)
+            logger.warning("crawl_site page failed %s: %s", url, e.code)
+            continue
+        except httpx.HTTPError as e:
+            failures.append(url)
+            logger.warning("crawl_site page failed %s: %s", url, e)
+            continue
+        pages.append({"url": url, "title": title, "text": text})
+        total_bytes += len(text)
+        if len(pages) >= params.max_pages:
+            break
+        try:
+            raw_resp = httpx.get(
+                url, headers={"User-Agent": USER_AGENT}, timeout=PAGE_TIMEOUT,
+                follow_redirects=False,
+            )
+            raw = _response_text(raw_resp)
+        except (httpx.HTTPError, ValueError):
+            continue
+        for link in _extract_links(raw, url):
+            if len(pages) + len(queue) >= params.max_pages:
+                break
+            if link in seen or not _same_host(link, host):
+                continue
+            try:
+                _assert_public_http_url(link)
+            except ToolError:
+                continue
+            seen.add(link)
+            queue.append(link)
+
+    if not pages:
+        raise ToolError(
+            "Aucune page n'a pu être récupérée pour ce site.",
+            code="crawl_failed",
+        )
+
+    lines = [
+        f"# Crawl de {host}",
+        "",
+        f"> {len(pages)} page(s) capturée(s) depuis {start} — {time.strftime('%Y-%m-%d %H:%M')}",
+        "",
+    ]
+    for page in pages:
+        lines.append(f"## {page['title'] or page['url']}")
+        lines.append("")
+        lines.append(f"Source : {page['url']}")
+        lines.append("")
+        lines.append(page["text"])
+        lines.append("")
+    digest = "\n".join(lines).encode("utf-8")
+    try:
+        saved = save_raw_file(
+            params.vault, params.path, digest, overwrite=True, allow_docs=False
+        )
+    except ServiceError as e:
+        raise ToolError(e.message, code=e.code, details=e.details) from e
+    return {
+        "url": start,
+        "vault": params.vault,
+        "path": saved.get("path", params.path),
+        "pages": len(pages),
+        "failed": failures[:10],
+        "size": saved.get("size", len(digest)),
+    }

backend/tools/documents.py

@@ -0,0 +1,229 @@
+"""Document-production tools (phase 2 #92) — WRITE, confirmation required.
+
+The assistant can generate real files inside a vault:
+
+* ``create_xlsx`` — spreadsheet (openpyxl);
+* ``create_docx`` — Word document (python-docx);
+* ``create_csv``  — CSV (stdlib);
+* ``create_pdf``  — PDF (reportlab, from markdown-ish content).
+
+Every tool is ``WRITE`` (two-step confirm in the UI / propose-apply over MCP),
+vault-scoped through ``requires_vault`` and saved via the shared mutation
+service (path safety, read-only check, backup on overwrite).
+"""
+
+from __future__ import annotations
+
+import csv as csv_lib
+import io
+import logging
+import re
+from typing import Any
+from xml.sax import saxutils
+
+from backend.services.errors import ServiceError
+from backend.services.mutations import save_raw_file
+from backend.tools.context import ToolContext, ToolError, ToolRisk
+from backend.tools.registry import tool
+from backend.tools.schemas import CsvInput, DocxInput, PdfInput, SpreadsheetInput
+
+logger = logging.getLogger("obsigate.tools.documents")
+
+MAX_PDF_CHARS = 200_000
+MAX_ROWS = 5_000
+
+
+def _save(vault: str, path: str, content: bytes, overwrite: bool) -> dict[str, Any]:
+    """Shared save helper (maps ServiceError to ToolError)."""
+    try:
+        return save_raw_file(vault, path, content, overwrite=overwrite, allow_docs=True)
+    except ServiceError as e:
+        raise ToolError(e.message, code=e.code, details=e.details) from e
+
+
+def _check_rows(rows: list[list[Any]]) -> None:
+    if not rows:
+        raise ToolError("Aucune ligne fournie", code="invalid_arguments")
+    if len(rows) > MAX_ROWS:
+        raise ToolError(
+            f"Trop de lignes ({len(rows)} > {MAX_ROWS})", code="invalid_arguments"
+        )
+
+
+def _check_extension(path: str, expected: str) -> str:
+    """Enforce the document extension; return the normalized path."""
+    path = (path or "").strip()
+    if not path.lower().endswith(expected):
+        raise ToolError(
+            f"Extension attendue : {expected}", code="invalid_arguments"
+        )
+    return path
+
+
+@tool(
+    name="create_xlsx",
+    description=(
+        "Create an .xlsx spreadsheet in a vault from rows of cell values "
+        "(first row = header). Use for tables, budgets, checklists the user "
+        "asked to turn into an Excel file."
+    ),
+    input_model=SpreadsheetInput,
+    risk=ToolRisk.WRITE,
+    requires_vault=True,
+)
+def create_xlsx(ctx: ToolContext, params: SpreadsheetInput) -> dict[str, Any]:
+    """Build the workbook with openpyxl and save it into the vault."""
+    from openpyxl import Workbook
+
+    _check_rows(params.rows)
+    path = _check_extension(params.path, ".xlsx")
+    wb = Workbook()
+    ws = wb.active
+    ws.title = params.sheet_name[:31] or "Feuille1"
+    for row in params.rows:
+        ws.append(list(row))
+    buffer = io.BytesIO()
+    wb.save(buffer)
+    return _save(params.vault, path, buffer.getvalue(), params.overwrite)
+
+
+@tool(
+    name="create_docx",
+    description=(
+        "Create a .docx Word document in a vault from an optional title and "
+        "ordered paragraphs. Use for letters, reports, structured drafts."
+    ),
+    input_model=DocxInput,
+    risk=ToolRisk.WRITE,
+    requires_vault=True,
+)
+def create_docx(ctx: ToolContext, params: DocxInput) -> dict[str, Any]:
+    """Build the document with python-docx and save it into the vault."""
+    from docx import Document
+
+    if not params.paragraphs:
+        raise ToolError("Aucun paragraphe fourni", code="invalid_arguments")
+    path = _check_extension(params.path, ".docx")
+    doc = Document()
+    if params.title.strip():
+        doc.add_heading(params.title.strip(), level=1)
+    for paragraph in params.paragraphs:
+        doc.add_paragraph(paragraph)
+    buffer = io.BytesIO()
+    doc.save(buffer)
+    return _save(params.vault, path, buffer.getvalue(), params.overwrite)
+
+
+@tool(
+    name="create_csv",
+    description=(
+        "Create a .csv file in a vault from rows of cell values (first row = "
+        "header). Use for flat data exports, simple tables."
+    ),
+    input_model=CsvInput,
+    risk=ToolRisk.WRITE,
+    requires_vault=True,
+)
+def create_csv(ctx: ToolContext, params: CsvInput) -> dict[str, Any]:
+    """Serialize the rows and save the CSV into the vault."""
+    _check_rows(params.rows)
+    path = _check_extension(params.path, ".csv")
+    delimiter = params.delimiter if params.delimiter in (",", ";", "\t") else ","
+    buffer = io.StringIO()
+    writer = csv_lib.writer(buffer, delimiter=delimiter, lineterminator="\n")
+    writer.writerows(params.rows)
+    return _save(params.vault, path, buffer.getvalue().encode("utf-8"), params.overwrite)
+
+
+_HEADING_RE = re.compile(r"^(#{1,6})\s+(.*)$")
+
+
+def _markdown_to_flowables(content: str) -> list[tuple[str, str]]:
+    """Split markdown-ish content into (style, text) blocks for reportlab."""
+    blocks: list[tuple[str, str]] = []
+    for raw_line in content.splitlines():
+        line = raw_line.rstrip()
+        if not line.strip():
+            continue
+        heading = _HEADING_RE.match(line)
+        if heading:
+            blocks.append((f"H{min(3, len(heading.group(1)))}", heading.group(2).strip()))
+        else:
+            blocks.append(("P", line.strip()))
+    return blocks
+
+
+def _render_markdown_pdf(content: str, title: str) -> bytes | None:
+    """Render markdown → HTML → PDF through the document-page pipeline.
+
+    Uses the same stack as the « Download PDF » button of the document viewer
+    (mistune with the table plugin + WeasyPrint print CSS), so tables, code
+    blocks and lists are laid out correctly. Returns ``None`` when WeasyPrint
+    is not importable (missing GTK on some hosts) so the caller can fall back
+    to the simplified reportlab renderer.
+    """
+    try:
+        import mistune
+
+        from backend.pdf_export import build_pdf_html, generate_pdf
+
+        renderer = mistune.create_markdown(
+            escape=False,
+            plugins=["table", "strikethrough", "footnotes", "task_lists"],
+        )
+        html = renderer(content)
+        return generate_pdf(build_pdf_html(html, title), title)
+    except Exception as e:
+        # WeasyPrint loads GTK lazily: a missing native library can surface at
+        # import OR render time. Fall back to the simple renderer either way.
+        logger.warning("WeasyPrint pipeline unavailable for create_pdf: %s", e)
+        return None
+
+
+def _render_reportlab_pdf(content: str, title: str) -> bytes:
+    """Fallback renderer (no WeasyPrint): headings + paragraphs, no tables."""
+    from reportlab.lib.pagesizes import A4
+    from reportlab.lib.styles import getSampleStyleSheet
+    from reportlab.platypus import Paragraph, SimpleDocTemplate, Spacer
+
+    styles = getSampleStyleSheet()
+    style_map = {
+        "P": styles["BodyText"],
+        "H1": styles["Heading1"],
+        "H2": styles["Heading2"],
+        "H3": styles["Heading3"],
+    }
+    buffer = io.BytesIO()
+    doc = SimpleDocTemplate(buffer, pagesize=A4, title=title[:200])
+    story: list[Any] = [Paragraph(saxutils.escape(title[:300]), styles["Title"])]
+    for style, line in _markdown_to_flowables(content):
+        story.append(Spacer(1, 4))
+        story.append(Paragraph(saxutils.escape(line), style_map[style]))
+    doc.build(story)
+    return buffer.getvalue()
+
+
+@tool(
+    name="create_pdf",
+    description=(
+        "Create a .pdf document in a vault from markdown content (headings, "
+        "paragraphs, tables, code blocks, lists). Use for printable "
+        "deliverables; tables are laid out like the document-page PDF export."
+    ),
+    input_model=PdfInput,
+    risk=ToolRisk.WRITE,
+    requires_vault=True,
+)
+def create_pdf(ctx: ToolContext, params: PdfInput) -> dict[str, Any]:
+    """Render the content and save the PDF into the vault.
+
+    Primary path: mistune (tables) + WeasyPrint — identical to the viewer's
+    « Download PDF » export. Fallback (WeasyPrint unavailable): simplified
+    reportlab layout without tables.
+    """
+    path = _check_extension(params.path, ".pdf")
+    content = params.content[:MAX_PDF_CHARS]
+    pdf_bytes = _render_markdown_pdf(content, params.title[:300])
+    if pdf_bytes is None:
+        pdf_bytes = _render_reportlab_pdf(content, params.title[:300])
+    return _save(params.vault, path, pdf_bytes, params.overwrite)

backend/tools/labels.py

@@ -47,6 +47,14 @@ _STEP_LABELS: dict[str, tuple[str, str | None]] = {
     "restore_backup": ("backup_restore", "path"),
     "web_search": ("web_search", "query"),
     "fetch_url": ("fetch_url", "url"),
+    "crawl_site": ("crawl", "url"),
+    "git_list_repos": ("git_repos", "provider"),
+    "git_search_issues": ("git_issues", "query"),
+    "git_get_file": ("git_file", "path"),
+    "create_xlsx": ("xlsx_create", "path"),
+    "create_docx": ("docx_create", "path"),
+    "create_csv": ("csv_create", "path"),
+    "create_pdf": ("pdf_create", "path"),
 }
 
 GENERIC_KEY = "generic"

backend/tools/schemas.py

@@ -251,6 +251,90 @@ class FetchUrlInput(BaseModel):
     """Fetch one public web page and return its readable text."""
 
     url: str = Field(..., description="Absolute http(s) URL of a public page")
+    render: bool = Field(
+        False,
+        description="Render JavaScript with the optional Playwright worker (dynamic SPA pages)",
+    )
+
+
+class CrawlSiteInput(BaseModel):
+    """Crawl a small public site (same-host only) and save a digest into a vault."""
+
+    url: str = Field(..., description="Absolute http(s) URL where the crawl starts")
+    vault: str = Field(..., description="Vault name")
+    path: str = Field(..., description="Vault-relative path of the digest file to write (.md)")
+    max_pages: int = Field(5, ge=1, le=20, description="Maximum number of pages to crawl")
+
+
+class GitProviderInput(BaseModel):
+    """Base fields for connected-source tools (Gitea / GitHub)."""
+
+    provider: str = Field(..., description="'gitea' (OBSIGATE_GITEA_URL) or 'github'")
+    repo: str = Field("", description="Optional 'owner/name' repository filter")
+    limit: int = Field(20, ge=1, le=50, description="Maximum number of entries")
+
+
+class GitSearchIssuesInput(BaseModel):
+    """Search issues/pull requests on a connected Gitea or GitHub instance."""
+
+    provider: str = Field(..., description="'gitea' or 'github'")
+    query: str = Field(..., min_length=1, description="Search keywords")
+    repo: str = Field("", description="Optional 'owner/name' scope (empty = instance-wide)")
+    state: str = Field("open", description="'open' or 'closed'")
+    limit: int = Field(10, ge=1, le=20, description="Maximum number of issues")
+
+
+class GitGetFileInput(BaseModel):
+    """Read a file from a connected Gitea or GitHub repository."""
+
+    provider: str = Field(..., description="'gitea' or 'github'")
+    repo: str = Field(..., description="'owner/name' repository")
+    path: str = Field(..., description="Repository-relative file path")
+    ref: str = Field("", description="Optional branch/tag/commit (empty = default branch)")
+
+
+class SpreadsheetInput(BaseModel):
+    """Create an .xlsx spreadsheet in a vault from rows of cells."""
+
+    vault: str = Field(..., description="Vault name")
+    path: str = Field(..., description="Vault-relative path of the file to write (.xlsx)")
+    rows: list[list[str | int | float | bool | None]] = Field(
+        ..., description="Rows of cell values (first row = header)"
+    )
+    sheet_name: str = Field("Feuille1", description="Worksheet name")
+    overwrite: bool = Field(True, description="Replace an existing file (with backup)")
+
+
+class DocxInput(BaseModel):
+    """Create a .docx Word document in a vault from paragraphs."""
+
+    vault: str = Field(..., description="Vault name")
+    path: str = Field(..., description="Vault-relative path of the file to write (.docx)")
+    title: str = Field("", description="Optional document title (heading 1)")
+    paragraphs: list[str] = Field(..., description="Paragraph texts, in order")
+    overwrite: bool = Field(True, description="Replace an existing file (with backup)")
+
+
+class CsvInput(BaseModel):
+    """Create a .csv file in a vault from rows of cells."""
+
+    vault: str = Field(..., description="Vault name")
+    path: str = Field(..., description="Vault-relative path of the file to write (.csv)")
+    rows: list[list[str | int | float | bool | None]] = Field(
+        ..., description="Rows of cell values (first row = header)"
+    )
+    delimiter: str = Field(",", description="Field separator (',' ';' '\\t')")
+    overwrite: bool = Field(True, description="Replace an existing file (with backup)")
+
+
+class PdfInput(BaseModel):
+    """Create a .pdf document in a vault from markdown-ish content."""
+
+    vault: str = Field(..., description="Vault name")
+    path: str = Field(..., description="Vault-relative path of the file to write (.pdf)")
+    title: str = Field("Document", description="Document title")
+    content: str = Field(..., description="Content (headings with #/##, then paragraphs)")
+    overwrite: bool = Field(True, description="Replace an existing file (with backup)")
 
 
 class ToolResult(BaseModel):

backend/tools/secrets.py

@@ -0,0 +1,109 @@
+"""Tool-layer secrets — user-configured tokens & API keys (#103).
+
+The connected-source (Gitea / GitHub) and keyed web-search (Tavily, Brave,
+SerpAPI, Exa) tools read their credentials through this module instead of
+``os.environ`` directly. The value comes from the store the user edits in the
+configuration page (``data/api_keys.json`` — the same file the AI provider
+keys use) first, then falls back to the environment (Infisical-injected in
+production). Nothing is ever hard-coded and no tool result carries a secret
+(the registry redacts payloads).
+
+Allowed names are whitelisted: only the variables below can be stored or
+deleted from the configuration page.
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import os
+from pathlib import Path
+
+logger = logging.getLogger("obsigate.tools.secrets")
+
+# Whitelisted configuration names (config page « Sources connectées & recherche »).
+TOOL_KEY_NAMES: tuple[str, ...] = (
+    "OBSIGATE_TAVILY_API_KEY",
+    "OBSIGATE_BRAVE_API_KEY",
+    "OBSIGATE_SERPAPI_API_KEY",
+    "OBSIGATE_EXA_API_KEY",
+    "OBSIGATE_GITEA_URL",
+    "OBSIGATE_GITEA_TOKEN",
+    "OBSIGATE_GITHUB_TOKEN",
+)
+
+_SECRET_MARKERS = ("API_KEY", "TOKEN")
+
+
+def _keys_file() -> Path:
+    base = os.environ.get("OBSIGATE_DATA_DIR", "data")
+    return Path(base) / "api_keys.json"
+
+
+def _read_keys() -> dict:
+    path = _keys_file()
+    if not path.exists():
+        return {}
+    try:
+        data = json.loads(path.read_text(encoding="utf-8"))
+    except (OSError, ValueError) as e:
+        logger.warning("tool key store unreadable (%s): %s", path, e)
+        return {}
+    return data if isinstance(data, dict) else {}
+
+
+def _write_keys(data: dict) -> None:
+    path = _keys_file()
+    path.parent.mkdir(parents=True, exist_ok=True)
+    tmp = path.with_suffix(".tmp")
+    tmp.write_text(json.dumps(data, indent=2), encoding="utf-8")
+    tmp.replace(path)
+
+
+def is_secret_name(name: str) -> bool:
+    """True for API keys / tokens (masked in API responses); URLs are clear."""
+    return any(marker in name for marker in _SECRET_MARKERS)
+
+
+def mask_value(name: str, value: str) -> str:
+    """Mask a secret for display; non-secret values (URLs) are returned as-is."""
+    if not value:
+        return ""
+    if not is_secret_name(name):
+        return value
+    return value[:4] + "..." + value[-4:] if len(value) > 8 else "***"
+
+
+def get_tool_key(name: str) -> str:
+    """Stored (configuration page) value first, then environment fallback."""
+    if name not in TOOL_KEY_NAMES:
+        return os.environ.get(name, "").strip()
+    stored = _read_keys().get(name)
+    if isinstance(stored, str) and stored.strip():
+        return stored.strip()
+    return os.environ.get(name, "").strip()
+
+
+def set_tool_key(name: str, value: str) -> None:
+    """Persist one whitelisted key into the store (admin configuration page)."""
+    if name not in TOOL_KEY_NAMES:
+        raise ValueError(f"Clé non prise en charge: {name}")
+    value = (value or "").strip()
+    keys = _read_keys()
+    if value:
+        keys[name] = value
+    else:
+        keys.pop(name, None)
+    _write_keys(keys)
+
+
+def delete_tool_key(name: str) -> bool:
+    """Remove one key from the store; return True when it existed."""
+    if name not in TOOL_KEY_NAMES:
+        raise ValueError(f"Clé non prise en charge: {name}")
+    keys = _read_keys()
+    if name in keys:
+        del keys[name]
+        _write_keys(keys)
+        return True
+    return False

backend/tools/web.py

@@ -8,6 +8,16 @@ Phase 1 of the documented web-toolset roadmap:
   answering « je n'ai pas accès à internet ».
 * ``fetch_url``   — retrieve a public web page and return readable text.
 
+Phase 2 (#92) additions:
+
+* keyed providers — Tavily, Brave Search, SerpAPI and Exa are used first when
+  their API key is configured (env, injected by Infisical in production);
+* SQLite cache — search/fetch results are cached with a TTL
+  (:mod:`backend.tools.webcache`);
+* retry with backoff — transient network errors get one extra attempt;
+* dynamic rendering — ``fetch_url(render=True)`` uses an isolated Playwright
+  worker (optional dependency, graceful degradation).
+
 All are READ-risk tools (no confirmation), rate-limited through the shared
 registry, SSRF-guarded (scheme + private-address rejection), and size-capped.
 
@@ -16,6 +26,14 @@ Configuration (environment):
 * ``OBSIGATE_WEB_TIMEOUT``   — seconds, default 10
 * ``OBSIGATE_WEB_FALLBACK``  — ``0``/``false`` disables the keyless HTML
   fallbacks (SearXNG only), default enabled
+* ``OBSIGATE_TAVILY_API_KEY`` / ``OBSIGATE_BRAVE_API_KEY`` /
+  ``OBSIGATE_SERPAPI_API_KEY`` / ``OBSIGATE_EXA_API_KEY`` — optional keyed
+  providers, tried before SearXNG when set
+* ``OBSIGATE_WEB_PROVIDERS`` — optional comma-separated provider order
+  (e.g. ``brave,searxng``); keyed providers without a key are skipped
+* ``OBSIGATE_WEB_RETRY``     — extra attempts for transient network errors
+  (default 1)
+* ``OBSIGATE_WEB_CACHE_TTL`` — cache TTL seconds, ``0`` disables (default 900)
 """
 
 from __future__ import annotations
@@ -28,15 +46,18 @@ import logging
 import os
 import re
 import socket
+import time
 from collections.abc import Callable
 from typing import Any
 from urllib.parse import parse_qs, urlparse
 
 import httpx
 
+from backend.tools import webcache
 from backend.tools.context import ToolError, ToolRisk, ToolScope
 from backend.tools.registry import tool
 from backend.tools.schemas import FetchUrlInput, WebSearchInput
+from backend.tools.secrets import get_tool_key
 
 logger = logging.getLogger("obsigate.tools.web")
 
@@ -48,6 +69,7 @@ WEB_FALLBACK_ENABLED = os.environ.get("OBSIGATE_WEB_FALLBACK", "1").strip().lowe
     "no",
     "off",
 }
+WEB_RETRY_ATTEMPTS = int(os.environ.get("OBSIGATE_WEB_RETRY", "1"))
 USER_AGENT = "ObsiGateAssistant/1.0 (+self-hosted vault AI)"
 # Search engines reject non-browser agents on their public HTML endpoints.
 BROWSER_UA = (
@@ -163,6 +185,115 @@ def _result(
     }
 
 
+def _with_retry(call: Callable[[], Any]) -> Any:
+    """Run *call* with one extra attempt on transient network errors.
+
+    House-made backoff (the roadmap's « tenacity ou boucle maison »): DNS
+    blips and rate-limit hiccups are the common failure mode, and a single
+    retry keeps the fallback chain from being consumed too early.
+    """
+    for attempt in range(1 + max(0, WEB_RETRY_ATTEMPTS)):
+        try:
+            return call()
+        except httpx.TransportError:
+            if attempt >= max(0, WEB_RETRY_ATTEMPTS):
+                raise
+            time.sleep(0.2 * (attempt + 1))
+    raise RuntimeError("unreachable")  # pragma: no cover
+
+
+def _env_key(name: str) -> str:
+    """Read an API key: configuration-page store first, then environment."""
+    return get_tool_key(name)
+
+
+def _search_tavily(query: str, params: WebSearchInput) -> tuple[list[dict[str, Any]], list[str]]:
+    """Tavily Search API (agent-oriented results, key required)."""
+    resp = httpx.post(
+        "https://api.tavily.com/search",
+        json={
+            "api_key": _env_key("OBSIGATE_TAVILY_API_KEY"),
+            "query": query,
+            "max_results": params.max_results,
+            "search_depth": "basic",
+            "include_answer": False,
+        },
+        headers={"User-Agent": USER_AGENT},
+        timeout=WEB_TIMEOUT,
+    )
+    resp.raise_for_status()
+    data = resp.json()
+    return [
+        _result(item.get("title") or "", item.get("url") or "", item.get("content") or "")
+        for item in (data.get("results") or [])
+    ], []
+
+
+def _search_brave(query: str, params: WebSearchInput) -> tuple[list[dict[str, Any]], list[str]]:
+    """Brave Search API (key required)."""
+    resp = httpx.get(
+        "https://api.search.brave.com/res/v1/web/search",
+        params={"q": query, "count": params.max_results, "safesearch": "moderate"},
+        headers={
+            "X-Subscription-Id": _env_key("OBSIGATE_BRAVE_API_KEY"),
+            "Accept": "application/json",
+            "User-Agent": USER_AGENT,
+        },
+        timeout=WEB_TIMEOUT,
+    )
+    resp.raise_for_status()
+    data = resp.json()
+    return [
+        _result(item.get("title") or "", item.get("url") or "", item.get("description") or "")
+        for item in ((data.get("web") or {}).get("results") or [])
+    ], []
+
+
+def _search_serpapi(query: str, params: WebSearchInput) -> tuple[list[dict[str, Any]], list[str]]:
+    """SerpAPI (Google SERP, key required)."""
+    resp = httpx.get(
+        "https://serpapi.com/search",
+        params={"q": query, "api_key": _env_key("OBSIGATE_SERPAPI_API_KEY"),
+                "num": params.max_results},
+        headers={"User-Agent": USER_AGENT},
+        timeout=WEB_TIMEOUT,
+    )
+    resp.raise_for_status()
+    data = resp.json()
+    return [
+        _result(item.get("title") or "", item.get("link") or "", item.get("snippet") or "")
+        for item in (data.get("organic_results") or [])
+    ], []
+
+
+def _search_exa(query: str, params: WebSearchInput) -> tuple[list[dict[str, Any]], list[str]]:
+    """Exa neural search (key required)."""
+    resp = httpx.post(
+        "https://api.exa.ai/search",
+        json={"query": query, "numResults": params.max_results},
+        headers={
+            "x-api-key": _env_key("OBSIGATE_EXA_API_KEY"),
+            "User-Agent": USER_AGENT,
+        },
+        timeout=WEB_TIMEOUT,
+    )
+    resp.raise_for_status()
+    data = resp.json()
+    return [
+        _result(item.get("title") or "", item.get("url") or "", (item.get("text") or "")[:600])
+        for item in (data.get("results") or [])
+    ], []
+
+
+# Keyed providers: name -> (implementation, API key env var)
+_KEYED_PROVIDERS: dict[str, tuple[_Provider, str]] = {
+    "tavily": (_search_tavily, "OBSIGATE_TAVILY_API_KEY"),
+    "brave": (_search_brave, "OBSIGATE_BRAVE_API_KEY"),
+    "serpapi": (_search_serpapi, "OBSIGATE_SERPAPI_API_KEY"),
+    "exa": (_search_exa, "OBSIGATE_EXA_API_KEY"),
+}
+
+
 def _search_searxng(
     query: str, params: WebSearchInput
 ) -> tuple[list[dict[str, Any]], list[str]]:
@@ -288,8 +419,22 @@ _Provider = Callable[[str, WebSearchInput], "tuple[list[dict[str, Any]], list[st
 
 
 def _provider_chain() -> list[tuple[str, _Provider]]:
-    """Ordered providers: self-hosted meta-search first, then keyless fallbacks."""
-    chain: list[tuple[str, _Provider]] = [("searxng", _search_searxng)]
+    """Ordered providers: keyed APIs first, then self-hosted, then keyless.
+
+    ``OBSIGATE_WEB_PROVIDERS`` (comma-separated) overrides the default order;
+    unknown names are ignored and keyed providers without their key are skipped.
+    """
+    chain: list[tuple[str, _Provider]] = []
+    configured = [
+        name.strip().lower()
+        for name in os.environ.get("OBSIGATE_WEB_PROVIDERS", "").split(",")
+        if name.strip()
+    ]
+    for name in configured or list(_KEYED_PROVIDERS):
+        entry = _KEYED_PROVIDERS.get(name)
+        if entry and _env_key(entry[1]):
+            chain.append((name, entry[0]))
+    chain.append(("searxng", _search_searxng))
     if WEB_FALLBACK_ENABLED:
         chain.append(("duckduckgo", _search_duckduckgo))
         chain.append(("bing", _search_bing))
@@ -313,6 +458,17 @@ def web_search(ctx, params: WebSearchInput) -> dict[str, Any]:
     if not query:
         raise ToolError("Requête vide", code="invalid_arguments")
 
+    key = webcache.cache_key("search", {
+        "q": query,
+        "max_results": params.max_results,
+        "category": params.category,
+        "language": params.language,
+        "page": params.page,
+    })
+    cached = webcache.cache_get(key)
+    if cached is not None:
+        return {**cached, "cached": True}
+
     attempts: list[str] = []
     unresponsive: list[str] = []
     reachable = False
@@ -320,8 +476,12 @@ def web_search(ctx, params: WebSearchInput) -> dict[str, Any]:
 
     for name, provider in _provider_chain():
         attempts.append(name)
+
+        def _attempt(p: _Provider = provider) -> tuple[list[dict[str, Any]], list[str]]:
+            return p(query, params)
+
         try:
-            results, engines = provider(query, params)
+            results, engines = _with_retry(_attempt)
         except (httpx.HTTPError, ValueError, AttributeError) as e:
             logger.warning("web_search provider %s failed: %s", name, e)
             last_error = e
@@ -338,6 +498,7 @@ def web_search(ctx, params: WebSearchInput) -> dict[str, Any]:
             }
             if unresponsive:
                 payload["unresponsive_engines"] = unresponsive[:8]
+            webcache.cache_set(key, payload)
             return payload
 
     if not reachable:
@@ -378,6 +539,20 @@ def web_search(ctx, params: WebSearchInput) -> dict[str, Any]:
 def fetch_url(ctx, params: FetchUrlInput) -> dict[str, Any]:
     """Retrieve one page, guard against SSRF, and extract its text."""
     url = _assert_public_http_url(params.url.strip())
+    key = webcache.cache_key("fetch", {"url": url, "render": params.render})
+    cached = webcache.cache_get(key)
+    if cached is not None:
+        return {**cached, "cached": True}
+
+    if params.render:
+        # Dynamic pages (SPA/React): delegated to the isolated Playwright
+        # worker; the browser dependency stays optional (graceful error).
+        from backend.tools.webrender import render_page
+
+        payload = render_page(url)
+        webcache.cache_set(key, payload)
+        return payload
+
     try:
         # Follow redirects manually so every hop is re-checked against the
         # private-address SSRF guard (a public page can redirect to 127.0.0.1).
@@ -414,10 +589,12 @@ def fetch_url(ctx, params: FetchUrlInput) -> dict[str, Any]:
     title_match = re.search(r"<title[^>]*>(.*?)</title>", raw, re.IGNORECASE | re.DOTALL)
     title = html_lib.unescape(title_match.group(1)).strip()[:300] if title_match else ""
     text = _html_to_text(raw)[:MAX_TEXT_CHARS]
-    return {
+    payload = {
         "url": str(resp.url),
         "status": resp.status_code,
         "title": title,
         "text": text,
         "truncated": len(raw) > MAX_TEXT_CHARS,
     }
+    webcache.cache_set(key, payload)
+    return payload

backend/tools/webcache.py

@@ -0,0 +1,138 @@
+"""SQLite cache for web tool results (search results, fetched pages).
+
+Phase 2 of the web-toolset roadmap (« Transverse »): repeated web searches and
+page fetches (common in agent loops, where the model re-reads a source) must
+not hammer the providers. Results are cached in a dedicated SQLite table with
+a TTL; the cache is best-effort — any error silently disables it so a broken
+database file never takes the assistant down.
+
+Configuration (environment):
+* ``OBSIGATE_DATA_DIR``        — base data directory (default ``data``)
+* ``OBSIGATE_WEB_CACHE_PATH``  — explicit cache file override
+* ``OBSIGATE_WEB_CACHE_TTL``   — seconds, ``0`` disables the cache (default 900)
+"""
+
+from __future__ import annotations
+
+import hashlib
+import json
+import logging
+import os
+import sqlite3
+import threading
+import time
+from pathlib import Path
+from typing import Any
+
+logger = logging.getLogger("obsigate.tools.webcache")
+
+DEFAULT_TTL_SECONDS = 900
+_schema_ready = False
+_write_lock = threading.Lock()
+
+
+def ttl_seconds() -> float:
+    """Configured TTL in seconds (``0`` = cache disabled)."""
+    return float(os.environ.get("OBSIGATE_WEB_CACHE_TTL", str(DEFAULT_TTL_SECONDS)))
+
+
+def _cache_path() -> Path:
+    override = os.environ.get("OBSIGATE_WEB_CACHE_PATH", "").strip()
+    if override:
+        return Path(override)
+    return Path(os.environ.get("OBSIGATE_DATA_DIR", "data")) / "web_cache.sqlite3"
+
+
+def _connect() -> sqlite3.Connection:
+    """Open (and lazily create) the cache database."""
+    global _schema_ready
+    path = _cache_path()
+    path.parent.mkdir(parents=True, exist_ok=True)
+    conn = sqlite3.connect(path, timeout=5, check_same_thread=False)
+    if not _schema_ready:
+        conn.execute(
+            "CREATE TABLE IF NOT EXISTS web_cache ("
+            "key TEXT PRIMARY KEY, value TEXT NOT NULL, created REAL NOT NULL)"
+        )
+        conn.commit()
+        _schema_ready = True
+    return conn
+
+
+def cache_key(prefix: str, payload: dict[str, Any]) -> str:
+    """Deterministic cache key from a prefix and the normalized arguments."""
+    raw = json.dumps(payload, ensure_ascii=False, sort_keys=True, default=str)
+    digest = hashlib.sha256(raw.encode("utf-8")).hexdigest()[:32]
+    return f"{prefix}:{digest}"
+
+
+def cache_get(key: str) -> Any | None:
+    """Return the cached payload for *key*, or ``None`` (miss/expiry/disabled)."""
+    if ttl_seconds() <= 0:
+        return None
+    try:
+        conn = _connect()
+        row = conn.execute(
+            "SELECT value, created FROM web_cache WHERE key = ?", (key,)
+        ).fetchone()
+        conn.close()
+    except sqlite3.Error as e:
+        logger.warning("web cache read failed (%s): %s", key, e)
+        return None
+    if row is None:
+        return None
+    value, created = row
+    if time.time() - float(created) > ttl_seconds():
+        return None
+    try:
+        return json.loads(value)
+    except (ValueError, TypeError):
+        return None
+
+
+def cache_set(key: str, value: Any) -> None:
+    """Store *value* under *key* (best effort, never raises)."""
+    if ttl_seconds() <= 0:
+        return
+    try:
+        with _write_lock:
+            conn = _connect()
+            conn.execute(
+                "INSERT INTO web_cache (key, value, created) VALUES (?, ?, ?) "
+                "ON CONFLICT(key) DO UPDATE SET value = excluded.value, created = excluded.created",
+                (key, json.dumps(value, ensure_ascii=False, default=str), time.time()),
+            )
+            conn.commit()
+            conn.close()
+    except sqlite3.Error as e:
+        logger.warning("web cache write failed (%s): %s", key, e)
+
+
+def purge_expired() -> int:
+    """Delete expired rows; return the number of removed entries (maintenance)."""
+    try:
+        conn = _connect()
+        cursor = conn.execute(
+            "DELETE FROM web_cache WHERE created < ?", (time.time() - ttl_seconds(),)
+        )
+        conn.commit()
+        deleted = cursor.rowcount
+        conn.close()
+        return int(deleted)
+    except sqlite3.Error as e:
+        logger.warning("web cache purge failed: %s", e)
+        return 0
+
+
+def clear_cache() -> int:
+    """Drop every cached entry (tests / admin); returns the number of rows."""
+    try:
+        conn = _connect()
+        cursor = conn.execute("DELETE FROM web_cache")
+        conn.commit()
+        deleted = cursor.rowcount
+        conn.close()
+        return int(deleted)
+    except sqlite3.Error as e:
+        logger.warning("web cache clear failed: %s", e)
+        return 0

backend/tools/webrender.py

@@ -0,0 +1,100 @@
+"""Dynamic page rendering (Playwright) — ``fetch_url(render=True)``.
+
+Static pages are fetched with httpx inside :mod:`backend.tools.web`. Dynamic
+pages (SPA/React, JS-loaded content) need a real browser engine; this module
+runs one Playwright call inside a dedicated worker thread so browser
+crashes/timeouts never take over the tool layer, and the heavyweight
+dependency stays optional:
+
+* not installed → ``ToolError(code="playwright_unavailable")`` with a clear
+  message (the assistant explains the limitation instead of hanging);
+* installed → ``pip install playwright && playwright install chromium``.
+
+The SSRF guard (scheme + private-address rejection) is applied before the
+browser navigates. Note: unlike the httpx path, internal redirects performed
+by the browser engine are not re-checked hop by hop.
+"""
+
+from __future__ import annotations
+
+import html as html_lib
+import logging
+import re
+from concurrent.futures import ThreadPoolExecutor
+from typing import Any
+
+from backend.tools.context import ToolError
+from backend.tools.web import (
+    MAX_TEXT_CHARS,
+    USER_AGENT,
+    _assert_public_http_url,
+    _html_to_text,
+)
+
+logger = logging.getLogger("obsigate.tools.webrender")
+
+# One worker: browser automation is serialized on purpose (one Chromium at a
+# time keeps memory predictable on small hosts).
+_executor = ThreadPoolExecutor(max_workers=1, thread_name_prefix="obsigate-playwright")
+GOTO_TIMEOUT_MS = 20_000
+
+
+def _playwright_available() -> bool:
+    try:
+        import playwright  # noqa: F401
+    except ImportError:
+        return False
+    return True
+
+
+def _render_in_worker(url: str) -> dict[str, Any]:
+    """Synchronous Playwright render — runs in the dedicated worker thread."""
+    from playwright.sync_api import sync_playwright
+
+    status = 0
+    with sync_playwright() as p:
+        browser = p.chromium.launch(headless=True)
+        try:
+            page = browser.new_page(user_agent=USER_AGENT)
+            response = page.goto(url, wait_until="networkidle", timeout=GOTO_TIMEOUT_MS)
+            if response is not None:
+                status = response.status
+            raw = page.content()
+            title = html_lib.unescape(page.title() or "").strip()
+            text = _html_to_text(raw)[:MAX_TEXT_CHARS]
+        finally:
+            browser.close()
+    title = re.sub(r"\s+", " ", title)[:300]
+    return {
+        "url": url,
+        "status": status,
+        "title": title,
+        "text": text,
+        "rendered": True,
+        "truncated": len(raw) > MAX_TEXT_CHARS,
+    }
+
+
+def render_page(url: str) -> dict[str, Any]:
+    """Render *url* (JavaScript included) and return readable text.
+
+    Raises:
+        ToolError: ``playwright_unavailable`` when the optional dependency is
+            missing, ``render_unavailable`` when the render itself failed.
+    """
+    _assert_public_http_url(url)
+    if not _playwright_available():
+        raise ToolError(
+            "Rendu dynamique indisponible : Playwright n'est pas installé "
+            "(pip install playwright && playwright install chromium).",
+            code="playwright_unavailable",
+        )
+    try:
+        return _executor.submit(_render_in_worker, url).result(timeout=GOTO_TIMEOUT_MS / 1000 + 40)
+    except ToolError:
+        raise
+    except Exception as e:
+        logger.warning("render_page failed for %s: %s", url, e)
+        raise ToolError(
+            "Le rendu dynamique de la page a échoué.", code="render_unavailable"
+        ) from e

desktop/Cargo.lock

@@ -2626,7 +2626,7 @@ dependencies = [
 
 [[package]]
 name = "obsigate-desktop"
-version = "2.9.1"
+version = "2.11.2"
 dependencies = [
  "chrono",
  "env_logger",

desktop/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "obsigate-desktop"
-version = "2.9.1"
+version = "2.11.2"
 description = "ObsiGate Desktop — Porte d'entrée native pour vos vaults Obsidian"
 authors = ["Bruno Charest"]
 edition = "2021"

desktop/tauri.conf.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://raw.githubusercontent.com/nicedoc/obsigate/main/desktop/tauri.conf.schema.json",
   "productName": "ObsiGate",
-  "version": "2.9.1",
+  "version": "2.11.2",
   "identifier": "com.obsigate.desktop",
   "build": {
     "frontendDist": "../frontend",

docs/ISSUES_TODOLIST.md

@@ -168,6 +168,7 @@ Avant de corriger quoi que ce soit, un agent IA doit :
 | *BUG-056* | [🟡 IMPORTANT] Éditeur Forge en plein écran : l'Assistant IA s'ouvre en arrière-plan et reste invisible | 🟢 corrigé | P1 | 📱 frontend | IA | `frontend/editor-poc.html`, `frontend/js/sync.js`, `tests/frontend/forge-completion.test.mjs`, `tests/frontend/editor-inline.test.mjs` | Forge : passer en plein écran puis cliquer le bouton « Assistant IA » (ou `Ctrl+J`) — le panneau s'ouvre dans le document parent, masqué par l'iframe plein écran | Sortie du plein écran **avant** d'ouvrir le panneau, des deux côtés : côté iframe (`openAssistant` → `document.exitFullscreen()` puis `postMessage` à la résolution) **et** côté parent (`sync.js` sur `forge-open-ai` → `document.exitFullscreen()` puis `openForCurrentContext()`), car le plein écran peut être détenu par le document parent et non par l'iframe (dans ce cas `document.fullscreenElement` est nul dans l'iframe et sa sortie échoue). Tests : `forge-completion.test.mjs` (+1), `editor-inline.test.mjs` (+1) | Le panneau assistant est monté dans `document.body` du parent : l'API Fullscreen ne rend que l'élément plein écran et ses descendants, donc il ne peut pas s'afficher au-dessus de l'iframe Forge en plein écran. La sortie côté iframe seule ne suffisait pas quand le parent détient le plein écran |
 | *BUG-057* | [🟡 IMPORTANT] Assistant IA : le bouton « Ajouter » est inopérant dans l'éditeur Forge (fonctionne seulement dans « Editer ») | 🟢 corrigé | P1 | 📱 frontend | IA | `frontend/js/bookslm.js`, `frontend/editor-poc.html` | Ouvrir un document dans Forge, demander une réponse à l'assistant puis cliquer « Ajouter » | `_insertIntoEditor()` cible Forge (`#forge-iframe`) : `postMessage({ type: 'parent-insert', text })` ; `editor-poc.html` insère au curseur (`insertAtCursor`) et marque le tampon modifié. Repli textarea inclus. Tests : `tests/frontend/ai.test.mjs` (+3), `tests/frontend/editor-inline.test.mjs` (+1) | `state.editorView` (CodeMirror) est nul en Forge : le clic affichait « Aucun document ouvert dans l'éditeur » |
 | *BUG-058* | [🔵 MINEUR] Éditeur « Editer » : la barre de numérotation de ligne ne suit pas la couleur du thème (gutter clair `#f5f5f5` en thème sombre) | 🟢 corrigé | P2 | 📱 frontend | IA | `frontend/style.css` | Ouvrir un document → Editer en thème sombre : la colonne des numéros de ligne reste gris clair alors que le fond de l'éditeur est sombre | Thème du gutter CodeMirror via les variables CSS (`color-mix(var(--text-primary) …)` pour le fond, `--text-secondary` pour les numéros, `--border` pour la séparation, `--text-primary` pour la ligne active) au lieu des valeurs codées en dur de CodeMirror ; test de non-régression dans `tests/frontend/editor-inline.test.mjs`. Vérifié Playwright (instance de test) : sombre `color(srgb 0.90 0.93 0.95 / 0.05)` + bordure `#21262d`, clair `color(srgb 0.12 0.14 0.16 / 0.05)` + bordure `#d0d7de` | CodeMirror applique `background:#f5f5f5` par défaut, indépendamment du thème ObsiGate ; en mode sombre le fond de l'éditeur suit `--bg-secondary` mais pas le gutter |
+| *BUG-060* | [🟡 IMPORTANT] Viewer PDF : l'affichage des pages ne fonctionne pas — seule la barre d'outils « PDF — N pages » s'affiche, le contenu reste vide | 🟢 corrigé | P1 | 📱 frontend | IA | `frontend/js/viewer.js`, `tests/frontend/pdf-viewer.test.mjs` (nouveau), `tests/e2e/pdf-viewer.spec.js` (nouveau) | Cliquer un fichier `.pdf` dans l'arborescence | `frontend/js/viewer.js` : le rendu PDF passe de `<embed type="application/pdf">` à `<iframe>` (autorisée par `frame-src 'self'`, le stream étant same-origin). Tests : `tests/frontend/pdf-viewer.test.mjs` (+6) et `tests/e2e/pdf-viewer.spec.js` (fixture `test_vault/sample-pdf.pdf`) | Cause : la CSP durcie en BUG-034 pose `object-src 'none'`, directive qui gouverne `<embed>`/`<object>` → le lecteur PDF natif était bloqué (barre d'outils rendue, corps vide). Le test E2E échoue bien avec l'ancien `<embed>`. `object-src 'none'` conservé (le correctif ne désarme pas la CSP) |
 |  | | | | | | | | | | |
 
 ### TODOs techniques (améliorations / nouvelles tâches)
@@ -229,6 +230,8 @@ Avant de corriger quoi que ce soit, un agent IA doit :
 | 2026-09-17 | BUG-056 | Correction | `frontend/editor-poc.html`, `frontend/js/sync.js`, `tests/frontend/forge-completion.test.mjs`, `tests/frontend/editor-inline.test.mjs`, `CHANGELOG.md`, `docs/ISSUES_TODOLIST.md` | **BUG-056** : en plein écran Forge, l'Assistant IA s'ouvrait en arrière-plan. La sortie du plein écran est désormais faite **côté iframe** (`openAssistant` → `document.exitFullscreen()` puis `postMessage` à la résolution) **et côté parent** (`sync.js` sur `forge-open-ai` → `document.exitFullscreen()` puis `openForCurrentContext()`), car le plein écran peut appartenir au document parent (l'iframe voit alors `fullscreenElement` nul et sa sortie échoue — c'était le cas non couvert par le premier correctif). Vérifié : `forge-completion.test.mjs` 32/32 (+1), `editor-inline.test.mjs` 42/42 (+1), 14 suites frontend vertes, validate-imports 38 modules. | 🟢 corrigé (en attente vérif utilisateur) |
 | 2026-09-17 | BUG-057, #102 | Correction + feature | `frontend/js/bookslm.js`, `frontend/editor-poc.html`, `frontend/style.css`, `frontend/locales/{fr,en}.json`, `tests/frontend/ai.test.mjs`, `tests/frontend/editor-inline.test.mjs`, `docs/archive/COMPLETED_v1-v2.md`, `docs/ROADMAP.md`, `CHANGELOG.md` | **BUG-057** : le bouton « Ajouter » de l'assistant ne ciblait que `state.editorView` (CodeMirror) ; en Forge il affichait « Aucun document ouvert dans l'éditeur ». `_insertIntoEditor()` gère désormais les trois surfaces : CodeMirror, l'iframe Forge (`postMessage({ type: 'parent-insert', text })` → `insertAtCursor` dans `editor-poc.html`) et le textarea de repli. **#102** : chaque bloc de code d'une réponse reçoit un bouton « Ajouter la section » (`.bookslm-code-insert`, révélé au survol) qui insère le contenu du bloc sans les délimiteurs ` ``` `. Vérifié : `ai.test.mjs` 91/91 (+3), `editor-inline.test.mjs` 43/43 (+1), `forge-completion.test.mjs` 32/32, unit 9/9, validate-imports 38 modules, pytest 1101 passed / 6 skipped, ruff 0, mypy 0. | 🟢 corrigé (en attente vérif utilisateur) |
 | 2026-09-17 | BUG-058 | Correction | `frontend/style.css`, `tests/frontend/editor-inline.test.mjs`, `CHANGELOG.md`, `docs/ISSUES_TODOLIST.md` | **BUG-058** : la barre de numérotation de ligne de l'éditeur « Editer » ne suivait pas le thème — CodeMirror peint `.cm-gutters` avec des valeurs claires codées en dur (`#f5f5f5`, bordure `#ddd`), visibles en thème sombre. Correctif : le gutter dérive des variables CSS ObsiGate (`background: color-mix(in srgb, var(--text-primary) 5%, transparent)`, `color: var(--text-secondary)`, `border-right: 1px solid var(--border)`, ligne active `color-mix(… 10% …)` / `--text-primary`), donc il suit les 15 thèmes et les 4 modes. Vérifié : `editor-inline.test.mjs` 44/44 (+1), unit 9/9, validate-imports 38 modules, pytest 1101 passed / 6 skipped, ruff 0, mypy 0, et Playwright sur l'instance de test (route `style.css` remplacée par le fichier local) — sombre `color(srgb 0.90 0.93 0.95 / 0.05)` + bordure `#21262d`, clair `color(srgb 0.12 0.14 0.16 / 0.05)` + bordure `#d0d7de`, plus de `rgb(245,245,245)`. | 🟢 corrigé (en attente vérif utilisateur) |
+| 2026-09-17 | BUG-059 | Correction | `frontend/js/bookslm.js`, `tests/frontend/ai.test.mjs`, `CHANGELOG.md`, `docs/ISSUES_TODOLIST.md` | **BUG-059** : dans une conversation ouverte (post ancré en haut), **tout clic** dans la fenêtre de messages — lien de fichier, étapes, sélection de texte — faisait sauter toute la conversation au bas de la fenêtre. Cause : le gestionnaire `mousedown` de dépintage (prévu pour la molette/tactile/poignée de scroll) se déclenchait aussi sur un simple clic, et le retrait du padding d'ancre (`paddingBottom`) bornait le `scrollTop` à la nouvelle hauteur max → saut au bas. Correctif : helper pur `isScrollbarPress(target, clientX, container)` — un appui ne dépine que s'il vise la **poignée de scroll** (cible = conteneur + zone de gouttière droite) ; molette et tactile conservent leur comportement. Vérifié : `ai.test.mjs` 92/92 (+1), unit 9/9, validate-imports 38 modules, pytest / ruff / mypy inchangés côté backend. | 🟢 corrigé (en attente vérif utilisateur) |
+| 2026-09-17 | BUG-060 | Correction | `frontend/js/viewer.js`, `.gitea/workflows/ci.yml`, `tests/frontend/pdf-viewer.test.mjs` (nouveau), `tests/e2e/pdf-viewer.spec.js` (nouveau), `test_vault/sample-pdf.pdf` (nouveau), `CHANGELOG.md`, `docs/ISSUES_TODOLIST.md` | **BUG-060** : l'ouverture d'un PDF n'affichait aucune page (barre d'outils « PDF — N pages » présente, corps vide). Cause : la CSP durcie en BUG-034 pose `object-src 'none'` — directive qui gouverne `<embed>`/`<object>` — alors que le viewer rendait le PDF via `<embed type="application/pdf">` : le lecteur natif était bloqué. Correctif : rendu dans une `<iframe>` (autorisée par `frame-src 'self'`, le stream `/api/file/{vault}/pdf/stream` étant same-origin) ; `object-src 'none'` conservé. Tests : `pdf-viewer.test.mjs` 6/6 (statique : pas d'`<embed>`, CSP `frame-src 'self'`, iframe pleine hauteur), `pdf-viewer.spec.js` (E2E : iframe + stream `application/pdf` 200/206 + zéro violation CSP ; échoue bien avec l'ancien `<embed>`). Vérifié : pytest 1184 passed / 6 skipped, frontend 14 suites JSDOM vertes, validate-imports 38 modules, ruff/mypy 0. | 🟢 corrigé (en attente vérif utilisateur) |
 
 ---
 

docs/ROADMAP.md

@@ -1,6 +1,6 @@
 # ObsiGate — Roadmap
 
-> **Version :** 2.9.1 | **Dernière mise à jour :** 2026-09-17
+> **Version :** 2.11.2 | **Dernière mise à jour :** 2026-09-17
 > **Ce fichier ne contient que le travail à venir** (🔵 En cours + ⚪ Backlog) et un index compact
 > vers les fonctionnalités livrées.
 > - **Méthode de livraison à appliquer pour toute tâche : [DELIVERY_WORKFLOW.md](./DELIVERY_WORKFLOW.md)**
@@ -78,23 +78,6 @@
   - [x] Personnalisation (clé à molette) : ajouter / supprimer / réordonner les commandes
   - [x] i18n FR/EN + tests frontend (helpers purs) + E2E mobile
 
-### 92. Assistant IA — Écosystème d'outils (phase 2 : web étendu, sources connectées, documents)
-
-- **Effort :** 3-5 jours | **Impact :** 🟠 | **Zone :** backend (`backend/tools/`)
-- **Dépend de :** #91 (registre + section « steps » + `web_search`/`fetch_url` livrés)
-- **Description :** étendre le catalogue d'outils de l'assistant au-delà du vault, en
-  suivant la feuille de route technique détaillée :
-  [features/ai-tools-roadmap.md](./features/ai-tools-roadmap.md) (frameworks évalués,
-  bibliothèques par catégorie, transverse retry/cache/secrets/async).
-- **Sous-tâches :**
-  - [x] `web_search` : chaîne de repli sans clé (SearXNG → DuckDuckGo → Bing, `OBSIGATE_WEB_FALLBACK`) — BUG-051
-  - [ ] `web_search` : fournisseurs optionnels à clé (Tavily, Brave, SerpAPI, Exa)
-  - [ ] `fetch_url` : pages dynamiques via Playwright (worker isolé) ; crawl multi-pages Scrapy en tâche de fond
-  - [ ] Sources connectées : Gitea/GitHub (priorité haute) puis Google Drive / OneDrive (OAuth2 `authlib`)
-  - [ ] Production de documents : conversion, tableurs, PDF/Word (outils WRITE + confirmation)
-  - [ ] Transverse : `tenacity` (backoff), cache SQLite des résultats web avec TTL, secrets via Infisical
-  - [ ] Chaque outil : libellé `labels.py` + clés i18n `ai.step.*` FR/EN + tests (httpx mocké)
-
 ---
 
 ## ⚪ Backlog — Sécurité, architecture & performance (P0/P1)
@@ -201,6 +184,8 @@
 | 101 | Forge — Assistant IA partagé (bouton AI Panel = assistant, fournisseur/modèle configuré, autocomplétion) + plein écran Forge/Editer | 2.8.0 | [features/forge-assistant.md](./features/forge-assistant.md) |
 | BUG-057 | Assistant IA — bouton « Ajouter » fonctionnel dans l'éditeur Forge (en plus d'« Editer ») | 2.9.0 | [archive](./archive/COMPLETED_v1-v2.md) |
 | 102 | Assistant IA — bouton « Ajouter la section » par bloc de code (insertion du bloc seul) | 2.9.0 | [archive](./archive/COMPLETED_v1-v2.md) |
+| 92 | Assistant IA — Écosystème d'outils phase 2 (recherche à clé, cache/retry, Playwright, crawl, Gitea/GitHub, documents XLSX/DOCX/CSV/PDF) | 2.10.0 | [features/ai-tools-roadmap.md](./features/ai-tools-roadmap.md) |
+| 103 | Configuration — clés utilisateur des sources connectées & recherche à clé (page Configurations, `data/api_keys.json`, priorité sur l'env) | 2.11.0 | [features/ai-tools-roadmap.md](./features/ai-tools-roadmap.md) |
 
 ---
 
@@ -208,12 +193,11 @@
 
 | Priorité | Items | Effort total estimé |
 |---|---|---|
-| ✅ Complété | #1 → #59, #61–72, #74–76, #78–84, #88–93, #94–100 | ~114 jours réalisés |
+| ✅ Complété | #1 → #59, #61–72, #74–76, #78–84, #88–93, #94–100, #102, #92 | ~114 jours réalisés |
 | 🔵 P2 restant | #77 Desktop : signature de code (non retenue), 6 tests E2E **manuels** ([protocole](./DESKTOP_E2E_CHECKLIST.md)) | ~0,5-1 jour |
 | ⚪ P4 restant | #73 Sync (6-8j) | 6-8 jours |
-| ⚪ P2 restant | #92 Assistant IA — écosystème d'outils phase 2 (web étendu, sources connectées, documents) | 3-5 jours |
 | ⚪ P0/P1 restant | #85-87 Refonte architecturale, performance, CI/CD (issues BUG-035 → BUG-040) | ~15-23 jours |
-| **Total restant** | **10 items + finitions** | **~30-47 jours** |
+| **Total restant** | **7 items + finitions** | **~27-42 jours** |
 
 ---
 

docs/features/ai-tools-roadmap.md

@@ -1,6 +1,6 @@
 # #92 — Assistant IA — Écosystème d'outils : feuille de route technique
 
-> **Statut :** ⚪ Backlog (phase 1 livrée dans #91)
+> **Statut :** ✅ livré (phase 2, version 2.10.0) — phase 1 livrée dans #91
 > **Effort estimé :** 3-5 jours pour la phase 2 | **Impact :** 🟠
 > **Références :** [Roadmap](../ROADMAP.md) · [Outils & MCP #79](./ai-tools-mcp.md) ·
 > [Fenêtre de discussion #91](./ai-assistant-conversation-ux.md) · [Changelog](../../CHANGELOG.md)
@@ -36,6 +36,17 @@ réécriture de la boucle n'est nécessaire.
 
 ## 3. Phase 2 — catégories à implémenter
 
+> **Livré (2.10.0, #92).** Récapitulatif des décisions finales :
+
+| Catégorie | Décision livrée |
+|---|---|
+| Recherche web étendue | Tavily, Brave, SerpAPI, Exa à clé (`OBSIGATE_*_API_KEY`), essayés avant SearXNG ; ordre via `OBSIGATE_WEB_PROVIDERS` |
+| Lecture de pages | `fetch_url(render=True)` → worker Playwright isolé (`backend/tools/webrender.py`), dépendance optionnelle + erreur explicite |
+| Crawl multi-pages | `crawl_site` (WRITE + confirmation) : BFS httpx borné (≤ 20 pages, même hôte, SSRF sur chaque URL) → condensé Markdown dans le vault. Scrapy écarté (dépendance lourde inutile à cette échelle) |
+| Sources connectées | Gitea + GitHub (`git_list_repos`, `git_search_issues`, `git_get_file`) via env/Infisical ; drives cloud (Drive/OneDrive) orientés serveur MCP externe (#79). **#103 (2.11.0)** : les clés (URL Gitea, tokens Gitea/GitHub, clés Tavily/Brave/SerpAPI/Exa) se saisissent aussi dans la page Configurations — `backend/tools/secrets.py`, valeur stockée prioritaire sur l'env |
+| Production de documents | `create_xlsx`, `create_docx`, `create_csv`, `create_pdf` — WRITE + confirmation, écrit via `save_raw_file(allow_docs=True)` (path safety + backup) |
+| Transverse | Cache SQLite (`webcache.py`, TTL `OBSIGATE_WEB_CACHE_TTL`), retry backoff maison (`OBSIGATE_WEB_RETRY`), secrets par env (Infisical-compatible) |
+
 ### 3.1 Recherche web étendue (`web_search`)
 - **Fallback sans clé — ✅ livré (BUG-051)** : chaîne de fournisseurs dans
   `backend/tools/web.py` — SearXNG auto-hébergé (`OBSIGATE_SEARXNG_URL`) puis, si

docs/features/pdf.md

@@ -8,6 +8,7 @@
 
 - **Implémentation réelle (vérifiée 2026-09-07) :**
   - **Bugs corrigés (2026-09) :** `api_pdf_stream` crashait en 500 (`NameError: current_user` jamais injecté) ; l'indexation incrémentale du watcher faisait `read_text()` sur les PDFs (garbage) ; Range/206 et `pdf/info` absents malgré le texte ci-dessous.
+  - **BUG-060 (2026-09-17) :** l'affichage inline ne fonctionnait plus — la CSP durcie en BUG-034 (`object-src 'none'`) bloquait l'`<embed>` du viewer (barre d'outils rendue, corps vide). Le rendu passe par une `<iframe>` (autorisée par `frame-src 'self'`), conforme à E1. Tests : `tests/frontend/pdf-viewer.test.mjs` + `tests/e2e/pdf-viewer.spec.js`.
   - `GET /api/file/{vault}/pdf/info` — métadonnées seules sans transférer le document (C3)
   - Stream avec `Accept-Ranges` + 206 Partial Content (single range, suffix-range, 416) (C2)
   - `OBSIGATE_PDF_MAX_SIZE_MB` (50) + `OBSIGATE_PDF_EXTRACT_TIMEOUT` (30s via thread-pool) (B4/G3)

frontend/index.html

@@ -1543,6 +1543,7 @@
 <li><a href="#cfg-hidden-files" class="help-nav-link" data-i18n="config.section_hidden"></a></li>
 <li><a href="#cfg-diags" class="help-nav-link" data-i18n="settings.diagnostics"></a></li>
 <li><a href="#cfg-ai" class="help-nav-link" data-i18n="settings.ai"></a></li>
+<li><a href="#cfg-sources" class="help-nav-link" data-i18n="config.section_sources">Sources connectées</a></li>
 <li><a href="#cfg-themes" class="help-nav-link" data-i18n="settings.themes"></a></li>
 <li><a href="#cfg-profile" class="help-nav-link" data-i18n="settings.profile"></a></li>
 <li><a href="#cfg-security" class="help-nav-link" data-i18n="settings.security"></a></li>
@@ -2260,6 +2261,133 @@
                                 </div>
                             </section>
 
+                            <!-- Connected sources & keyed web search (#103) -->
+                            <section
+                                class="config-section help-section"
+                                id="cfg-sources"
+                            >
+                                <h2 data-i18n="config.section_sources"
+                                    >Sources connectées & recherche web</h2
+                                >
+                                <p
+                                    class="config-description"
+                                    data-i18n="config.sources_desc"
+                                >
+                                    Clés utilisées par les outils de l'Assistant IA
+                                    (recherche web à clé, Gitea, GitHub). Elles sont
+                                    stockées localement et priment sur les variables
+                                    d'environnement.
+                                </p>
+                                <div class="config-row">
+                                    <label
+                                        class="config-label"
+                                        for="cfg-tavily-key"
+                                        >Tavily API Key</label
+                                    >
+                                    <input
+                                        type="password"
+                                        id="cfg-tavily-key"
+                                        class="config-input"
+                                        placeholder="tvly-..."
+                                        autocomplete="off"
+                                    />
+                                </div>
+                                <div class="config-row">
+                                    <label
+                                        class="config-label"
+                                        for="cfg-brave-key"
+                                        >Brave Search API Key</label
+                                    >
+                                    <input
+                                        type="password"
+                                        id="cfg-brave-key"
+                                        class="config-input"
+                                        placeholder="BSA..."
+                                        autocomplete="off"
+                                    />
+                                </div>
+                                <div class="config-row">
+                                    <label
+                                        class="config-label"
+                                        for="cfg-serpapi-key"
+                                        >SerpAPI Key</label
+                                    >
+                                    <input
+                                        type="password"
+                                        id="cfg-serpapi-key"
+                                        class="config-input"
+                                        placeholder="..."
+                                        autocomplete="off"
+                                    />
+                                </div>
+                                <div class="config-row">
+                                    <label
+                                        class="config-label"
+                                        for="cfg-exa-key"
+                                        >Exa API Key</label
+                                    >
+                                    <input
+                                        type="password"
+                                        id="cfg-exa-key"
+                                        class="config-input"
+                                        placeholder="..."
+                                        autocomplete="off"
+                                    />
+                                </div>
+                                <div class="config-row">
+                                    <label
+                                        class="config-label"
+                                        for="cfg-gitea-url"
+                                        data-i18n="config.gitea_url"
+                                        >URL Gitea</label
+                                    >
+                                    <input
+                                        type="text"
+                                        id="cfg-gitea-url"
+                                        class="config-input"
+                                        placeholder="https://git.example.net"
+                                        autocomplete="off"
+                                    />
+                                </div>
+                                <div class="config-row">
+                                    <label
+                                        class="config-label"
+                                        for="cfg-gitea-token"
+                                        >Gitea Token</label
+                                    >
+                                    <input
+                                        type="password"
+                                        id="cfg-gitea-token"
+                                        class="config-input"
+                                        placeholder="token personnel..."
+                                        autocomplete="off"
+                                    />
+                                </div>
+                                <div class="config-row">
+                                    <label
+                                        class="config-label"
+                                        for="cfg-github-token"
+                                        >GitHub Token</label
+                                    >
+                                    <input
+                                        type="password"
+                                        id="cfg-github-token"
+                                        class="config-input"
+                                        placeholder="ghp_..."
+                                        autocomplete="off"
+                                    />
+                                </div>
+                                <div
+                                    class="config-actions-row"
+                                    style="margin-top: 16px"
+                                >
+                                    <button class="config-btn-save"
+                                        id="cfg-save-tool-keys" data-i18n="help.shortcut_save">
+                                        Sauvegarder
+                                    </button>
+                                </div>
+                            </section>
+
                             <!-- Themes -->
                             <section
                                 class="config-section help-section"

frontend/js/bookslm.js

@@ -43,6 +43,25 @@ const PANEL_MIN_WIDTH = 320;
 const PANEL_MAX_WIDTH = 1000;
 const PANEL_WIDTH_KEY = 'obsigate-bookslm-width';
 
+/**
+ * BUG-059 — Is this pointer press a scrollbar drag (and only that)?
+ *
+ * Only genuine scroll gestures may release the top-pinning of the latest
+ * question (wheel / touchmove / scrollbar drag). A scrollbar drag reports the
+ * scrollable container itself as the event target and lands inside the
+ * vertical scrollbar gutter. A plain click anywhere in the content — a link,
+ * a file path, the steps toggle, text selection — must NOT unpin: clearing
+ * the anchor padding would clamp the scroll position and jump the whole
+ * thread to the bottom of the conversation window.
+ */
+export function isScrollbarPress(target, clientX, container) {
+  if (!container || target !== container) return false;
+  const rect = container.getBoundingClientRect();
+  if (!rect || !Number.isFinite(rect.right)) return false;
+  const GUTTER = 24; // conservative vertical-scrollbar width estimate
+  return clientX >= rect.right - GUTTER;
+}
+
 /**
  * Accent- and case-insensitive normalization used to match `/` commands and
  * `@` mentions: skill ids/labels and vault paths may contain accented
@@ -985,7 +1004,12 @@ class BooksLM {
       };
       messagesEl.addEventListener('wheel', unpin, { passive: true });
       messagesEl.addEventListener('touchmove', unpin, { passive: true });
-      messagesEl.addEventListener('mousedown', unpin, { passive: true });
+      // BUG-059: a scrollbar drag only — a plain click on the content must
+      // not unpin (it would clear the anchor padding and jump the thread to
+      // the bottom of the window).
+      messagesEl.addEventListener('mousedown', (e) => {
+        if (isScrollbarPress(e.target, e.clientX, messagesEl)) unpin();
+      }, { passive: true });
     }
 
     // Close the session / command menus when clicking elsewhere in the panel.

frontend/js/config.js

@@ -715,6 +715,7 @@ function initConfigModal() {
     await loadHiddenFilesSettings();
     loadWebhooksUI();
     loadSharesUI();
+    loadToolKeys();
     safeCreateIcons();
   });
 
@@ -765,6 +766,9 @@ function initConfigModal() {
   if (saveAIKeysBtn) saveAIKeysBtn.addEventListener("click", saveAIKeys);
   const testAIKeysBtn = document.getElementById("cfg-test-ai-keys");
   if (testAIKeysBtn) testAIKeysBtn.addEventListener("click", testAIKeys);
+  // Tool & connected-source keys (#103)
+  const saveToolKeysBtn = document.getElementById("cfg-save-tool-keys");
+  if (saveToolKeysBtn) saveToolKeysBtn.addEventListener("click", saveToolKeys);
   // Default provider/model selection
   const aiDefaultProviderSel = document.getElementById("cfg-ai-default-provider");
   if (aiDefaultProviderSel) {
@@ -1715,6 +1719,102 @@ async function testAIKeys() {
   }
 
 
+// ── Tool & connected-source keys (#103) ──
+const TOOL_KEY_MAP = {
+  "cfg-tavily-key": "OBSIGATE_TAVILY_API_KEY",
+  "cfg-brave-key": "OBSIGATE_BRAVE_API_KEY",
+  "cfg-serpapi-key": "OBSIGATE_SERPAPI_API_KEY",
+  "cfg-exa-key": "OBSIGATE_EXA_API_KEY",
+  "cfg-gitea-url": "OBSIGATE_GITEA_URL",
+  "cfg-gitea-token": "OBSIGATE_GITEA_TOKEN",
+  "cfg-github-token": "OBSIGATE_GITHUB_TOKEN",
+};
+
+function _ensureToolKeyUI() {
+  for (const [inputId] of Object.entries(TOOL_KEY_MAP)) {
+    const input = document.getElementById(inputId);
+    if (!input) continue;
+    const row = input.closest(".config-row");
+    if (!row || row.dataset.toolKeyEnhanced) continue;
+    row.dataset.toolKeyEnhanced = "1";
+    row.style.cssText += "display:flex;align-items:center;gap:8px;flex-wrap:wrap;";
+    const badge = document.createElement("span");
+    badge.id = inputId + "-badge";
+    badge.style.cssText = "font-size:11px;padding:2px 8px;border-radius:10px;white-space:nowrap;";
+    row.appendChild(badge);
+    const delBtn = document.createElement("button");
+    delBtn.type = "button";
+    delBtn.id = inputId + "-delete";
+    delBtn.className = "config-btn-secondary";
+    delBtn.style.cssText = "font-size:11px;padding:4px 10px;color:var(--danger,#e74c3c);border-color:var(--danger,#e74c3c);cursor:pointer;display:none;";
+    delBtn.textContent = "\u00d7 " + t("config.delete_key");
+    delBtn.addEventListener("click", () => deleteToolKey(inputId));
+    row.appendChild(delBtn);
+  }
+}
+
+function _setToolKeyBadge(inputId, hasKey) {
+  const badge = document.getElementById(inputId + "-badge");
+  const delBtn = document.getElementById(inputId + "-delete");
+  if (badge) {
+    if (hasKey) {
+      badge.textContent = "\u2713 " + t("config.key_set");
+      badge.style.background = "var(--success-bg, #27ae6022)";
+      badge.style.color = "var(--success, #27ae60)";
+      badge.style.border = "1px solid var(--success, #27ae60)";
+    } else {
+      badge.textContent = t("config.key_unset");
+      badge.style.background = "var(--muted-bg, #ffffff10)";
+      badge.style.color = "var(--text-muted, #888)";
+      badge.style.border = "1px solid var(--border, #444)";
+    }
+  }
+  if (delBtn) delBtn.style.display = hasKey ? "inline-block" : "none";
+}
+
+async function loadToolKeys() {
+  _ensureToolKeyUI();
+  try {
+    const data = await api("/api/config/tool-keys");
+    for (const [inputId, name] of Object.entries(TOOL_KEY_MAP)) {
+      const input = document.getElementById(inputId);
+      const val = data[name] || "";
+      if (input && !input.value.trim()) input.placeholder = val || input.placeholder;
+      _setToolKeyBadge(inputId, !!val);
+    }
+  } catch(e) { /* non-admin: the section stays inert */ }
+}
+
+async function saveToolKeys() {
+  const keys = {};
+  for (const [id, name] of Object.entries(TOOL_KEY_MAP)) {
+    const input = document.getElementById(id);
+    if (input && input.value.trim()) keys[name] = input.value.trim();
+  }
+  if (!Object.keys(keys).length) {
+    showToast(t("config.no_keys"), "warning");
+    return;
+  }
+  try {
+    await api("/api/config/tool-keys", { method: "POST", body: JSON.stringify(keys) });
+    showToast(t("config.api_keys_saved"), "success");
+    Object.keys(TOOL_KEY_MAP).forEach(id => { const el = document.getElementById(id); if (el) el.value = ""; });
+    loadToolKeys();
+  } catch(e) { showToast("Erreur: " + e.message, "error"); }
+}
+
+async function deleteToolKey(inputId) {
+  const name = TOOL_KEY_MAP[inputId];
+  if (!name) return;
+  if (!confirm(t("config.delete_key_confirm") + " " + name + " ?")) return;
+  try {
+    await api("/api/config/tool-keys/" + name, { method: "DELETE" });
+    showToast(t("config.key_deleted") + " " + name, "success");
+    loadToolKeys();
+  } catch(e) { showToast("Erreur: " + e.message, "error"); }
+}
+
+
 export {
   initSidebarTabs,
   initConfigModal,

frontend/js/viewer.js

@@ -555,7 +555,7 @@ export function renderFile(data) {
         </div>
         <div class="pdf-body">
           ${tocHtml}
-          <embed src="${pdfUrl}" class="pdf-iframe" type="application/pdf" title="${escapeHtml(data.title)}"></embed>
+          <iframe src="${pdfUrl}" class="pdf-iframe" title="${escapeHtml(data.title)}"></iframe>
         </div>
       </div>`;
     lucide.createIcons();

frontend/locales/en.json

@@ -364,6 +364,14 @@
   "config.ai_model": "Model",
   "config.ai_openrouter_label": "OpenRouter API Key",
   "config.api_keys_saved": "API keys saved",
+  "config.section_sources": "🔗 Connected sources & search",
+  "config.sources_desc": "Keys used by the AI assistant tools (keyed web search: Tavily, Brave, SerpAPI, Exa; connected sources: Gitea, GitHub). They are stored server-side and take precedence over environment variables.",
+  "config.gitea_url": "Gitea URL",
+  "config.key_set": "Configured",
+  "config.key_unset": "Not configured",
+  "config.delete_key": "Delete",
+  "config.delete_key_confirm": "Delete key",
+  "config.key_deleted": "Key deleted:",
   "config.backups": "Backups",
   "config.backups_desc": "Manage automatic file backups.",
   "config.client_config": "Client config",
@@ -1822,6 +1830,14 @@
   "ai.step.vaults": "Listed the vaults",
   "ai.step.fetch_url": "Opened a web page: {value}",
   "ai.step.web_search": "Searched the web: {value}",
+  "ai.step.crawl": "Crawled a site: {value}",
+  "ai.step.git_repos": "Listed repositories ({value})",
+  "ai.step.git_issues": "Searched issues: {value}",
+  "ai.step.git_file": "Read a repo file: {value}",
+  "ai.step.xlsx_create": "Spreadsheet proposed: {value}",
+  "ai.step.docx_create": "Word document proposed: {value}",
+  "ai.step.csv_create": "CSV file proposed: {value}",
+  "ai.step.pdf_create": "PDF document proposed: {value}",
   "bookslm.copied": "Copied to clipboard",
   "bookslm.error": "AI service error",
   "bookslm.regenerate": "Regenerate",

frontend/locales/fr.json

@@ -364,6 +364,14 @@
   "config.ai_model": "Modèle",
   "config.ai_openrouter_label": "OpenRouter API Key",
   "config.api_keys_saved": "Clés API sauvegardées",
+  "config.section_sources": "🔗 Sources connectées & recherche",
+  "config.sources_desc": "Clés utilisées par les outils de l'Assistant IA (recherche web à clé : Tavily, Brave, SerpAPI, Exa ; sources connectées : Gitea, GitHub). Elles sont stockées sur le serveur et priment sur les variables d'environnement.",
+  "config.gitea_url": "URL Gitea",
+  "config.key_set": "Configuré",
+  "config.key_unset": "Non configuré",
+  "config.delete_key": "Supprimer",
+  "config.delete_key_confirm": "Supprimer la clé",
+  "config.key_deleted": "Clé supprimée :",
   "config.backups": "Sauvegardes",
   "config.backups_desc": "Gérez les sauvegardes automatiques de vos fichiers.",
   "config.client_config": "Configuration client",
@@ -1822,6 +1830,14 @@
   "ai.step.vaults": "Liste des vaults consultée",
   "ai.step.fetch_url": "Page web consultée : {value}",
   "ai.step.web_search": "Recherche sur le web : {value}",
+  "ai.step.crawl": "Site exploré : {value}",
+  "ai.step.git_repos": "Dépôts listés ({value})",
+  "ai.step.git_issues": "Issues recherchées : {value}",
+  "ai.step.git_file": "Fichier de dépôt lu : {value}",
+  "ai.step.xlsx_create": "Tableur proposé : {value}",
+  "ai.step.docx_create": "Document Word proposé : {value}",
+  "ai.step.csv_create": "Fichier CSV proposé : {value}",
+  "ai.step.pdf_create": "Document PDF proposé : {value}",
   "bookslm.copied": "Réponse copiée dans le presse-papiers",
   "bookslm.error": "Erreur du service AI",
   "bookslm.regenerate": "Régénérer",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "obsigate",
-  "version": "2.9.1",
+  "version": "2.11.2",
   "description": "**Porte d'entrée web ultra-léger pour vos vaults Obsidian** — Accédez, naviguez et recherchez dans toutes vos notes Obsidian depuis n'importe quel appareil via une interface web moderne et responsive.",
   "main": "patch.js",
   "directories": {

test_vault/sample-pdf.pdf

@@ -0,0 +1,106 @@
+%PDF-1.3
+%“Œ‹ž ReportLab Generated PDF document (opensource)
+1 0 obj
+<<
+/F1 2 0 R
+>>
+endobj
+2 0 obj
+<<
+/BaseFont /Helvetica /Encoding /WinAnsiEncoding /Name /F1 /Subtype /Type1 /Type /Font
+>>
+endobj
+3 0 obj
+<<
+/Contents 9 0 R /MediaBox [ 0 0 612 792 ] /Parent 8 0 R /Resources <<
+/Font 1 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ]
+>> /Rotate 0 /Trans <<
+
+>> 
+  /Type /Page
+>>
+endobj
+4 0 obj
+<<
+/Contents 10 0 R /MediaBox [ 0 0 612 792 ] /Parent 8 0 R /Resources <<
+/Font 1 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ]
+>> /Rotate 0 /Trans <<
+
+>> 
+  /Type /Page
+>>
+endobj
+5 0 obj
+<<
+/Contents 11 0 R /MediaBox [ 0 0 612 792 ] /Parent 8 0 R /Resources <<
+/Font 1 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ]
+>> /Rotate 0 /Trans <<
+
+>> 
+  /Type /Page
+>>
+endobj
+6 0 obj
+<<
+/PageMode /UseNone /Pages 8 0 R /Type /Catalog
+>>
+endobj
+7 0 obj
+<<
+/Author (anonymous) /CreationDate (D:20260917153218-04'00') /Creator (anonymous) /Keywords () /ModDate (D:20260917153218-04'00') /Producer (ReportLab PDF Library - \(opensource\)) 
+  /Subject (unspecified) /Title (untitled) /Trapped /False
+>>
+endobj
+8 0 obj
+<<
+/Count 3 /Kids [ 3 0 R 4 0 R 5 0 R ] /Type /Pages
+>>
+endobj
+9 0 obj
+<<
+/Filter [ /ASCII85Decode /FlateDecode ] /Length 135
+>>
+stream
+GapQh0E=F,0U\H3T\pNYT^QKk?tc>IP,;W#U1^23ihPEM_?CU^!/VX4lBrg6%A?7Y)Zc(P6:e82L4<*@VL)cDW^;5oRmL:j77h2jWe.B?6"5/?Jt]&.8<uSu(.bn9(BF;Q*M*~>endstream
+endobj
+10 0 obj
+<<
+/Filter [ /ASCII85Decode /FlateDecode ] /Length 135
+>>
+stream
+GapQh0E=F,0U\H3T\pNYT^QKk?tc>IP,;W#U1^23ihPEM_?CU^!/VX4lBrg6%A?7Y)Zc(P6:e82L4<*@VL)cDW^;5oRmL:j77h2jWe.B?6"5/?Jruos8<uSu(.bn9(BF;_*M3~>endstream
+endobj
+11 0 obj
+<<
+/Filter [ /ASCII85Decode /FlateDecode ] /Length 135
+>>
+stream
+GapQh0E=F,0U\H3T\pNYT^QKk?tc>IP,;W#U1^23ihPEM_?CU^!/VX4lBrg6%A?7Y)Zc(P6:e82L4<*@VL)cDW^;5oRmL:j77h2jWe.B?6"5/?K!D1>8<uSu(.bn9(BF;m*M<~>endstream
+endobj
+xref
+0 12
+0000000000 65535 f 
+0000000061 00000 n 
+0000000092 00000 n 
+0000000199 00000 n 
+0000000392 00000 n 
+0000000586 00000 n 
+0000000780 00000 n 
+0000000848 00000 n 
+0000001109 00000 n 
+0000001180 00000 n 
+0000001405 00000 n 
+0000001631 00000 n 
+trailer
+<<
+/ID 
+[<464fc7cfdf793a5b6d29e3d0d043c5a7><464fc7cfdf793a5b6d29e3d0d043c5a7>]
+% ReportLab generated PDF document -- digest (opensource)
+
+/Info 7 0 R
+/Root 6 0 R
+/Size 12
+>>
+startxref
+1857
+%%EOF

tests/conftest.py

@@ -22,6 +22,23 @@ def _reset_tool_ratelimit():
     ratelimit.reset()
 
 
+@pytest.fixture(autouse=True)
+def _disable_web_cache():
+    """Web cache off by default: tests stay hermetic (no cross-test hits).
+
+    tests/test_web_cache.py re-enables it explicitly with a tmp path.
+    """
+    from backend.tools import webcache
+
+    saved_path = os.environ.get("OBSIGATE_WEB_CACHE_PATH")
+    os.environ["OBSIGATE_WEB_CACHE_TTL"] = "0"
+    yield
+    if saved_path is None:
+        os.environ.pop("OBSIGATE_WEB_CACHE_PATH", None)
+    else:
+        os.environ["OBSIGATE_WEB_CACHE_PATH"] = saved_path
+
+
 @pytest.fixture(autouse=True)
 def _clean_env():
     """Ensure no vault env vars leak between tests — but preserve test vault config."""

tests/e2e/pdf-viewer.spec.js

@@ -0,0 +1,92 @@
+/**
+ * E2E tests for ObsiGate PDF inline viewer (BUG-060).
+ *
+ * Regression : la CSP posée par BUG-034 (`object-src 'none'`) bloque l'élément
+ * `<embed>` qui servait le PDF. Le viewer doit rendre le stream dans une
+ * `<iframe>` (autorisée par `frame-src 'self'`).
+ *
+ * Fixtures : `test_vault/sample-pdf.pdf` (3 pages, texte simple).
+ *
+ * Run (local):
+ *   BASE_URL=http://localhost:2029 npx playwright test tests/e2e/pdf-viewer.spec.js
+ *   BASE_URL=http://localhost:2029 npx playwright test tests/e2e/pdf-viewer.spec.js --headed
+ */
+
+import { test, expect } from '@playwright/test';
+
+const BASE = process.env.BASE_URL || 'http://localhost:2029';
+
+const CREDS = {
+  username: process.env.OBSIGATE_USER || 'admin',
+  password: process.env.OBSIGATE_PASS || 'test123',
+};
+
+async function login(page) {
+  await page.goto(BASE);
+  const loginForm = page.locator('#login-screen');
+  await expect(loginForm).toBeVisible({ timeout: 5000 }).catch(() => {});
+  if (await loginForm.isVisible()) {
+    await page.fill('#login-username', CREDS.username);
+    await page.fill('#login-password', CREDS.password);
+    await page.click('#login-btn');
+  }
+  await page.waitForFunction(() => window.__OBSIGATE_BOOTED === true, { timeout: 20000 });
+}
+
+async function openFile(page, vault, filePath) {
+  const treeItem = page.locator(`.tree-item[data-vault="${vault}"][data-path="${filePath}"]`);
+  // Le vault peut être replié (auth activée) : l'étendre avant de chercher le fichier.
+  if (!(await treeItem.count())) {
+    await page.locator(`.tree-item.vault-item[data-vault="${vault}"]`).first().click();
+    await treeItem.waitFor({ state: 'attached', timeout: 8000 });
+  }
+  await treeItem.dblclick({ timeout: 5000 });
+  await page.waitForTimeout(500);
+}
+
+test.describe('PDF viewer — affichage inline (BUG-060)', () => {
+
+  test('ouvre un PDF dans une iframe (pas d\'<embed>) et le stream charge sans violation CSP', async ({ page }) => {
+    const cspViolations = [];
+    page.on('console', (msg) => {
+      const text = msg.text();
+      if (text.includes('Content Security Policy') && (text.includes('object-src') || text.includes('Refused'))) {
+        cspViolations.push(text);
+      }
+    });
+
+    await login(page);
+
+    // Le stream est demandé au moment où le viewer monte l'iframe : enregistrer
+    // l'écoute AVANT d'ouvrir le fichier (sinon la réponse est déjà passée).
+    const streamResponsePromise = page.waitForResponse(
+      (r) => r.url().includes('/pdf/stream') && (r.status() === 200 || r.status() === 206),
+      { timeout: 15000 },
+    );
+
+    await openFile(page, 'TestVault', 'sample-pdf.pdf');
+
+    const iframe = page.locator('#content-area .pdf-iframe');
+    await expect(iframe).toBeVisible({ timeout: 15000 });
+    await expect(iframe).toHaveAttribute('src', /\/api\/file\/TestVault\/pdf\/stream\?path=/);
+
+    // La balise doit être une iframe (le <embed>/<object> serait bloqué par CSP)
+    const tagName = await iframe.evaluate((el) => el.tagName);
+    expect(tagName).toBe('IFRAME');
+    expect(await page.locator('#content-area embed, #content-area object').count()).toBe(0);
+
+    // La barre d'outils indique le nombre de pages du PDF
+    await expect(page.locator('.pdf-info')).toContainText('3 pages');
+
+    // Le stream est bien servi en application/pdf (200 ou 206 Range)
+    const streamResp = await streamResponsePromise;
+    expect(streamResp.headers()['content-type'] || '').toContain('application/pdf');
+
+    // Le cadre embarque réellement le document PDF (navigateur natif)
+    const pdfFrame = await iframe.contentFrame();
+    expect(pdfFrame).not.toBeNull();
+
+    // Aucune violation CSP liée à object-src pendant l'ouverture
+    expect(cspViolations).toEqual([]);
+  });
+});

tests/frontend/ai.test.mjs

@@ -302,6 +302,25 @@ async function main() {
       }
     });
 
+    await test("isScrollbarPress: content clicks never unpin, scrollbar drags do (BUG-059)", () => {
+      const { isScrollbarPress } = bookslmMod;
+      const container = document.createElement("div");
+      container.getBoundingClientRect = () => ({
+        left: 0, right: 800, top: 0, bottom: 600, width: 800, height: 600,
+      });
+      const link = document.createElement("a");
+      // Click on a file link / steps toggle → must NOT unpin (the thread
+      // would otherwise jump to the bottom when the padding is cleared).
+      assert.equal(isScrollbarPress(link, 790, container), false);
+      // Click on blank content area → must NOT unpin either.
+      assert.equal(isScrollbarPress(container, 300, container), false);
+      // Dragging the vertical scrollbar: target is the container itself and
+      // the press lands in the right-edge gutter → unpin allowed.
+      assert.equal(isScrollbarPress(container, 792, container), true);
+      // Defensive: no container / no geometry → never unpin.
+      assert.equal(isScrollbarPress(link, 790, null), false);
+    });
+
     await test("the placeholder render keeps the anchor (no scroll reset before first token)", async () => {
       // Regression: the assistant placeholder used to be rendered while
       // `_isLoading` was still false, so it took the "restore previous

tests/frontend/pdf-viewer.test.mjs

@@ -0,0 +1,95 @@
+#!/usr/bin/env node
+/**
+ * ObsiGate — Viewer PDF non-regression tests (BUG-060).
+ *
+ * Static checks on the source of the PDF inline viewer:
+ *  - BUG-060 : the CSP set by BUG-034 puts `object-src 'none'`, which blocks
+ *    `<embed>`/`<object>`. The PDF body was therefore never rendered (blank
+ *    pages). The viewer must now use an `<iframe>` — permitted by
+ *    `frame-src 'self'` since the PDF stream URL is same-origin.
+ *
+ * Usage: node tests/frontend/pdf-viewer.test.mjs
+ */
+
+import { strict as assert } from "node:assert";
+import { readFileSync } from "node:fs";
+import path from "node:path";
+import { fileURLToPath } from "node:url";
+
+const __dirname = path.dirname(fileURLToPath(import.meta.url));
+const ROOT = path.join(__dirname, "..", "..");
+
+const viewer = readFileSync(path.join(ROOT, "frontend", "js", "viewer.js"), "utf8");
+const main = readFileSync(path.join(ROOT, "backend", "main.py"), "utf8");
+const css = readFileSync(path.join(ROOT, "frontend", "style.css"), "utf8");
+
+function test(label, fn) {
+  try {
+    fn();
+    console.log("  \u2713 " + label);
+  } catch (err) {
+    console.error("  \u2717 " + label + "\n    " + err.message);
+    process.exitCode = 1;
+  }
+}
+
+// ── viewer.js : le rendu PDF passe par une iframe ─────────────────────────
+test("viewer.js — PDF branch renders the stream in an <iframe class=pdf-iframe>", () => {
+  const block = viewer.match(/if \(data\.is_pdf\) \{([\s\S]*?)\n  \}/);
+  assert.ok(block, "PDF render block not found");
+  assert.match(
+    block[1],
+    /<iframe src="\$\{pdfUrl\}" class="pdf-iframe"/,
+    "PDF must use <iframe>, not <embed>/<object> (CSP object-src 'none' otherwise blocks it)",
+  );
+  assert.match(
+    block[1],
+    /\.pdf-iframe[\s\S]*?src="\$\{pdfUrl\}"/,
+    "iframe src must come from the /pdf/stream URL",
+  );
+});
+
+test("viewer.js — no <embed>/<object> left in the source", () => {
+  assert.doesNotMatch(viewer, /<embed\b/i, "<embed> is blocked by CSP object-src 'none'");
+  assert.doesNotMatch(viewer, /<object\b/i, "<object> is blocked by CSP object-src 'none'");
+});
+
+test("viewer.js — TOC still targets the pdf-iframe via contentWindow", () => {
+  assert.match(
+    viewer,
+    /document\.querySelector\('\.pdf-iframe'\)\.contentWindow\.location\.hash='page=\$\{item\.page\}'/,
+    "TOC links must keep navigating the iframe",
+  );
+});
+
+// ── backend : la CSP autorise le cadre same-origin ─────────────────────────
+test("backend CSP — frame-src 'self' allows same-origin iframes", () => {
+  const csp = main.match(/frame-src ([^";]+);/);
+  assert.ok(csp, "CSP frame-src directive not found");
+  assert.ok(
+    csp[1].includes("'self'"),
+    `frame-src must allow 'self' (found: ${csp[1]}) — otherwise the PDF iframe is blocked`,
+  );
+});
+
+test("backend CSP — object-src 'none' stays in place (no defusing)", () => {
+  assert.match(
+    main,
+    /object-src 'none';/,
+    "object-src must stay locked to 'none': the fix is moving to <iframe>, not weakening CSP",
+  );
+});
+
+// ── style.css : l'iframe garde une hauteur utile ───────────────────────────
+test("style.css — .pdf-iframe fills the viewer body", () => {
+  const rule = css.match(/\.pdf-iframe\s*\{([^}]*)\}/);
+  assert.ok(rule, ".pdf-iframe rule not found");
+  assert.match(rule[1], /flex:\s*1/, "iframe must stretch to fill the available height");
+  assert.match(rule[1], /min-height/, "iframe must keep its minimum height");
+});
+
+if (process.exitCode) {
+  console.error("\nPDF viewer tests FAILED");
+} else {
+  console.log("\nAll PDF viewer tests passed.");
+}

tests/test_connected_tools.py

@@ -0,0 +1,230 @@
+"""Unit tests for the connected sources (#92): Gitea & GitHub tools.
+
+All HTTP calls are mocked (httpx.request monkeypatched) — the CI never talks
+to a real Gitea/GitHub instance.
+"""
+
+import base64
+from typing import Any
+
+import pytest
+
+import backend.tools.connected as connected
+from backend.tools.context import ToolContext, ToolError, ToolMode
+from backend.tools.registry import get_tool
+
+
+class FakeResponse:
+    def __init__(self, json_data: Any = None, status_code: int = 200):
+        self._json = json_data
+        self.status_code = status_code
+
+    def json(self):
+        return self._json
+
+    def raise_for_status(self):
+        if self.status_code >= 400:
+            import httpx
+
+            raise httpx.HTTPStatusError("boom", request=None, response=self)  # type: ignore[arg-type]
+
+
+def _ctx() -> ToolContext:
+    return ToolContext(user={"username": "tester", "vaults": []}, mode=ToolMode.IN_APP)
+
+
+@pytest.fixture
+def gitea_env(monkeypatch):
+    monkeypatch.setenv("OBSIGATE_GITEA_URL", "https://git.example.net")
+    monkeypatch.setenv("OBSIGATE_GITEA_TOKEN", "tok-gitea")
+
+
+@pytest.fixture
+def github_env(monkeypatch):
+    monkeypatch.setenv("OBSIGATE_GITHUB_TOKEN", "tok-gh")
+
+
+def _patch_request(monkeypatch, handler):
+    def fake_request(method, url, headers=None, timeout=None, follow_redirects=False, **kw):
+        captured = {"method": method, "url": str(url), "headers": headers or {},
+                    "params": kw.get("params")}
+        return handler(captured)
+
+    monkeypatch.setattr(connected.httpx, "request", fake_request)
+
+
+class TestRegistration:
+    @pytest.mark.parametrize("name", ["git_list_repos", "git_search_issues", "git_get_file"])
+    def test_tools_registered_read(self, name):
+        from backend.tools.context import ToolRisk
+
+        spec = get_tool(name)
+        assert spec is not None
+        assert spec.risk == ToolRisk.READ
+        assert "gitea" in spec.description or "github" in spec.description.lower()
+
+
+class TestConfiguration:
+    def test_gitea_requires_base_url(self, monkeypatch):
+        monkeypatch.delenv("OBSIGATE_GITEA_URL", raising=False)
+        with pytest.raises(ToolError) as ei:
+            connected._provider_base("gitea")
+        assert ei.value.code == "provider_not_configured"
+
+    def test_unknown_provider_rejected(self):
+        with pytest.raises(ToolError) as ei:
+            connected._provider_base("gitlab")
+        assert ei.value.code == "invalid_arguments"
+
+    def test_gitea_token_sent_as_header(self, gitea_env, monkeypatch):
+        captured = {}
+
+        def handler(captured_req):
+            captured.update(captured_req)
+            return FakeResponse(json_data={"data": []})
+
+        _patch_request(monkeypatch, handler)
+        connected.git_list_repos(_ctx(), connected.GitProviderInput(provider="gitea"))
+        assert captured["headers"]["Authorization"] == "token tok-gitea"
+
+
+class TestListRepos:
+    def test_gitea_search_endpoint(self, gitea_env, monkeypatch):
+        captured = {}
+
+        def handler(captured_req):
+            captured.update(captured_req)
+            return FakeResponse(json_data={"data": [
+                {"name": "ObsiGate", "full_name": "bruno/ObsiGate",
+                 "html_url": "https://git.example.net/bruno/ObsiGate",
+                 "description": "vault gateway", "updated_at": "2026-09-01",
+                 "private": False},
+            ]})
+
+        _patch_request(monkeypatch, handler)
+        out = connected.git_list_repos(_ctx(), connected.GitProviderInput(provider="gitea"))
+        assert "/api/v1/repos/search" in captured["url"]
+        assert out["repos"][0]["name"] == "ObsiGate"
+        assert out["count"] == 1
+
+    def test_github_single_repo(self, github_env, monkeypatch):
+        captured = {}
+
+        def handler(captured_req):
+            captured.update(captured_req)
+            return FakeResponse(json_data={
+                "name": "ObsiGate", "full_name": "bruno/ObsiGate",
+                "html_url": "https://github.com/bruno/ObsiGate",
+                "description": "", "updated_at": "2026-09-02", "private": True,
+            })
+
+        _patch_request(monkeypatch, handler)
+        out = connected.git_list_repos(_ctx(), connected.GitProviderInput(
+            provider="github", repo="bruno/ObsiGate"))
+        assert captured["url"].endswith("/repos/bruno/ObsiGate")
+        assert out["repos"][0]["full_name"] == "bruno/ObsiGate"
+        assert out["repos"][0]["private"] is True
+
+
+class TestSearchIssues:
+    def test_gitea_scoped_to_repo(self, gitea_env, monkeypatch):
+        captured = {}
+
+        def handler(captured_req):
+            captured.update(captured_req)
+            return FakeResponse(json_data=[
+                {"number": 12, "title": "Bug affichage", "html_url": "https://x/12",
+                 "state": "open"},
+            ])
+
+        _patch_request(monkeypatch, handler)
+        out = connected.git_search_issues(_ctx(), connected.GitSearchIssuesInput(
+            provider="gitea", query="affichage", repo="bruno/ObsiGate"))
+        assert "/repos/bruno/ObsiGate/issues" in captured["url"]
+        assert out["issues"][0]["id"] == 12
+        assert out["issues"][0]["pull_request"] is False
+
+    def test_github_search_syntax(self, github_env, monkeypatch):
+        captured = {}
+
+        def handler(captured_req):
+            captured.update(captured_req)
+            return FakeResponse(json_data={"items": [
+                {"number": 5, "title": "Crash on save", "html_url": "https://gh/5",
+                 "state": "open", "pull_request": {"url": "x"}},
+            ]})
+
+        _patch_request(monkeypatch, handler)
+        out = connected.git_search_issues(_ctx(), connected.GitSearchIssuesInput(
+            provider="github", query="crash", repo="bruno/ObsiGate", state="open"))
+        assert "/search/issues" in captured["url"]
+        assert "repo:bruno/ObsiGate" in captured["params"]["q"]
+        assert out["issues"][0]["pull_request"] is True
+
+
+class TestGetFile:
+    def test_gitea_base64_content_decoded(self, gitea_env, monkeypatch):
+        payload = base64.b64encode("# Readme\n\nBonjour".encode()).decode()
+
+        def handler(_captured):
+            return FakeResponse(json_data={
+                "path": "README.md", "size": 15, "encoding": "base64", "content": payload,
+            })
+
+        _patch_request(monkeypatch, handler)
+        out = connected.git_get_file(_ctx(), connected.GitGetFileInput(
+            provider="gitea", repo="bruno/ObsiGate", path="README.md"))
+        assert "Bonjour" in out["content"]
+        assert out["truncated"] is False
+
+    def test_github_ref_parameter(self, github_env, monkeypatch):
+        captured = {}
+
+        def handler(captured_req):
+            captured.update(captured_req)
+            return FakeResponse(json_data={
+                "path": "a.md", "size": 1, "encoding": "base64",
+                "content": base64.b64encode(b"x").decode(),
+            })
+
+        _patch_request(monkeypatch, handler)
+        connected.git_get_file(_ctx(), connected.GitGetFileInput(
+            provider="github", repo="o/r", path="a.md", ref="v2.9.0"))
+        assert captured["url"].endswith("?ref=v2.9.0")
+
+    def test_missing_repo_or_path_rejected(self, gitea_env):
+        with pytest.raises(ToolError) as ei:
+            connected.git_get_file(_ctx(), connected.GitGetFileInput(
+                provider="gitea", repo="", path="a.md"))
+        assert ei.value.code == "invalid_arguments"
+
+
+class TestErrors:
+    def test_404_maps_to_not_found(self, gitea_env, monkeypatch):
+        def handler(_captured):
+            return FakeResponse(json_data={}, status_code=404)
+
+        _patch_request(monkeypatch, handler)
+        with pytest.raises(ToolError) as ei:
+            connected.git_list_repos(_ctx(), connected.GitProviderInput(provider="gitea"))
+        assert ei.value.code == "not_found"
+
+    def test_401_maps_to_permission_denied(self, gitea_env, monkeypatch):
+        def handler(_captured):
+            return FakeResponse(json_data={}, status_code=401)
+
+        _patch_request(monkeypatch, handler)
+        with pytest.raises(ToolError) as ei:
+            connected.git_list_repos(_ctx(), connected.GitProviderInput(provider="gitea"))
+        assert ei.value.code == "permission_denied"
+
+    def test_network_error_maps_to_tool_error(self, gitea_env, monkeypatch):
+        import httpx
+
+        def fake_request(*a, **kw):
+            raise httpx.ConnectError("down")
+
+        monkeypatch.setattr(connected.httpx, "request", fake_request)
+        with pytest.raises(ToolError) as ei:
+            connected.git_list_repos(_ctx(), connected.GitProviderInput(provider="gitea"))
+        assert ei.value.code == "connected_source_unavailable"

tests/test_crawler.py

@@ -0,0 +1,135 @@
+"""Unit tests for the bounded site crawler (#92): crawl_site (WRITE + confirmation)."""
+
+from typing import Any
+
+import pytest
+
+import backend.tools.crawler as crawler
+from backend.tools.api import ToolConfirmationRequired, ToolContext, ToolError, call_tool
+
+
+class FakeResponse:
+    def __init__(self, content: bytes = b"", status_code: int = 200,
+                 headers: dict | None = None):
+        self.content = content
+        self.status_code = status_code
+        self.headers = headers or {"content-type": "text/html; charset=utf-8"}
+        self.encoding = "utf-8"
+
+    def raise_for_status(self):
+        pass
+
+
+def _ctx() -> ToolContext:
+    return ToolContext(
+        user={"username": "tester", "role": "admin", "vaults": ["*"]},
+        audit_enabled=False,
+    )
+
+
+@pytest.fixture
+def vault(tmp_path, monkeypatch):
+    vault_dir = tmp_path / "Vault"
+    vault_dir.mkdir()
+    monkeypatch.setitem(__import__("backend.indexer", fromlist=["index"]).index,
+                        "Vault", {"name": "Vault", "path": str(vault_dir), "config": {}})
+    return vault_dir
+
+
+PAGE_A = (
+    b"<html><head><title>Docs</title></head><body>"
+    b"<p>Bienvenue sur la documentation.</p>"
+    b'<a href="/page-b">Suite</a><a href="https://other.dev/x">ext</a>'
+    b"</body></html>"
+)
+PAGE_B = (
+    b"<html><head><title>Page B</title></head><body><p>Details ici.</p></body></html>"
+)
+
+
+@pytest.fixture
+def local_urls(monkeypatch):
+    """Skip the DNS-based SSRF guard: test hosts are fake, HTTP is mocked."""
+    monkeypatch.setattr(crawler, "_assert_public_http_url", lambda url: url)
+
+
+@pytest.fixture
+def two_pages(monkeypatch, local_urls):
+    def fake_get(url, **kw):
+        url = str(url)
+        if url.endswith("/page-b"):
+            return FakeResponse(content=PAGE_B)
+        return FakeResponse(content=PAGE_A)
+
+    monkeypatch.setattr(crawler.httpx, "get", fake_get)
+
+
+class TestConfirmation:
+    def test_requires_confirmation(self, vault, two_pages):
+        with pytest.raises(ToolConfirmationRequired):
+            call_tool("crawl_site", _ctx(), {
+                "url": "https://docs.example.dev/start",
+                "vault": "Vault", "path": "Crawls/docs.md",
+            })
+
+
+class TestCrawl:
+    def test_saves_same_host_pages(self, vault, two_pages):
+        out = call_tool("crawl_site", _ctx(), {
+            "url": "https://docs.example.dev/start",
+            "vault": "Vault", "path": "Crawls/docs.md",
+        }, confirm=True)
+        assert out.ok and out.data["pages"] == 2
+        digest = (vault / "Crawls" / "docs.md").read_text(encoding="utf-8")
+        assert "# Crawl de docs.example.dev" in digest
+        assert "Bienvenue sur la documentation." in digest
+        assert "Details ici." in digest
+        assert "other.dev" not in digest
+
+    def test_max_pages_bound(self, vault, monkeypatch, local_urls):
+        # A link farm: every page links to a new page — cap at max_pages.
+        def fake_get(url, **kw):
+            url = str(url)
+            n = int(url.rsplit("/", 1)[-1] or 0)
+            return FakeResponse(
+                content=f"<html><head><title>P{n}</title></head><body>"
+                        f"<p>page {n}</p><a href=\"/{n + 1}\">next</a></body></html>".encode())
+
+        monkeypatch.setattr(crawler.httpx, "get", fake_get)
+        out = call_tool("crawl_site", _ctx(), {
+            "url": "https://farm.example.dev/0",
+            "vault": "Vault", "path": "farm.md", "max_pages": 3,
+        }, confirm=True)
+        assert out.ok and out.data["pages"] == 3
+
+    def test_no_pages_recovered(self, vault, monkeypatch, local_urls):
+        def dead_get(*a, **kw):
+            raise crawler.httpx.ConnectError("down")
+
+        monkeypatch.setattr(crawler.httpx, "get", dead_get)
+        with pytest.raises(ToolError) as ei:
+            call_tool("crawl_site", _ctx(), {
+                "url": "https://dead.example.dev/", "vault": "Vault", "path": "x.md",
+            }, confirm=True)
+        assert ei.value.code == "crawl_failed"
+
+    def test_internal_url_rejected(self, vault):
+        with pytest.raises(ToolError) as ei:
+            call_tool("crawl_site", _ctx(), {
+                "url": "http://127.0.0.1:8080/", "vault": "Vault", "path": "x.md",
+            }, confirm=True)
+        assert ei.value.code in ("ssrf_blocked", "dns_error")
+
+    def test_binary_content_skipped(self, vault, monkeypatch, local_urls):
+        def fake_get(url, **kw):
+            url = str(url)
+            if url.endswith("/x.pdf"):
+                return FakeResponse(content=b"%PDF-1.4", headers={"content-type": "application/pdf"})
+            return FakeResponse(content=PAGE_A)
+
+        monkeypatch.setattr(crawler.httpx, "get", fake_get)
+        out = call_tool("crawl_site", _ctx(), {
+            "url": "https://docs.example.dev/start",
+            "vault": "Vault", "path": "docs.md", "max_pages": 5,
+        }, confirm=True)
+        assert out.ok and out.data["pages"] >= 1

tests/test_document_tools.py

@@ -0,0 +1,197 @@
+"""Unit tests for the document-production tools (#92): create_xlsx, create_docx,
+create_csv, create_pdf — WRITE risk, confirmation gating, vault persistence."""
+
+import csv
+import io
+from pathlib import Path
+
+import pytest
+
+from backend.tools.api import (
+    ToolConfirmationRequired,
+    ToolContext,
+    ToolError,
+    call_tool,
+    get_tool,
+)
+from backend.tools.context import ToolRisk
+
+
+@pytest.fixture
+def vault(tmp_path, monkeypatch):
+    """A minimal configured vault (index entry patched, no full build)."""
+    vault_dir = tmp_path / "Vault"
+    vault_dir.mkdir()
+    monkeypatch.setitem(__import__("backend.indexer", fromlist=["index"]).index,
+                        "Vault", {"name": "Vault", "path": str(vault_dir), "config": {}})
+    return vault_dir
+
+
+def _ctx() -> ToolContext:
+    return ToolContext(
+        user={"username": "tester", "role": "admin", "vaults": ["*"]},
+        audit_enabled=False,
+    )
+
+
+class TestRegistry:
+    @pytest.mark.parametrize("name", ["create_xlsx", "create_docx", "create_csv", "create_pdf"])
+    def test_write_risk_and_confirmation(self, name):
+        spec = get_tool(name)
+        assert spec is not None
+        assert spec.risk == ToolRisk.WRITE
+        assert spec.requires_confirmation is True
+
+
+class TestConfirmationGating:
+    def test_csv_requires_confirmation(self, vault):
+        with pytest.raises(ToolConfirmationRequired):
+            call_tool("create_csv", _ctx(), {
+                "vault": "Vault", "path": "data.csv",
+                "rows": [["a", "b"], [1, 2]],
+            })
+
+    def test_pdf_requires_confirmation(self, vault):
+        with pytest.raises(ToolConfirmationRequired):
+            call_tool("create_pdf", _ctx(), {
+                "vault": "Vault", "path": "doc.pdf", "title": "T", "content": "# H\npara",
+            })
+
+
+class TestCreateCsv:
+    def test_creates_file_in_vault(self, vault):
+        out = call_tool("create_csv", _ctx(), {
+            "vault": "Vault", "path": "Exports/data.csv",
+            "rows": [["nom", "score"], ["alice", 12], ["bob", 9.5]],
+        }, confirm=True)
+        assert out.ok and out.data["success"] is True
+        path = vault / "Exports" / "data.csv"
+        assert path.exists()
+        rows = list(csv.reader(io.StringIO(path.read_text(encoding="utf-8"))))
+        assert rows[0] == ["nom", "score"]
+        assert rows[2] == ["bob", "9.5"]
+
+    def test_semicolon_delimiter(self, vault):
+        call_tool("create_csv", _ctx(), {
+            "vault": "Vault", "path": "d.csv", "delimiter": ";",
+            "rows": [["a", "b"], [1, 2]],
+        }, confirm=True)
+        content = (vault / "d.csv").read_text(encoding="utf-8")
+        assert "a;b" in content
+
+    def test_wrong_extension_rejected(self, vault):
+        with pytest.raises(ToolError) as ei:
+            call_tool("create_csv", _ctx(), {
+                "vault": "Vault", "path": "d.txt", "rows": [["a"], [1]],
+            }, confirm=True)
+        assert ei.value.code == "invalid_arguments"
+
+    def test_empty_rows_rejected(self, vault):
+        with pytest.raises(ToolError):
+            call_tool("create_csv", _ctx(), {
+                "vault": "Vault", "path": "d.csv", "rows": [],
+            }, confirm=True)
+
+
+class TestCreateXlsx:
+    def test_creates_readable_workbook(self, vault):
+        call_tool("create_xlsx", _ctx(), {
+            "vault": "Vault", "path": "Rapports/budget.xlsx",
+            "rows": [["item", "cout"], ["serveur", 1200], ["licence", 300]],
+            "sheet_name": "Budget",
+        }, confirm=True)
+        from openpyxl import load_workbook
+
+        wb = load_workbook(vault / "Rapports" / "budget.xlsx")
+        ws = wb.active
+        assert ws.title == "Budget"
+        assert ws.cell(row=1, column=1).value == "item"
+        assert ws.cell(row=2, column=2).value == 1200
+
+    def test_wrong_extension_rejected(self, vault):
+        with pytest.raises(ToolError):
+            call_tool("create_xlsx", _ctx(), {
+                "vault": "Vault", "path": "b.docx", "rows": [["a"], [1]],
+            }, confirm=True)
+
+
+class TestCreateDocx:
+    def test_creates_readable_document(self, vault):
+        call_tool("create_docx", _ctx(), {
+            "vault": "Vault", "path": "rapport.docx",
+            "title": "Rapport hebdo", "paragraphs": ["Premier point.", "Second point."],
+        }, confirm=True)
+        import docx as docx_lib
+
+        doc = docx_lib.Document(str(vault / "rapport.docx"))
+        texts = [p.text for p in doc.paragraphs]
+        assert "Rapport hebdo" in texts
+        assert "Second point." in texts
+
+    def test_no_paragraphs_rejected(self, vault):
+        with pytest.raises(ToolError):
+            call_tool("create_docx", _ctx(), {
+                "vault": "Vault", "path": "r.docx", "paragraphs": [],
+            }, confirm=True)
+
+
+class TestCreatePdf:
+    def test_creates_valid_pdf(self, vault):
+        call_tool("create_pdf", _ctx(), {
+            "vault": "Vault", "path": "docs/archi.pdf",
+            "title": "Architecture", "content": "# Titre\n\nUn paragraphe.\n## Sous-titre\nAutre texte.",
+        }, confirm=True)
+        raw = (vault / "docs" / "archi.pdf").read_bytes()
+        assert raw.startswith(b"%PDF")
+
+    def test_long_content_truncated(self, vault):
+        call_tool("create_pdf", _ctx(), {
+            "vault": "Vault", "path": "big.pdf", "title": "T", "content": "x" * 500_000,
+        }, confirm=True)
+        assert (vault / "big.pdf").exists()
+
+    def test_markdown_tables_go_through_the_export_pipeline(self, vault, monkeypatch):
+        # The document-page pipeline (mistune tables + WeasyPrint) must be
+        # used when available: capture the HTML handed to the PDF generator.
+        import sys
+        import types
+
+        captured = {}
+        fake = types.ModuleType("backend.pdf_export")
+
+        def fake_build(html, title, **kw):
+            captured["html"] = html
+            captured["title"] = title
+            return "<html>" + html + "</html>"
+
+        fake.build_pdf_html = fake_build
+        fake.generate_pdf = lambda html, title=None, **kw: b"%PDF-fake"
+        monkeypatch.setitem(sys.modules, "backend.pdf_export", fake)
+        out = call_tool("create_pdf", _ctx(), {
+            "vault": "Vault", "path": "table.pdf", "title": "Rapport",
+            "content": "# T\n\n| a | b |\n|---|---|\n| 1 | 2 |",
+        }, confirm=True)
+        assert out.ok
+        assert "<table>" in captured["html"]
+        assert captured["title"] == "Rapport"
+        assert (vault / "table.pdf").read_bytes() == b"%PDF-fake"
+
+    def test_reportlab_fallback_when_weasyprint_missing(self, vault, monkeypatch):
+        # sys.modules[name] = None makes `from backend.pdf_export import …`
+        # raise ImportError → the simplified renderer must take over.
+        import sys
+
+        monkeypatch.setitem(sys.modules, "backend.pdf_export", None)
+        call_tool("create_pdf", _ctx(), {
+            "vault": "Vault", "path": "fb.pdf", "title": "T", "content": "# H\ntexte",
+        }, confirm=True)
+        assert (vault / "fb.pdf").read_bytes().startswith(b"%PDF")
+
+
+class TestVaultSafety:
+    def test_path_outside_vault_rejected(self, vault):
+        with pytest.raises(ToolError) as ei:
+            call_tool("create_csv", _ctx(), {
+                "vault": "Vault", "path": "../outside.csv", "rows": [["a"], [1]],
+            }, confirm=True)
+        assert ei.value.code in ("path_outside_vault", "invalid_arguments", "tool_execution_error")

tests/test_tool_keys.py

@@ -0,0 +1,163 @@
+"""Unit tests for the tool/connected-source key store (#103).
+
+Covers ``backend.tools.secrets`` (precedence, masking, whitelist) and the
+``/api/config/tool-keys`` endpoints (masked GET, POST, DELETE, admin-only).
+"""
+
+import json
+from pathlib import Path
+
+import pytest
+
+from backend.tools.secrets import (
+    TOOL_KEY_NAMES,
+    delete_tool_key,
+    get_tool_key,
+    is_secret_name,
+    mask_value,
+    set_tool_key,
+)
+
+
+@pytest.fixture
+def key_store(tmp_path, monkeypatch):
+    """Isolated key store directory."""
+    monkeypatch.setenv("OBSIGATE_DATA_DIR", str(tmp_path))
+    yield tmp_path
+
+
+def _write_store(tmp_path, data):
+    (tmp_path / "api_keys.json").write_text(json.dumps(data), encoding="utf-8")
+
+
+class TestGetToolKey:
+    def test_stored_value_takes_precedence_over_env(self, key_store, monkeypatch):
+        _write_store(key_store, {"OBSIGATE_GITHUB_TOKEN": "stored-token"})
+        monkeypatch.setenv("OBSIGATE_GITHUB_TOKEN", "env-token")
+        assert get_tool_key("OBSIGATE_GITHUB_TOKEN") == "stored-token"
+
+    def test_env_fallback_when_not_stored(self, key_store, monkeypatch):
+        monkeypatch.setenv("OBSIGATE_GITEA_TOKEN", "env-token")
+        assert get_tool_key("OBSIGATE_GITEA_TOKEN") == "env-token"
+
+    def test_missing_everywhere_returns_empty(self, key_store, monkeypatch):
+        monkeypatch.delenv("OBSIGATE_GITHUB_TOKEN", raising=False)
+        assert get_tool_key("OBSIGATE_GITHUB_TOKEN") == ""
+
+    def test_non_whitelisted_name_uses_env_only(self, key_store, monkeypatch):
+        _write_store(key_store, {"OTHER_KEY": "stored"})
+        monkeypatch.setenv("OTHER_KEY", "env")
+        assert get_tool_key("OTHER_KEY") == "env"
+
+    def test_whitelist_covers_expected_names(self):
+        assert set(TOOL_KEY_NAMES) == {
+            "OBSIGATE_TAVILY_API_KEY",
+            "OBSIGATE_BRAVE_API_KEY",
+            "OBSIGATE_SERPAPI_API_KEY",
+            "OBSIGATE_EXA_API_KEY",
+            "OBSIGATE_GITEA_URL",
+            "OBSIGATE_GITEA_TOKEN",
+            "OBSIGATE_GITHUB_TOKEN",
+        }
+
+
+class TestSetDelete:
+    def test_set_then_get_roundtrip(self, key_store):
+        set_tool_key("OBSIGATE_TAVILY_API_KEY", "tvly-1234")
+        assert get_tool_key("OBSIGATE_TAVILY_API_KEY") == "tvly-1234"
+
+    def test_set_empty_value_deletes_entry(self, key_store):
+        set_tool_key("OBSIGATE_TAVILY_API_KEY", "tvly-1234")
+        set_tool_key("OBSIGATE_TAVILY_API_KEY", "")
+        assert get_tool_key("OBSIGATE_TAVILY_API_KEY") == ""
+        assert "OBSIGATE_TAVILY_API_KEY" not in json.loads(
+            (key_store / "api_keys.json").read_text(encoding="utf-8")
+        )
+
+    def test_delete_removes_and_reports(self, key_store):
+        set_tool_key("OBSIGATE_GITEA_URL", "https://git.example.net")
+        assert delete_tool_key("OBSIGATE_GITEA_URL") is True
+        assert delete_tool_key("OBSIGATE_GITEA_URL") is False
+
+    def test_unknown_name_rejected(self, key_store):
+        with pytest.raises(ValueError):
+            set_tool_key("NOT_WHITELISTED", "x")
+        with pytest.raises(ValueError):
+            delete_tool_key("NOT_WHITELISTED")
+
+    def test_store_keeps_other_entries(self, key_store):
+        _write_store(key_store, {"DEEPSEEK_API_KEY": "sk-existing"})
+        set_tool_key("OBSIGATE_EXA_API_KEY", "exa-key")
+        data = json.loads((key_store / "api_keys.json").read_text(encoding="utf-8"))
+        assert data["DEEPSEEK_API_KEY"] == "sk-existing"
+        assert data["OBSIGATE_EXA_API_KEY"] == "exa-key"
+
+
+class TestMasking:
+    def test_urls_returned_clear(self):
+        assert mask_value("OBSIGATE_GITEA_URL", "https://git.example.net") == \
+            "https://git.example.net"
+
+    def test_tokens_masked(self):
+        masked = mask_value("OBSIGATE_GITHUB_TOKEN", "ghp_abcdefgh1234")
+        assert masked.startswith("ghp_")
+        assert "abcdefgh1234" not in masked
+        assert "..." in masked
+
+    def test_short_secret_fully_masked(self):
+        assert mask_value("OBSIGATE_EXA_API_KEY", "abc") == "***"
+
+    def test_secret_detection(self):
+        assert is_secret_name("OBSIGATE_GITEA_TOKEN")
+        assert is_secret_name("OBSIGATE_TAVILY_API_KEY")
+        assert not is_secret_name("OBSIGATE_GITEA_URL")
+
+
+class TestToolKeysAPI:
+    def _login(self, admin_client):
+        resp = admin_client.post(
+            "/api/auth/login", json={"username": "admin", "password": "chab30"}
+        )
+        assert resp.status_code == 200, resp.text
+        token = resp.json()["access_token"]
+        return {"Authorization": f"Bearer {token}"}
+
+    def test_get_masks_tokens_shows_urls(self, admin_client, key_store):
+        headers = self._login(admin_client)
+        _write_store(key_store, {
+            "OBSIGATE_GITEA_URL": "https://git.example.net",
+            "OBSIGATE_GITHUB_TOKEN": "ghp_abcdefgh1234",
+        })
+        resp = admin_client.get("/api/config/tool-keys", headers=headers)
+        assert resp.status_code == 200
+        data = resp.json()
+        assert data["OBSIGATE_GITEA_URL"] == "https://git.example.net"
+        assert "abcdefgh1234" not in data["OBSIGATE_GITHUB_TOKEN"]
+        assert data["OBSIGATE_GITHUB_TOKEN"].startswith("ghp_")
+
+    def test_post_roundtrip_then_delete(self, admin_client, key_store):
+        headers = self._login(admin_client)
+        resp = admin_client.post(
+            "/api/config/tool-keys",
+            headers=headers,
+            json={"OBSIGATE_EXA_API_KEY": "exa-key-1234"},
+        )
+        assert resp.status_code == 200
+        assert resp.json()["status"] == "ok"
+        assert get_tool_key("OBSIGATE_EXA_API_KEY") == "exa-key-1234"
+
+        resp = admin_client.delete("/api/config/tool-keys/OBSIGATE_EXA_API_KEY", headers=headers)
+        assert resp.status_code == 200
+        assert resp.json()["status"] == "deleted"
+        assert get_tool_key("OBSIGATE_EXA_API_KEY") == ""
+
+    def test_post_unknown_name_rejected(self, admin_client, key_store):
+        headers = self._login(admin_client)
+        resp = admin_client.post(
+            "/api/config/tool-keys", headers=headers, json={"MY_SECRET": "x"}
+        )
+        assert resp.status_code == 400
+
+    def test_requires_admin(self, admin_client, key_store):
+        resp = admin_client.get("/api/config/tool-keys", headers={})
+        assert resp.status_code in (401, 403)

tests/test_web_cache.py

@@ -0,0 +1,82 @@
+"""Unit tests for the SQLite web cache (backend.tools.webcache, #92)."""
+
+import pytest
+
+from backend.tools import webcache
+
+
+@pytest.fixture
+def cache_enabled(tmp_path, monkeypatch):
+    """Enable the cache against an isolated file with a short TTL."""
+    monkeypatch.setenv("OBSIGATE_WEB_CACHE_PATH", str(tmp_path / "cache.sqlite3"))
+    monkeypatch.setenv("OBSIGATE_WEB_CACHE_TTL", "60")
+    webcache._schema_ready = False
+    yield
+    webcache._schema_ready = False
+
+
+class TestCacheKey:
+    def test_deterministic_and_payload_sensitive(self):
+        a = webcache.cache_key("search", {"q": "pizza", "page": 1})
+        b = webcache.cache_key("search", {"page": 1, "q": "pizza"})
+        c = webcache.cache_key("search", {"q": "pasta", "page": 1})
+        d = webcache.cache_key("fetch", {"q": "pizza", "page": 1})
+        assert a == b
+        assert a != c
+        assert a != d
+
+
+class TestCacheRoundTrip:
+    def test_set_get_roundtrip(self, cache_enabled):
+        key = webcache.cache_key("search", {"q": "x"})
+        webcache.cache_set(key, {"results": [1, 2, 3], "provider": "tavily"})
+        assert webcache.cache_get(key) == {"results": [1, 2, 3], "provider": "tavily"}
+
+    def test_miss_returns_none(self, cache_enabled):
+        assert webcache.cache_get("search:unknown") is None
+
+    def test_overwrite_updates_value(self, cache_enabled):
+        key = webcache.cache_key("search", {"q": "x"})
+        webcache.cache_set(key, {"v": 1})
+        webcache.cache_set(key, {"v": 2})
+        assert webcache.cache_get(key) == {"v": 2}
+
+    def test_ttl_expiry(self, tmp_path, monkeypatch):
+        monkeypatch.setenv("OBSIGATE_WEB_CACHE_PATH", str(tmp_path / "cache.sqlite3"))
+        monkeypatch.setenv("OBSIGATE_WEB_CACHE_TTL", "0.05")
+        webcache._schema_ready = False
+        key = webcache.cache_key("search", {"q": "x"})
+        webcache.cache_set(key, {"v": 1})
+        assert webcache.cache_get(key) == {"v": 1}
+        import time
+
+        time.sleep(0.15)
+        assert webcache.cache_get(key) is None
+
+    def test_disabled_when_ttl_zero(self, cache_enabled, monkeypatch):
+        monkeypatch.setenv("OBSIGATE_WEB_CACHE_TTL", "0")
+        key = webcache.cache_key("search", {"q": "x"})
+        webcache.cache_set(key, {"v": 1})
+        assert webcache.cache_get(key) is None
+
+    def test_purge_expired(self, cache_enabled, monkeypatch):
+        key = webcache.cache_key("search", {"q": "x"})
+        webcache.cache_set(key, {"v": 1})
+        monkeypatch.setenv("OBSIGATE_WEB_CACHE_TTL", "0.05")
+        import time
+
+        time.sleep(0.15)
+        assert webcache.purge_expired() >= 1
+        assert webcache.cache_get(key) is None
+
+    def test_corrupt_db_degrades_silently(self, tmp_path, monkeypatch):
+        # A directory as cache file breaks sqlite3.connect: the cache must
+        # disable itself instead of breaking the tools.
+        monkeypatch.setenv("OBSIGATE_WEB_CACHE_PATH", str(tmp_path))
+        monkeypatch.setenv("OBSIGATE_WEB_CACHE_TTL", "60")
+        webcache._schema_ready = False
+        try:
+            assert webcache.cache_get("search:x") is None
+            webcache.cache_set("search:x", {"v": 1})
+        finally:
+            webcache._schema_ready = False

tests/test_web_search_providers.py

@@ -0,0 +1,155 @@
+"""Unit tests for the keyed web-search providers (#92): Tavily, Brave,
+SerpAPI, Exa — plus provider ordering and the transient retry."""
+
+import httpx
+import pytest
+
+import backend.tools.web as web
+from backend.tools.context import ToolContext, ToolError, ToolMode
+
+
+class FakeResponse:
+    def __init__(self, json_data=None, status_code=200, content=b""):
+        self._json = json_data
+        self.status_code = status_code
+        self.content = content
+        self.encoding = "utf-8"
+        self.headers = {}
+
+    def json(self):
+        return self._json
+
+    def raise_for_status(self):
+        if self.status_code >= 400:
+            raise web.httpx.HTTPStatusError("boom", request=None, response=self)  # type: ignore[arg-type]
+
+
+def _ctx() -> ToolContext:
+    return ToolContext(user={"username": "tester", "vaults": []}, mode=ToolMode.IN_APP)
+
+
+def _no_fallback(monkeypatch):
+    """Limit the chain to the provider under test (no searxng/ddg/bing noise)."""
+    monkeypatch.setattr(web, "WEB_FALLBACK_ENABLED", False)
+    monkeypatch.setattr(web, "SEARXNG_URL", "http://searxng.invalid")
+    monkeypatch.setattr(web.httpx, "get", lambda *a, **kw: (_ for _ in ()).throw(
+        httpx.ConnectError("offline")))
+    monkeypatch.setattr(web.httpx, "post", lambda *a, **kw: (_ for _ in ()).throw(
+        httpx.ConnectError("offline")))
+
+
+class TestKeyedProviderParsers:
+    def test_tavily_maps_results(self, monkeypatch):
+        captured = {}
+
+        def fake_post(url, json=None, **kw):
+            captured["url"] = url
+            captured["payload"] = json
+            return FakeResponse(json_data={"results": [
+                {"title": "T", "url": "https://a.dev", "content": "c" * 800},
+            ]})
+
+        monkeypatch.setattr(web.httpx, "post", fake_post)
+        results, engines = web._search_tavily("q", web.WebSearchInput(query="q", max_results=3))
+        assert results[0]["title"] == "T"
+        assert len(results[0]["snippet"]) <= 600
+        assert engines == []
+        assert captured["payload"]["api_key"] == ""
+        assert captured["payload"]["max_results"] == 3
+
+    def test_brave_maps_results(self, monkeypatch):
+        captured = {}
+
+        def fake_get(url, params=None, headers=None, **kw):
+            captured["url"] = url
+            captured["headers"] = headers
+            return FakeResponse(json_data={"web": {"results": [
+                {"title": "B", "url": "https://b.dev", "description": "d"},
+            ]}})
+
+        monkeypatch.setattr(web.httpx, "get", fake_get)
+        results, _ = web._search_brave("q", web.WebSearchInput(query="q"))
+        assert results[0]["title"] == "B"
+        assert "api.search.brave.com" in str(captured["url"])
+
+    def test_serpapi_maps_results(self, monkeypatch):
+        monkeypatch.setattr(web.httpx, "get", lambda *a, **kw: FakeResponse(json_data={
+            "organic_results": [{"title": "S", "link": "https://s.dev", "snippet": "sn"}],
+        }))
+        results, _ = web._search_serpapi("q", web.WebSearchInput(query="q"))
+        assert results[0]["url"] == "https://s.dev"
+
+    def test_exa_maps_results(self, monkeypatch):
+        monkeypatch.setattr(web.httpx, "post", lambda *a, **kw: FakeResponse(json_data={
+            "results": [{"title": "E", "url": "https://e.dev", "text": "t" * 900}],
+        }))
+        results, _ = web._search_exa("q", web.WebSearchInput(query="q"))
+        assert results[0]["title"] == "E"
+        assert len(results[0]["snippet"]) <= 600
+
+
+class TestProviderChain:
+    def test_no_key_falls_back_to_searxng(self, monkeypatch):
+        for var in ("OBSIGATE_TAVILY_API_KEY", "OBSIGATE_BRAVE_API_KEY",
+                    "OBSIGATE_SERPAPI_API_KEY", "OBSIGATE_EXA_API_KEY"):
+            monkeypatch.delenv(var, raising=False)
+        chain = [name for name, _ in web._provider_chain()]
+        assert chain[0] == "searxng"
+        assert "tavily" not in chain
+
+    def test_keyed_provider_used_first_when_key_set(self, monkeypatch):
+        monkeypatch.setenv("OBSIGATE_TAVILY_API_KEY", "k")
+        chain = [name for name, _ in web._provider_chain()]
+        assert chain[0] == "tavily"
+        assert "brave" not in chain  # no key → skipped
+
+    def test_explicit_order_env(self, monkeypatch):
+        monkeypatch.setenv("OBSIGATE_TAVILY_API_KEY", "k")
+        monkeypatch.setenv("OBSIGATE_EXA_API_KEY", "k")
+        monkeypatch.setenv("OBSIGATE_WEB_PROVIDERS", "exa,unknown,tavily")
+        chain = [name for name, _ in web._provider_chain()]
+        assert chain[:2] == ["exa", "tavily"]
+
+    def test_search_uses_keyed_provider_first(self, monkeypatch):
+        _no_fallback(monkeypatch)
+        monkeypatch.setenv("OBSIGATE_BRAVE_API_KEY", "k")
+        monkeypatch.setattr(web.httpx, "get", lambda *a, **kw: FakeResponse(json_data={
+            "web": {"results": [{"title": "B", "url": "https://b.dev", "description": "d"}]},
+        }))
+        out = web.web_search(_ctx(), web.WebSearchInput(query="q"))
+        assert out["provider"] == "brave"
+        assert out["count"] == 1
+
+
+class TestRetry:
+    def test_transient_error_retried_then_succeeds(self, monkeypatch):
+        monkeypatch.setattr(web, "WEB_RETRY_ATTEMPTS", 1)
+        monkeypatch.setattr(web, "_provider_chain", lambda: [("searxng", web._search_searxng)])
+        calls = {"n": 0}
+
+        def flaky_get(*a, **kw):
+            calls["n"] += 1
+            if calls["n"] == 1:
+                raise httpx.ConnectError("blip")
+            return FakeResponse(json_data={"results": [
+                {"title": "A", "url": "https://a.dev", "content": "x"}]})
+
+        monkeypatch.setattr(web.httpx, "get", flaky_get)
+        out = web.web_search(_ctx(), web.WebSearchInput(query="q"))
+        assert out["provider"] == "searxng"
+        assert calls["n"] == 2
+
+    def test_persistent_error_not_retried_forever(self, monkeypatch):
+        monkeypatch.setattr(web, "WEB_RETRY_ATTEMPTS", 1)
+        monkeypatch.setattr(web, "_provider_chain", lambda: [("searxng", web._search_searxng)])
+        calls = {"n": 0}
+
+        def dead_get(*a, **kw):
+            calls["n"] += 1
+            raise httpx.ConnectError("down")
+
+        monkeypatch.setattr(web.httpx, "get", dead_get)
+        with pytest.raises(ToolError) as ei:
+            web.web_search(_ctx(), web.WebSearchInput(query="q"))
+        assert ei.value.code == "web_search_unavailable"
+        assert calls["n"] == 2  # initial + 1 retry, per provider

tests/test_webrender.py

@@ -0,0 +1,73 @@
+"""Unit tests for the dynamic rendering path (#92): fetch_url(render=True)."""
+
+import pytest
+
+import backend.tools.web as web
+from backend.tools import webrender
+from backend.tools.context import ToolContext, ToolError, ToolMode
+from backend.tools.registry import get_tool
+
+
+def _ctx() -> ToolContext:
+    return ToolContext(user={"username": "tester", "vaults": []}, mode=ToolMode.IN_APP)
+
+
+class TestRegistration:
+    def test_render_param_exposed_in_schema(self):
+        spec = get_tool("fetch_url")
+        assert spec is not None
+        assert "render" in spec.input_model.model_fields
+
+
+class TestRenderUnavailable:
+    def test_missing_playwright_clear_error(self, monkeypatch):
+        monkeypatch.setattr(webrender, "_playwright_available", lambda: False)
+        with pytest.raises(ToolError) as ei:
+            web.fetch_url(_ctx(), web.FetchUrlInput(
+                url="https://example.com/spa", render=True))
+        assert ei.value.code == "playwright_unavailable"
+
+    def test_ssrf_guard_applied_before_render(self, monkeypatch):
+        monkeypatch.setattr(webrender, "_playwright_available", lambda: True)
+        with pytest.raises(ToolError) as ei:
+            web.fetch_url(_ctx(), web.FetchUrlInput(
+                url="http://127.0.0.1:9222/devtools", render=True))
+        assert ei.value.code in ("ssrf_blocked", "dns_error")
+
+
+class TestRenderSuccess:
+    def test_fetch_url_delegates_to_worker(self, monkeypatch):
+        captured = {}
+
+        def fake_render(url):
+            captured["url"] = url
+            return {"url": url, "status": 200, "title": "SPA",
+                    "text": "dynamic content", "rendered": True, "truncated": False}
+
+        monkeypatch.setattr(webrender, "render_page", fake_render)
+        out = web.fetch_url(_ctx(), web.FetchUrlInput(
+            url="https://example.com/spa", render=True))
+        assert captured["url"] == "https://example.com/spa"
+        assert out["rendered"] is True
+        assert "dynamic content" in out["text"]
+
+    def test_worker_failure_maps_to_tool_error(self, monkeypatch):
+        monkeypatch.setattr(webrender, "_playwright_available", lambda: True)
+
+        def boom(url):
+            raise RuntimeError("chromium crashed")
+
+        # The executor re-raises the worker exception on .result(); render_page
+        # must wrap it into a ToolError instead of leaking a bare exception.
+        monkeypatch.setattr(webrender, "_render_in_worker", boom)
+        with pytest.raises(ToolError) as ei:
+            web.fetch_url(_ctx(), web.FetchUrlInput(
+                url="https://example.com/spa", render=True))
+        assert ei.value.code == "render_unavailable"
+
+
+class TestMarkdownExtraction:
+    def test_html_to_text_reused(self):
+        text = webrender._html_to_text("<html><body><p>hello</p><script>x()</script></body></html>")
+        assert "hello" in text
+        assert "x()" not in text