feat: v0.6.0 — collapse policy, session limiter, Claude Code provider, prune, browser auth, media downloads

src/config.py

@@ -20,6 +20,12 @@ _CLAUDE_PLACEHOLDER = ""
 # Valid OUTPUT_STRUCTURE values
 VALID_STRUCTURES = {"provider/project/year", "provider/project", "provider/year"}
 
+# Valid EXPORTER_HIDDEN_CONTENT values (see src/providers/base.py)
+VALID_HIDDEN_CONTENT = {"full", "placeholder", "omit"}
+
+# Valid EXPORTER_DOWNLOAD_MEDIA values (see src/media.py)
+VALID_DOWNLOAD_MEDIA = {"images", "all", "off"}
+
 
 class ConfigError(Exception):
     """Raised when required configuration is missing or invalid."""
@@ -43,6 +49,16 @@ class Config:
     # Joplin local REST API settings (Web Clipper service)
     joplin_api_token: str | None = None
     joplin_api_url: str = "http://localhost:41184"
+    # Policy for content invisible in the provider web UI (retrieval dumps,
+    # hidden context): full | placeholder | omit
+    hidden_content: str = "placeholder"
+    # Session cap: max conversations downloaded per export run (None = unlimited).
+    # Every run is resumable, so a capped run just continues next time.
+    max_conversations: int | None = None
+    # Seconds between consecutive API requests (politeness pacing; 0 disables)
+    request_delay: float = 1.0
+    # Asset download policy: images | all | off
+    download_media: str = "images"
 
 
 def load_config() -> Config:
@@ -67,6 +83,12 @@ def load_config() -> Config:
     joplin_token = os.getenv("JOPLIN_API_TOKEN", "").strip() or None
     joplin_url = os.getenv("JOPLIN_API_URL", "http://localhost:41184").strip()
 
+    hidden_content = os.getenv("EXPORTER_HIDDEN_CONTENT", "").strip().lower() or "placeholder"
+
+    max_conversations_raw = os.getenv("MAX_CONVERSATIONS_PER_RUN", "").strip()
+    request_delay_raw = os.getenv("REQUEST_DELAY", "").strip()
+    download_media = os.getenv("EXPORTER_DOWNLOAD_MEDIA", "").strip().lower() or "images"
+
     # Parse CHATGPT_PROJECT_IDS — comma-separated list of gizmo IDs (g-p-xxx)
     _project_ids_raw = os.getenv("CHATGPT_PROJECT_IDS", "").strip()
     chatgpt_project_ids = [
@@ -90,6 +112,46 @@ def load_config() -> Config:
             f"Must be one of: {', '.join(sorted(VALID_STRUCTURES))}"
         )
 
+    # Validate hidden-content policy
+    if hidden_content not in VALID_HIDDEN_CONTENT:
+        errors.append(
+            f"EXPORTER_HIDDEN_CONTENT '{hidden_content}' is invalid. "
+            f"Must be one of: {', '.join(sorted(VALID_HIDDEN_CONTENT))}"
+        )
+
+    # Validate media download policy
+    if download_media not in VALID_DOWNLOAD_MEDIA:
+        errors.append(
+            f"EXPORTER_DOWNLOAD_MEDIA '{download_media}' is invalid. "
+            f"Must be one of: {', '.join(sorted(VALID_DOWNLOAD_MEDIA))}"
+        )
+
+    # Validate session cap
+    max_conversations: int | None = None
+    if max_conversations_raw:
+        try:
+            max_conversations = int(max_conversations_raw)
+        except ValueError:
+            errors.append(
+                f"MAX_CONVERSATIONS_PER_RUN '{max_conversations_raw}' is not an integer."
+            )
+        else:
+            if max_conversations < 1:
+                errors.append(
+                    f"MAX_CONVERSATIONS_PER_RUN must be at least 1 (got {max_conversations})."
+                )
+
+    # Validate request pacing
+    request_delay = 1.0
+    if request_delay_raw:
+        try:
+            request_delay = float(request_delay_raw)
+        except ValueError:
+            errors.append(f"REQUEST_DELAY '{request_delay_raw}' is not a number.")
+        else:
+            if request_delay < 0:
+                errors.append(f"REQUEST_DELAY must be >= 0 (got {request_delay}).")
+
     # Validate and decode ChatGPT JWT
     chatgpt_expiry: datetime | None = None
     if chatgpt_token:
@@ -139,6 +201,10 @@ def load_config() -> Config:
         chatgpt_project_ids=chatgpt_project_ids,
         joplin_api_token=joplin_token,
         joplin_api_url=joplin_url,
+        hidden_content=hidden_content,
+        max_conversations=max_conversations,
+        request_delay=request_delay,
+        download_media=download_media,
     )
 
     _log_startup_summary(config)
@@ -223,7 +289,11 @@ def _log_startup_summary(cfg: Config) -> None:
         "Joplin: %s | "
         "export_dir=%s | "
         "structure=%s | "
-        "cache_dir=%s",
+        "cache_dir=%s | "
+        "hidden_content=%s | "
+        "max_conversations=%s | "
+        "request_delay=%.1fs | "
+        "download_media=%s",
         chatgpt_status,
         claude_status,
         len(cfg.chatgpt_project_ids),
@@ -231,4 +301,8 @@ def _log_startup_summary(cfg: Config) -> None:
         cfg.export_dir,
         cfg.output_structure,
         cfg.cache_dir,
+        cfg.hidden_content,
+        cfg.max_conversations if cfg.max_conversations is not None else "unlimited",
+        cfg.request_delay,
+        cfg.download_media,
     )