WIP Phase 4 ingestion: platform guides, exclusion gate, gitea/vault/graph harvest, payload provenance

corpus/config.py

@@ -13,7 +13,7 @@ from dataclasses import dataclass
 
 # Bumped whenever chunk boundaries or payload shape change. A stored corpus
 # carrying a different version is stale by definition and gets rebuilt.
-CHUNKER_VERSION = "blocks-v1"
+CHUNKER_VERSION = "blocks-v2-code-v1"
 
 # Provider defaults. `local-hashing` is a deterministic, offline provider used
 # by the tests, by `make corpus-test`, and by any rebuild on a host with no
@@ -29,6 +29,14 @@ DEFAULT_QDRANT_URL = "http://127.0.0.1:6333"
 DEFAULT_COLLECTION = "resume_corpus"
 DEFAULT_PROVIDER = "local-hashing"
 DEFAULT_OMNIROUTE_URL = "https://omniroute.lab.audasmedia.com.au"
+DEFAULT_GITEA_URL = "https://gitea.lab.audasmedia.com.au"
+DEFAULT_PLATFORMS = ("gitea", "obsidian", "graphify")
+DEFAULT_GRAPH_COLLECTION = "resume_graph"
+
+# A source that has not changed in this window is reported by the audit. The
+# estate is active; silence is evidence that ingestion stopped, not that the
+# work stopped.
+DEFAULT_SOURCE_SILENCE_DAYS = 30
 
 # Freshness horizon: a document whose `last_verified` is older than this is
 # reported stale by the nightly audit. docs/phase-4-notes.md section 5.
@@ -60,6 +68,13 @@ class Config:
     max_age_days: int
     warn_days: int
     apprise_url: str
+    gitea_url: str = DEFAULT_GITEA_URL
+    gitea_token: str = ""
+    platforms: tuple = DEFAULT_PLATFORMS
+    offline: bool = False
+    graph_path: str = ""
+    graph_collection: str = DEFAULT_GRAPH_COLLECTION
+    source_silence_days: int = DEFAULT_SOURCE_SILENCE_DAYS
     vectors_on_disk: bool = False
 
     # -- construction -----------------------------------------------------
@@ -102,6 +117,19 @@ class Config:
             ),
             warn_days=int(os.environ.get("RESUME_WARN_DAYS") or DEFAULT_WARN_DAYS),
             apprise_url=os.environ.get("RESUME_APPRISE_URL") or "",
+            gitea_url=(os.environ.get("GITEA_URL") or os.environ.get("RESUME_GITEA_URL") or DEFAULT_GITEA_URL).rstrip("/"),
+            gitea_token=os.environ.get("GITEA_TOKEN") or "",
+            platforms=tuple(
+                part.strip()
+                for part in (os.environ.get("RESUME_PLATFORMS") or ",".join(DEFAULT_PLATFORMS)).split(",")
+                if part.strip()
+            ),
+            offline=(os.environ.get("RESUME_OFFLINE") or "").lower() in ("1", "true", "yes"),
+            graph_path=os.environ.get("RESUME_GRAPH_PATH") or "",
+            graph_collection=os.environ.get("RESUME_GRAPH_COLLECTION") or DEFAULT_GRAPH_COLLECTION,
+            source_silence_days=int(
+                os.environ.get("RESUME_SOURCE_SILENCE_DAYS") or DEFAULT_SOURCE_SILENCE_DAYS
+            ),
             vectors_on_disk=(os.environ.get("RESUME_QDRANT_VECTORS_ON_DISK") or "").lower()
             in ("1", "true", "yes"),
         )
@@ -124,6 +152,21 @@ class Config:
             )
         if not os.path.isdir(self.content_dir):
             raise ConfigError(f"content directory not found: {self.content_dir}")
+        unknown = [name for name in self.platforms if name not in ("gitea", "obsidian", "graphify")]
+        if unknown:
+            raise ConfigError(
+                f"RESUME_PLATFORMS contains unknown platform(s) {unknown}; "
+                "expected gitea, obsidian, graphify"
+            )
+        if not self.offline and self.gitea_token == "":
+            # Only a hard error when a platform that needs Gitea is selected; the
+            # token itself is never printed or stored.
+            if set(self.platforms) & {"gitea", "obsidian", "graphify"}:
+                raise ConfigError(
+                    "GITEA_TOKEN is not set. Harvesting needs read access to Gitea "
+                    "(~/.config/environment.d/10-secrets.conf), or set RESUME_OFFLINE=1 "
+                    "to rebuild only the curated tier."
+                )
 
     # -- presentation -----------------------------------------------------
 
@@ -140,7 +183,10 @@ class Config:
             f"batch={self.batch_size}\n"
             f"api_url={self.api_url} api_key={key}\n"
             f"freshness=max_age_days:{self.max_age_days} warn_days:{self.warn_days}\n"
-            f"qdrant vectors_on_disk={self.vectors_on_disk}\n"
+            f"estate=platforms:{','.join(self.platforms)} offline:{self.offline} "
+            f"gitea:{self.gitea_url} token:{'set' if self.gitea_token else 'unset'} "
+            f"graph_path:{self.graph_path or 'from gitea'} silence_days:{self.source_silence_days}\n"
+            f"qdrant vectors_on_disk={self.vectors_on_disk} graph_collection={self.graph_collection}\n"
             f"chunker={CHUNKER_VERSION}"
         )