Merge pull request #94 from abinaze/fix/desktop-mode-chdir-writable-dir

fix: chdir into app-data dir at desktop startup, fixing 30+ writes at once

config/settings.py

@@ -182,6 +182,20 @@ MAX_RETRIES     = 3
 REQUEST_TIMEOUT = 30
 
 # Data paths
+# NOTE (P-1 finding, same shape as LOGS_PATH's own history before its fix):
+# these three constants are dead code -- grepped every consumer, zero hits
+# anywhere in the tree. All 30+ real writers/readers (19 scrapers' sample
+# fallback output, processing/pipeline.py, ai/multi_investigator.py,
+# ai/risk_scorer.py, ai/self_learning/schema_learner.py,
+# processing/alias_graph.py, graph/loader.py's glob read) hardcode their
+# own bare "data/processed/..." or "data/samples/..." string directly
+# instead. Unlike LOGS_PATH, these were NOT individually wired up to this
+# constant, because every one of them is genuinely CWD-relative (no
+# __file__-anchoring anywhere) -- so the actual desktop-mode fix is a
+# single os.chdir() into get_app_data_dir() in packaging/desktop_entry.py,
+# which redirects all 30+ of them at once with no per-file changes needed.
+# Left here as an accurate description of the intended folder layout, not
+# as something any code currently reads.
 DATA_RAW_PATH       = "data/raw/"
 DATA_PROCESSED_PATH = "data/processed/"
 DATA_SAMPLES_PATH   = "data/samples/"

packaging/desktop_entry.py

@@ -19,6 +19,30 @@ whenever the app is started this way, and so config/settings.py's local
 config-file loading is the primary configuration path a desktop user
 actually has, rather than a code path that only matters at packaging time.
 
+P-1 fix: also chdir()s into the OS-appropriate app-data directory before
+any other import. Grepped every bare (non-__file__-anchored) CWD-relative
+path in the codebase: 30+ real call sites across all 19 scrapers'
+data/samples/*.json sample-fallback output, processing/pipeline.py,
+ai/multi_investigator.py, ai/risk_scorer.py, ai/self_learning/
+schema_learner.py, processing/alias_graph.py, and graph/loader.py's own
+glob() read of pipeline output -- none of which reference the (equally
+dead) DATA_RAW_PATH/DATA_PROCESSED_PATH/DATA_SAMPLES_PATH constants in
+config/settings.py; each just hardcodes its own "data/processed/..." or
+"data/samples/..." string directly. On a real Windows install, a
+double-clicked app's CWD defaults to (and the install directory itself is
+typically read-only for) a non-admin user -- meaning every one of those
+30+ writes would fail outright, not just lose regeneratable cache data.
+Verified every one of them is genuinely CWD-relative (confirmed via
+direct testing that python-dotenv's own load_dotenv() calls elsewhere in
+the codebase are NOT affected by this, since dotenv resolves relative to
+the calling file's own frame, not CWD) -- so a single chdir() here fixes
+all 30+ call sites identically, with zero changes needed to any of them,
+rather than repeating the explicit per-file redirection this branch's
+sibling commits used for case_memory.json/logs/dossier output (which
+were __file__-anchored, not CWD-relative, and so could NOT have been
+fixed this way). Web-deployment behavior is unchanged -- this file is
+never imported by the Docker/app.py path.
+
 Binds to 127.0.0.1 only, matching the target architecture ("bound to
 127.0.0.1 only") -- this process is meant to be reached only by the Tauri
 shell's own webview (Phase D4), never by the network.
@@ -41,6 +65,15 @@ else:
     _app_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 sys.path.insert(0, _app_root)
 
+# P-1 fix: chdir into a guaranteed-writable directory before any other
+# import that might (transitively, later, at request time) write a bare
+# CWD-relative path. Must come after sys.path is set up (needs to import
+# config.settings) but before uvicorn/api.main are imported.
+from config.settings import get_app_data_dir
+_workdir = get_app_data_dir()
+os.makedirs(_workdir, exist_ok=True)
+os.chdir(_workdir)
+
 import uvicorn
 from api.main import app