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

2026-06-12 18:26:14 -04:00
parent 557994f7d9
commit 9e1a8ab7cb
23 changed files with 3133 additions and 197 deletions
@@ -0,0 +1,248 @@
+"""Tests for media downloads and Joplin resource rewriting."""
+
+from pathlib import Path
+
+import pytest
+
+from src.blocks import (
+    make_file_placeholder,
+    make_image_placeholder,
+    render_blocks_to_markdown,
+)
+from src.loss_report import LossReport
+from src.media import resolve_media, resolve_media_policy
+from src.providers.base import ProviderError
+from src.providers.chatgpt import parse_asset_file_id
+
+
+# ---------------------------------------------------------------------------
+# Asset reference parsing
+# ---------------------------------------------------------------------------
+
+
+class TestParseAssetFileId:
+    def test_plain_sediment(self):
+        assert parse_asset_file_id("sediment://file_00000000245c71fda5") == "file_00000000245c71fda5"
+
+    def test_generated_image_with_hash_and_page(self):
+        ref = "sediment://8456107fc383a53#file_00000000979c71f685#p_6.png"
+        assert parse_asset_file_id(ref) == "file_00000000979c71f685"
+
+    def test_file_service_scheme(self):
+        assert parse_asset_file_id("file-service://file-AbCdEf") == "file-AbCdEf"
+
+    def test_unrecognised(self):
+        assert parse_asset_file_id("https://example.com/x.png") is None
+        assert parse_asset_file_id("") is None
+        assert parse_asset_file_id(None) is None
+
+
+# ---------------------------------------------------------------------------
+# Media policy
+# ---------------------------------------------------------------------------
+
+
+class TestMediaPolicy:
+    def test_default(self, monkeypatch):
+        monkeypatch.delenv("EXPORTER_DOWNLOAD_MEDIA", raising=False)
+        assert resolve_media_policy() == "images"
+
+    def test_valid(self, monkeypatch):
+        monkeypatch.setenv("EXPORTER_DOWNLOAD_MEDIA", "all")
+        assert resolve_media_policy() == "all"
+
+    def test_invalid_falls_back(self, monkeypatch, caplog):
+        monkeypatch.setenv("EXPORTER_DOWNLOAD_MEDIA", "bogus")
+        assert resolve_media_policy() == "images"
+
+
+# ---------------------------------------------------------------------------
+# resolve_media
+# ---------------------------------------------------------------------------
+
+
+class _FakeProvider:
+    """Minimal provider exposing download_asset + the ref parser."""
+
+    def __init__(self, assets=None, fail_refs=None):
+        self._assets = assets or {}
+        self._fail_refs = fail_refs or {}
+        self.calls = []
+
+    def parse_asset_file_id(self, ref):
+        return parse_asset_file_id(ref)
+
+    def download_asset(self, ref):
+        self.calls.append(ref)
+        if ref in self._fail_refs:
+            raise ProviderError("chatgpt", "download_asset", self._fail_refs[ref])
+        return self._assets[ref]  # (content, mime, file_name)
+
+
+def _conv_with(blocks):
+    return {
+        "id": "conv-1",
+        "title": "Has Media",
+        "provider": "chatgpt",
+        "project": None,
+        "created_at": "2026-05-20T00:00:00+00:00",
+        "messages": [{"role": "user", "blocks": blocks}],
+    }
+
+
+class TestResolveMedia:
+    def test_downloads_image_and_inlines(self, tmp_path):
+        ref = "sediment://file_img1"
+        provider = _FakeProvider({ref: (b"\x89PNG\r\n", "image/png", "x.png")})
+        block = make_image_placeholder(ref=ref, source="user_upload")
+        conv = _conv_with([block])
+        report = LossReport()
+
+        n = resolve_media(conv, provider, tmp_path, "provider/project/year", "images", report)
+
+        assert n == 1
+        assert report.media_downloaded == 1
+        assert block["local_path"] == "media/file_img1.png"
+        rendered = render_blocks_to_markdown([block])
+        assert rendered == "![user_upload](media/file_img1.png)"
+        # File written under the conversation's media/ dir
+        written = list(tmp_path.rglob("media/file_img1.png"))
+        assert written and written[0].read_bytes() == b"\x89PNG\r\n"
+
+    def test_images_policy_skips_files(self, tmp_path):
+        ref = "sediment://file_audio1"
+        provider = _FakeProvider({ref: (b"RIFF", "audio/wav", "a.wav")})
+        block = make_file_placeholder(ref=ref, mime="audio/wav", size_bytes=1000)
+        conv = _conv_with([block])
+        report = LossReport()
+
+        n = resolve_media(conv, provider, tmp_path, "provider/project/year", "images", report)
+        assert n == 0
+        assert "local_path" not in block
+        assert provider.calls == []
+
+    def test_all_policy_downloads_files(self, tmp_path):
+        ref = "sediment://file_audio1"
+        provider = _FakeProvider({ref: (b"RIFFdata", "audio/wav", "a.wav")})
+        block = make_file_placeholder(ref=ref, mime="audio/wav", size_bytes=8)
+        conv = _conv_with([block])
+        report = LossReport()
+
+        n = resolve_media(conv, provider, tmp_path, "provider/project/year", "all", report)
+        assert n == 1
+        assert block["local_path"] == "media/file_audio1.wav"
+        rendered = render_blocks_to_markdown([block])
+        assert "media/file_audio1.wav" in rendered and rendered.startswith("> 📎")
+
+    def test_off_policy_noop(self, tmp_path):
+        provider = _FakeProvider({"sediment://file_x": (b"x", "image/png", None)})
+        block = make_image_placeholder(ref="sediment://file_x", source="user_upload")
+        conv = _conv_with([block])
+        report = LossReport()
+        assert resolve_media(conv, provider, tmp_path, "provider/project/year", "off", report) == 0
+        assert provider.calls == []
+
+    def test_idempotent_uses_disk(self, tmp_path):
+        ref = "sediment://file_img1"
+        provider = _FakeProvider({ref: (b"\x89PNG", "image/png", "x.png")})
+        conv = _conv_with([make_image_placeholder(ref=ref, source="user_upload")])
+        report = LossReport()
+        resolve_media(conv, provider, tmp_path, "provider/project/year", "images", report)
+        assert len(provider.calls) == 1
+
+        # Second run, fresh blocks: file already on disk → no new API call.
+        conv2 = _conv_with([make_image_placeholder(ref=ref, source="user_upload")])
+        resolve_media(conv2, provider, tmp_path, "provider/project/year", "images", LossReport())
+        assert len(provider.calls) == 1  # unchanged
+        assert conv2["messages"][0]["blocks"][0]["local_path"] == "media/file_img1.png"
+
+    def test_failure_keeps_placeholder_and_counts(self, tmp_path):
+        ref = "sediment://file_gone"
+        provider = _FakeProvider(fail_refs={ref: RuntimeError("Signed URL returned HTTP 404")})
+        block = make_image_placeholder(ref=ref, source="model_generated")
+        conv = _conv_with([block])
+        report = LossReport()
+
+        n = resolve_media(conv, provider, tmp_path, "provider/project/year", "images", report)
+        assert n == 0
+        assert "local_path" not in block
+        assert report.media_failed["expired-or-missing"] == 1
+        # Still renders as a placeholder, not a broken image link
+        assert render_blocks_to_markdown([block]).startswith("> 🖼️")
+
+    def test_provider_without_download_asset(self, tmp_path):
+        """claude-code has no remote assets — resolve_media must no-op."""
+        class NoDownload:
+            pass
+        block = make_image_placeholder(ref="sediment://file_x", source="user_upload")
+        conv = _conv_with([block])
+        assert resolve_media(conv, NoDownload(), tmp_path, "provider/project/year", "images", LossReport()) == 0
+
+
+# ---------------------------------------------------------------------------
+# Joplin media rewriting
+# ---------------------------------------------------------------------------
+
+
+class _FakeJoplin:
+    def __init__(self):
+        self.uploaded = []
+        self._n = 0
+
+    def create_resource(self, file_path, title=None):
+        self.uploaded.append(Path(file_path).name)
+        self._n += 1
+        return f"res{self._n}"
+
+
+class TestUploadMediaAndRewrite:
+    def _note(self, tmp_path, body):
+        media = tmp_path / "media"
+        media.mkdir()
+        (media / "file_img1.png").write_bytes(b"\x89PNG")
+        (media / "clip.wav").write_bytes(b"RIFF")
+        return body
+
+    def test_rewrites_image_and_file_links(self, tmp_path):
+        from src.joplin import upload_media_and_rewrite
+        body = self._note(
+            tmp_path,
+            "Look: ![user_upload](media/file_img1.png)\n"
+            "> 📎 **File attached** — [clip.wav](media/clip.wav) (audio/wav)",
+        )
+        client = _FakeJoplin()
+        new_body, res_map = upload_media_and_rewrite(body, tmp_path, client, {})
+
+        assert "![user_upload](:/res1)" in new_body
+        assert "(:/res2)" in new_body
+        assert "media/" not in new_body
+        assert res_map == {"media/file_img1.png": "res1", "media/clip.wav": "res2"}
+        assert len(client.uploaded) == 2
+
+    def test_reuses_known_resource_ids(self, tmp_path):
+        from src.joplin import upload_media_and_rewrite
+        body = self._note(tmp_path, "![x](media/file_img1.png)")
+        client = _FakeJoplin()
+        existing = {"media/file_img1.png": "existing-res"}
+        new_body, res_map = upload_media_and_rewrite(body, tmp_path, client, existing)
+        assert "(:/existing-res)" in new_body
+        assert client.uploaded == []  # no re-upload
+        assert res_map == existing
+
+    def test_missing_file_left_as_link(self, tmp_path):
+        from src.joplin import upload_media_and_rewrite
+        (tmp_path / "media").mkdir()
+        body = "![x](media/gone.png)"
+        client = _FakeJoplin()
+        new_body, res_map = upload_media_and_rewrite(body, tmp_path, client, {})
+        assert new_body == body
+        assert res_map == {}
+        assert client.uploaded == []
+
+    def test_no_media_links_untouched(self, tmp_path):
+        from src.joplin import upload_media_and_rewrite
+        body = "Just text with [a link](https://example.com) and `media/foo` in code."
+        client = _FakeJoplin()
+        new_body, res_map = upload_media_and_rewrite(body, tmp_path, client, {})
+        assert new_body == body
+        assert res_map == {}