v0.19.0 backend: /api/docs/sessions/* endpoints + TTL cache

Adds the four read endpoints the v0.19.0 /docs/sessions/* surface mounts on top of: - GET /api/docs/sessions/manifest → sessions.json (title map) - GET /api/docs/sessions/about → README.md - GET /api/docs/sessions/<NNNN>/index → per-session transcript list - GET /api/docs/sessions/<NNNN>/<file> → transcript body The framework mediates the gitea fetch so the rendered surface inherits the same chrome as the v0.14.0 /docs route and the browser makes no cross-origin call. Reads are aggressively cached in-process (60s for the manifest, 5min for content) so the framework doesn't hammer git.wiggleverse.org under normal traffic. Negative results (gitea 404) are also cached at the content TTL to absorb the expected empty-state at deploy-time (the parallel ohm-session-history repo restructure ships in driver subsession 0017.2). All four endpoints are anonymous-reachable, sibling to /api/philosophy and /api/docs. Path validation gates the network: only /^\d{4}$/ session dirs and the full SESSION-NNNN.M-TRANSCRIPT-...md filename shape pass to the upstream. Legacy flat-root names (e.g. SESSION-A-TRANSCRIPT.md) and path-traversal attempts are rejected 400 before any fetch. 18 new tests cover the happy paths, 404 empty-states, 502 upstream errors, path-validation rejections, and the cache-hit-within-TTL contract. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-28 09:07:01 -07:00
parent ac3513a686
commit 39e57706d9
3 changed files with 855 additions and 0 deletions
@@ -0,0 +1,379 @@
+"""v0.19.0 / roadmap item #30 — `/api/docs/sessions/*` endpoints.
+
+The framework mediates reads against the public
+`wiggleverse/ohm-session-history` gitea repo so the rendered
+`/docs/sessions/*` surface inherits the same chrome as `/docs/user-guide`.
+This test suite covers the four endpoints + the in-process TTL cache,
+mocking the upstream HTTP via `httpx.MockTransport` (the same shape the
+rest of the test suite uses for Gitea).
+
+The tests do NOT spin up the full FakeGitea — they only need to mock
+the gitea raw URL surface (and the contents API for the session-index
+endpoint). Each test owns its mock transport so we can dial in 200 /
+404 / 5xx / timeout responses per case.
+
+Path-validation tests intentionally bypass the network — a malformed
+`nnnn` or `filename` MUST be rejected at the route layer before any
+upstream call is made.
+"""
+from __future__ import annotations
+
+import json
+
+import httpx
+import pytest
+from fastapi.testclient import TestClient
+
+from app import docs_sessions
+
+# Reuse the proven app-construction fixtures from the proposal vertical
+# (same shape every test file in this repo uses).
+from test_propose_vertical import (  # noqa: F401
+    app_with_fake_gitea,
+    tmp_env,
+)
+
+
+# ---------------------------------------------------------------------------
+# Test scaffolding
+# ---------------------------------------------------------------------------
+
+
+class _UpstreamHandler:
+    """Records every URL the docs_sessions module fetched and returns
+    canned responses keyed by URL substring. Allows the test to assert
+    on call count (for cache verification) without needing a full Gitea
+    simulator.
+
+    `calls` tracks only URLs that hit the session-history host (the
+    `OHM_SESSION_HISTORY_*` bases) so reconciler/Gitea-side calls — which
+    also pass through this handler because `httpx.AsyncClient` is a
+    shared attribute the gitea-side fixture also monkeypatches — don't
+    inflate the count we use for cache-hit assertions.
+    """
+
+    _SESSION_HOST_MARKERS = ("ohm-session-history", "wiggleverse/ohm-session-history")
+
+    def __init__(self, responses: dict[str, tuple[int, str]]):
+        self.responses = responses
+        self.calls: list[str] = []
+
+    def __call__(self, request: httpx.Request) -> httpx.Response:
+        url = str(request.url)
+        if any(m in url for m in self._SESSION_HOST_MARKERS):
+            self.calls.append(url)
+        for key, (status, body) in self.responses.items():
+            if key in url:
+                return httpx.Response(status, text=body)
+        # Default: 404. Lets tests skip declaring "the rest is 404".
+        return httpx.Response(404, text="not found")
+
+
+@pytest.fixture
+def patched_httpx(monkeypatch):
+    """Provide a hook the test can call to install a MockTransport.
+
+    Returns a closure: `install(handler)` patches
+    `app.docs_sessions.httpx.AsyncClient` so every constructed client
+    uses the handler's transport.
+
+    NB: the upstream `app_with_fake_gitea` fixture also patches
+    `httpx.AsyncClient` (to route gitea calls to a FakeGitea handler),
+    and because `httpx` is a single shared module, that patch mutates
+    the *same* `AsyncClient` attribute we're about to overwrite. We
+    therefore import the unpatched class directly from the
+    `httpx._client` module so our install path can construct a fresh
+    real client around our MockTransport without going through the
+    FakeGitea wrapper.
+    """
+    from httpx._client import AsyncClient as RealAsyncClient
+
+    def install(handler):
+        def patched(*args, **kwargs):
+            kwargs["transport"] = httpx.MockTransport(handler)
+            return RealAsyncClient(*args, **kwargs)
+
+        monkeypatch.setattr("app.docs_sessions.httpx.AsyncClient", patched)
+        return handler
+
+    yield install
+
+
+@pytest.fixture
+def app(app_with_fake_gitea):
+    """Wrap the shared app fixture, resetting the docs-sessions cache so
+    cross-test state can't leak. Returns just the FastAPI app — the
+    fake-Gitea handle is irrelevant for the docs-sessions surface.
+    """
+    docs_sessions.reset_cache()
+    fastapi_app, _fake = app_with_fake_gitea
+    return fastapi_app
+
+
+# ---------------------------------------------------------------------------
+# Manifest endpoint
+# ---------------------------------------------------------------------------
+
+
+def test_manifest_happy_path(app, patched_httpx):
+    manifest_body = json.dumps(
+        {
+            "0001": {"title": "Bootstrap"},
+            "0014": {"title": "Wave 7 driver"},
+        }
+    )
+    patched_httpx(
+        _UpstreamHandler({"sessions.json": (200, manifest_body)})
+    )
+    with TestClient(app) as client:
+        r = client.get("/api/docs/sessions/manifest")
+        assert r.status_code == 200, r.text
+        payload = r.json()
+        assert payload == {
+            "0001": {"title": "Bootstrap"},
+            "0014": {"title": "Wave 7 driver"},
+        }
+
+
+def test_manifest_empty_state(app, patched_httpx):
+    """A 404 from gitea means the manifest hasn't been published yet.
+    The endpoint returns HTTP 200 + `{}` so the frontend can render the
+    no-sessions-yet state without an error banner.
+    """
+    patched_httpx(_UpstreamHandler({"sessions.json": (404, "not found")}))
+    with TestClient(app) as client:
+        r = client.get("/api/docs/sessions/manifest")
+        assert r.status_code == 200, r.text
+        assert r.json() == {}
+
+
+def test_manifest_upstream_5xx_returns_502(app, patched_httpx):
+    patched_httpx(_UpstreamHandler({"sessions.json": (500, "internal")}))
+    with TestClient(app) as client:
+        r = client.get("/api/docs/sessions/manifest")
+        assert r.status_code == 502, r.text
+        body = r.json()
+        assert body["detail"]["error"] == "session-history fetch failed"
+
+
+# ---------------------------------------------------------------------------
+# About endpoint
+# ---------------------------------------------------------------------------
+
+
+def test_about_happy_path(app, patched_httpx):
+    readme = "# OHM session history\n\nWelcome.\n"
+    patched_httpx(_UpstreamHandler({"README.md": (200, readme)}))
+    with TestClient(app) as client:
+        r = client.get("/api/docs/sessions/about")
+        assert r.status_code == 200, r.text
+        assert "text/markdown" in r.headers["content-type"]
+        assert r.text == readme
+
+
+def test_about_404(app, patched_httpx):
+    patched_httpx(_UpstreamHandler({"README.md": (404, "")}))
+    with TestClient(app) as client:
+        r = client.get("/api/docs/sessions/about")
+        assert r.status_code == 404, r.text
+
+
+def test_about_upstream_5xx_returns_502(app, patched_httpx):
+    patched_httpx(_UpstreamHandler({"README.md": (503, "down")}))
+    with TestClient(app) as client:
+        r = client.get("/api/docs/sessions/about")
+        assert r.status_code == 502, r.text
+
+
+# ---------------------------------------------------------------------------
+# Transcript endpoint
+# ---------------------------------------------------------------------------
+
+
+def test_transcript_happy_path(app, patched_httpx):
+    body = "# Session 0017.1 — Transcript\n\nbody.\n"
+    fname = "SESSION-0017.1-TRANSCRIPT-2026-05-28T08-50--2026-05-28T11-20.md"
+    patched_httpx(_UpstreamHandler({fname: (200, body)}))
+    with TestClient(app) as client:
+        r = client.get(f"/api/docs/sessions/0017/{fname}")
+        assert r.status_code == 200, r.text
+        assert "text/markdown" in r.headers["content-type"]
+        assert r.text == body
+
+
+def test_transcript_404(app, patched_httpx):
+    fname = "SESSION-9999.0-TRANSCRIPT-2026-01-01T00-00--2026-01-01T00-01.md"
+    patched_httpx(_UpstreamHandler({}))  # everything 404s
+    with TestClient(app) as client:
+        r = client.get(f"/api/docs/sessions/9999/{fname}")
+        assert r.status_code == 404, r.text
+
+
+def test_transcript_rejects_invalid_session_dir(app, patched_httpx):
+    """`nnnn` must be exactly 4 digits. `abcd` fails before any
+    network call.
+    """
+    handler = _UpstreamHandler({})
+    patched_httpx(handler)
+    with TestClient(app) as client:
+        r = client.get(
+            "/api/docs/sessions/abcd/"
+            "SESSION-0001.0-TRANSCRIPT-2026-01-01T00-00--2026-01-01T00-01.md"
+        )
+        assert r.status_code == 400, r.text
+    assert handler.calls == [], "rejected path must not hit the network"
+
+
+def test_transcript_rejects_path_traversal(app, patched_httpx):
+    """A filename that doesn't match the SESSION-NNNN.M-TRANSCRIPT regex
+    is rejected. `../etc/passwd` doesn't match; neither does the legacy
+    flat-root `SESSION-A-TRANSCRIPT.md`.
+    """
+    handler = _UpstreamHandler({})
+    patched_httpx(handler)
+    with TestClient(app) as client:
+        # Path traversal — but FastAPI normalizes `..` in the path before
+        # routing, so this resolves to /api/docs/sessions/0001/etc/passwd
+        # which routes to the same handler with filename=etc/passwd, and
+        # gets rejected as an invalid transcript filename. Even if the
+        # normalization didn't apply (some intermediary), the regex
+        # check rejects anything not matching the SESSION- prefix.
+        r = client.get(
+            "/api/docs/sessions/0001/etc%2Fpasswd"
+        )
+        # 400 (filename validation) or 404 (path didn't match the
+        # route); both reject before any network call. Either is
+        # acceptable — what matters is that we never fetched it.
+        assert r.status_code in (400, 404), r.text
+    assert handler.calls == [], "rejected path must not hit the network"
+
+
+def test_transcript_rejects_legacy_flat_filename(app, patched_httpx):
+    """Legacy `SESSION-A-TRANSCRIPT.md` (letter form) doesn't match the
+    numeric regex — by design, since post-#23 transcripts live in
+    `NNNN/` folders with numeric names. Reject 400.
+    """
+    handler = _UpstreamHandler({})
+    patched_httpx(handler)
+    with TestClient(app) as client:
+        r = client.get("/api/docs/sessions/0001/SESSION-A-TRANSCRIPT.md")
+        assert r.status_code == 400, r.text
+    assert handler.calls == [], "rejected path must not hit the network"
+
+
+def test_transcript_upstream_5xx_returns_502(app, patched_httpx):
+    fname = "SESSION-0001.0-TRANSCRIPT-2026-01-01T00-00--2026-01-01T00-01.md"
+    patched_httpx(_UpstreamHandler({fname: (502, "bad gateway")}))
+    with TestClient(app) as client:
+        r = client.get(f"/api/docs/sessions/0001/{fname}")
+        assert r.status_code == 502, r.text
+
+
+# ---------------------------------------------------------------------------
+# Session-index endpoint
+# ---------------------------------------------------------------------------
+
+
+def test_session_index_happy_path(app, patched_httpx):
+    """The contents API returns a JSON list of file entries. The
+    endpoint filters to entries that match the transcript regex and
+    sorts them.
+    """
+    # Two transcripts (driver + subagent) + a non-transcript sibling
+    # that must be filtered out.
+    listing = json.dumps(
+        [
+            {
+                "name": "SESSION-0017.0-TRANSCRIPT-"
+                "2026-05-28T08-30--2026-05-28T12-00.md",
+                "type": "file",
+            },
+            {
+                "name": "SESSION-0017.1-TRANSCRIPT-"
+                "2026-05-28T08-50--2026-05-28T11-20.md",
+                "type": "file",
+            },
+            {"name": "notes.md", "type": "file"},  # not a transcript
+            {"name": "attached-dir", "type": "dir"},  # not a file
+        ]
+    )
+    patched_httpx(_UpstreamHandler({"/contents/0017": (200, listing)}))
+    with TestClient(app) as client:
+        r = client.get("/api/docs/sessions/0017/index")
+        assert r.status_code == 200, r.text
+        files = r.json()["files"]
+        assert files == [
+            "SESSION-0017.0-TRANSCRIPT-2026-05-28T08-30--2026-05-28T12-00.md",
+            "SESSION-0017.1-TRANSCRIPT-2026-05-28T08-50--2026-05-28T11-20.md",
+        ]
+
+
+def test_session_index_404(app, patched_httpx):
+    patched_httpx(_UpstreamHandler({}))  # everything 404s
+    with TestClient(app) as client:
+        r = client.get("/api/docs/sessions/9999/index")
+        assert r.status_code == 404, r.text
+
+
+def test_session_index_rejects_invalid_session_dir(app, patched_httpx):
+    handler = _UpstreamHandler({})
+    patched_httpx(handler)
+    with TestClient(app) as client:
+        r = client.get("/api/docs/sessions/abc/index")
+        assert r.status_code == 400, r.text
+    assert handler.calls == [], "rejected path must not hit the network"
+
+
+# ---------------------------------------------------------------------------
+# Cache behavior
+# ---------------------------------------------------------------------------
+
+
+def test_manifest_cache_hits_within_ttl(app, patched_httpx, monkeypatch):
+    """Two consecutive manifest calls within the TTL window should
+    issue exactly one HTTP request to gitea.
+    """
+    # Generous TTL so the test never races.
+    monkeypatch.setenv("OHM_DOCS_SESSIONS_MANIFEST_TTL_SEC", "60")
+    handler = _UpstreamHandler(
+        {"sessions.json": (200, json.dumps({"0001": {"title": "x"}}))}
+    )
+    patched_httpx(handler)
+    with TestClient(app) as client:
+        r1 = client.get("/api/docs/sessions/manifest")
+        r2 = client.get("/api/docs/sessions/manifest")
+    assert r1.status_code == 200
+    assert r2.status_code == 200
+    assert len(handler.calls) == 1, (
+        f"expected one upstream call, got {handler.calls}"
+    )
+
+
+def test_transcript_cache_hits_within_ttl(app, patched_httpx, monkeypatch):
+    monkeypatch.setenv("OHM_DOCS_SESSIONS_CONTENT_TTL_SEC", "300")
+    fname = "SESSION-0001.0-TRANSCRIPT-2026-01-01T00-00--2026-01-01T00-01.md"
+    handler = _UpstreamHandler({fname: (200, "# body\n")})
+    patched_httpx(handler)
+    with TestClient(app) as client:
+        r1 = client.get(f"/api/docs/sessions/0001/{fname}")
+        r2 = client.get(f"/api/docs/sessions/0001/{fname}")
+    assert r1.status_code == 200
+    assert r2.status_code == 200
+    assert len(handler.calls) == 1
+
+
+def test_transcript_404_is_cached(app, patched_httpx, monkeypatch):
+    """Negative caching: a 404 result is cached at the content TTL so a
+    deployment with no published transcripts doesn't hammer gitea on
+    every navigation. Documented in `docs_sessions.fetch_transcript`.
+    """
+    monkeypatch.setenv("OHM_DOCS_SESSIONS_CONTENT_TTL_SEC", "300")
+    fname = "SESSION-9999.0-TRANSCRIPT-2026-01-01T00-00--2026-01-01T00-01.md"
+    handler = _UpstreamHandler({})  # everything 404s
+    patched_httpx(handler)
+    with TestClient(app) as client:
+        r1 = client.get(f"/api/docs/sessions/9999/{fname}")
+        r2 = client.get(f"/api/docs/sessions/9999/{fname}")
+    assert r1.status_code == 404
+    assert r2.status_code == 404
+    assert len(handler.calls) == 1, "negative caching should suppress the 2nd call"