Replace the single [llm] block in settings.toml with a curated catalog
of LLM "backends" (provider + model + sampling params + system prompt)
in server/src/analyze/backend.rs. Two backends ship initially:
gpt_oss_120b (default, reasoning_effort=medium) and llama_3_1_405b
(uses response_format: json_schema to sidestep the <|eot_id|> leak).
The case page now renders one submit button per available backend; the
clicked button's name=backend value rides through AnalysisInput.backend_id
to the worker, which looks it up via find_backend() with default fallback.
A submitted unknown backend id is rejected as 400. .analysis_failed.json
records the failed backend and the failure banner surfaces its label.
The API key now comes from IONOS_API_KEY (env), not settings.toml; the
[llm] section is read into a discarded field so old configs still load.
Backends without a satisfied requires_api_key are filtered from the UI
(any_backend_available()). Three end-to-end tests that mocked the LLM
endpoint via settings.llm.url are #[ignore]'d with a clear note — they
need per-test backend injection (Arc<Vec<LlmBackend>> through the worker)
before they can be re-enabled.
Replaces the `.transcript.txt` sidecar with a structured `.json` file
for recording metadata. This change consolidates transcript text,
duration, and other potential metadata into a single, extensible JSON
object.
This also refactors the `TranscriptState` enum to better represent the
on-disk state (absence of file means pending) and the in-memory
representation. The `Transcript` enum now specifically models the
terminal outcomes of the transcriber (`Silent` or `Content`).
The commit includes updates to documentation, data structures, path
handling, and various tests to align with the new metadata format.
Config sheds its 14 Bucket-B fields (retention, whisper, ollama, llm) and
gains a sibling Arc<Settings> in AppState, loaded from settings.toml at
startup via Settings::load_or_default. Workers (transcribe, analyze,
recovery, auto_trigger) and routes (health, bulk, case_actions,
user_web) take settings as a separate parameter or State<> extractor;
Config::llm_configured moves to Settings::llm_configured.
TestConfig::build_pair() returns (Arc<Config>, Arc<Settings>); the new
create_router_with_settings / create_router_and_session_store_with_settings
helpers wire both into integration tests that exercise LLM/Whisper/Ollama.
The legacy single-Arc create_router falls back to Settings::default()
so the 17 non-LLM tests stay untouched.
Verified: cargo build clean, clippy --all-targets clean, 318 tests pass.
Consolidate the sticky-Manual rule for oneliner.json into a single
helper paths::delete_oneliner_unless_manual that holds the per-case
lock, reads the state, keeps OnelinerState::Manual, and removes any
LLM-derived variant. Three previously-direct deletion paths now route
through it: handle_delete_recording, reset_case_artefacts (admin
single-reset), and bulk_reset (admin bulk action). Before this fix a
clinician's manual override was wiped by a recording delete, letting
the LLM auto-regen path overwrite it on the next view.
Tests: 4 unit tests for the wrapper contract, integration tests for
the recording-delete and case-reset endpoints (Manual preserved,
Ready wiped), and a static-scan invariant that fails on direct
remove_file(... ONELINER_FILENAME) calls outside paths.rs.
- Replace native confirm() in the recording list with an inline
two-step confirm row; hide the player via visibility:hidden
while open so the row height stays stable.
- Hard-redirect recording delete back to /web/cases/{id}/recordings
instead of relying on the Referer header (which silently fell
back to /web/cases when stripped).
- Switch analyze/reset to a hidden return_to form field so the
source page (case detail vs. case list) is preserved reliably,
with same-origin /web/ prefix validation.
- Tighten delete_recording_test on the concrete Location header;
adjust analyze/reset redirect expectations to the new
case-detail fallback.
Introduces CsrfForm<T>: a FromRequest extractor that looks up the
session's csrf_token and constant-time-compares it to a csrf_token
field in the form body. Drop-in replacement for Form<T> on every
state-changing /web/ POST handler. Missing or expired session →
redirect to /web/login; malformed body → 400; token mismatch → 403.
WebSession carries csrf_token, minted alongside the session token at
login and magic-link consume. Not rotated per request — rotation
would break multi-tab use and buys little over SameSite=Strict
cookies.
Handlers: bulk, purge-closed, reset, close, reopen, analyze,
delete-recording, logout all now require CsrfForm<_>. Login stays
unprotected (SameSite=Strict alone is sufficient — forced-login CSRF
has no impact on this codebase). /api/... is header-auth, exempt.
Constant-time compare via subtle::ConstantTimeEq avoids timing
oracles on the token.
Template work is NOT in this commit — browser forms still post
without csrf_token, so the live web UI will 403 until Schritt 6
(templates render the hidden field).
Tests: all 12 red specs in csrf_attack_test.rs now green, #[ignore]
removed. Integration tests that POSTed to protected endpoints
switched to a new create_router_and_session_store entrypoint which
returns a handle to the store so tests can read csrf_token for the
active session.
Move admin checks from individual bulk actions to the main handler for
`bulk.rs` and `case_actions.rs`. This consolidates the authorization
logic for these sensitive operations.
Additionally, refine the HTML template to conditionally render bulk
action UI elements and the purge form only when the user is an admin.
This ensures that non-admin users do not see or have access to these
administrative functions.
Update tests to reflect these changes, ensuring that non-admin users are
correctly rejected for these actions and that the UI is properly hidden.
Introduce `TranscriptState { Pending, Silent, Content }` in
doctate-common as the canonical three-way state of a recording's
`.transcript.txt` sidecar. Previously each call-site projected the
raw `Option<String>` / `.exists()` onto its own 2-state view and the
projections disagreed: the UI treated a 0-byte silent transcript like
`Content` while the oneliner worker treated it like `Pending`,
leaving silent-only cases stuck on "generiere Titel …" forever with
no persisted oneliner.json.
`update_oneliner` now settles a silent-only case to
`OnelinerState::Empty` when no `Content` transcript exists and no
recording is still `Pending`, so the UI resolves to "unbenannt" and
recovery treats it as terminal.
Single reader: `paths::read_transcript_state`. All call-sites
(scan_recordings, compute_oneliner_display, has_pending_recordings,
all_transcripts_joined, read_recordings, enqueue_pending_for_user,
scan_m4as, cases_needing_oneliner_in, case_recordings.html) go
through the same typed abstraction and must handle `Silent` via
exhaustive match.
Regression tests:
- silent_case_empty_test: heal path settles silent-only case to
Empty without calling Ollama
- case_page_silent_only_shows_empty_not_generating: UI renders
"unbenannt", not "generiere Titel …"
Three UX polish items for the show-closed listing, grouped because
they are the same root problem in three surfaces:
* handle_reopen_case now redirects via resolve_return_path(&headers)
instead of hard-coding /web/cases, so a reopen from the
?show_closed=1 listing stays in that view. Matches the pattern
already used by analyze/reset/delete-recording.
* handle_close_case now redirects via the new helper
resolve_list_return_path(&headers), which wraps resolve_return_path
and additionally collapses a /web/cases/{uuid} detail path to
/web/cases while keeping the query string. A close from the detail
page previously would have tried to redirect back to the now-404
detail, or when triggered from ?show_closed=1 would have dropped
the query.
* Closed cases in my_cases.html now render the checkbox,
Analysieren/Neu analysieren and Reset controls in disabled state
instead of being hidden. Layout stays consistent with mixed-state
listings, and the user can see what actions would be available
after reopen. The handlers remain the authoritative guard via
locate_case_or_404 -> 404 for closed cases, so the HTML disabled
is a hint only.
Adds four unit tests for resolve_list_return_path and two integration
tests for the new redirect behaviour (close from listing with query,
close from detail with query).
Iterates the user's data dir and removes every case directory that
carries a .closed marker. Requires form field confirm=yes as a server-
side guard against accidental browser-history re-POSTs. Emits CasePurged
per successfully removed case; per-case failures are logged but do not
abort the sweep.
UI button is deferred to the show-closed step so the endpoint is only
reachable after an explicit navigation. Three integration tests cover
the happy path, missing-confirm, and coexistence with open cases.
- POST /web/cases/:id/delete renamed to /close; emits CaseClosed.
- New POST /web/cases/:id/reopen removes the marker; emits CaseReopened.
- Bulk action "delete" renamed to "close"; the shared closed_at timestamp
still groups the selection for future UI features.
- POST /web/cases/undo-delete removed along with summarize_latest_close_group,
latest_close_timestamp and restore_close_group. Per-case reopen makes
the group-undo banner obsolete.
- CaseEventKind::CaseDeleted -> CaseClosed, CaseRestored -> CaseReopened.
- Templates updated to Lucide trash-2 icon, German label "Fall schliessen".
- Tests migrated; delete_watermark_test.rs moved to close_watermark_test.rs.
Internal rename: DELETE_MARKER -> CLOSE_MARKER, DeleteMarker ->
CloseMarker, is_deleted -> is_closed. The batch UUID is dropped;
undo now groups cases by their exact closed_at timestamp, which
bulk-close writes identically across its selection while per-case
close writes a unique stamp.
Behavior unchanged. No migration (project is pre-production);
legacy .deleted files in tmpdata were removed manually.
This commit introduces a new API endpoint for deleting recordings. The
endpoint
handles the removal of the audio file and its associated sidecar files
(transcript,
duration). It also invalidates derived artifacts like oneliner.json,
document.md,
and analysis_input.json. Additionally, it includes checks for path
traversal,
correct file extensions, and case ownership to ensure security and data
integrity.
A new `RecordingDeleted` event is also added to the `CaseEventKind`
enum.
Introduced a new macro `render` in `partials/oneliner.html` to handle
the display of the oneliner for cases. This macro encapsulates the logic
for rendering the oneliner, including states for ready, empty, error,
pending, and generating.
The `case_page.html` and `my_cases.html` templates are updated to use
this new macro. This refactoring centralizes the oneliner rendering
logic, making it more maintainable and consistent across different
views.
Additionally, the `OnelinerDisplay` enum is now used in
`CasePageTemplate` and `MyCasesTemplate` to represent the different
states of the oneliner, improving type safety and clarity.
The oneliner is now stored as `OnelinerState` enum which can represent
three states: `Ready`, `Empty` or `Error`. This allows the client to
differentiate between a case with no medical content and a case where
the oneliner generation failed.
The `OnelinerState` enum is serialized to JSON and stored in
`oneliner.json` file. The `OnelinerEntry` struct has been updated to
reflect this change.
The client-desktop application has been updated to handle the new
`OnelinerState` enum and display appropriate UI elements for each state.
The server-side code has also been updated to read and write the
`OnelinerState` enum, and to handle the new file format.
The `reset_case_artefacts` function in
`server/src/routes/case_actions.rs` has been updated to remove
`oneliner.txt` and create `oneliner.json` instead.
The tests have been updated to reflect these changes.
Introduces a `resolve_return_path` function to determine the redirect
target after a case action. This function prioritizes the `Referer`
header for a more contextual redirect, falling back to the default case
list page if the header is absent or invalid.
Additionally, this commit refactors the UI elements for actions on the
case detail and case list pages, improving organization and clarity.
Introduces a system for broadcasting real-time events to the web UI.
This enables features like automatic page reloads when case data changes
in the background, improving the user experience by keeping the UI
synchronized with the backend.
Key components:
- `events` module: Contains the `CaseEventKind` enum, `CaseEvent`
struct, and `EventSender` type for managing the broadcast channel.
- SSE endpoint (`/web/events`): Streams events to connected browsers.
- Client-side JavaScript: Listens for events and triggers debounced page
reloads.
- Integration points: Workers and route handlers now emit events when
relevant state changes occur.
This commit restructures the web interface for case details. The
previous `/web/cases/{case_id}` route, which previously showed both the
case summary and its recordings, has been split into two distinct pages:
- `/web/cases/{case_id}`: This page now displays the overall case
information, including the document if available.
- `/web/cases/{case_id}/recordings`: This new page is dedicated to
listing and displaying individual recordings within a case.
This change improves the organization and clarity of the web UI,
allowing for more focused views of case data. Additionally, the
`case_detail.html` and `document.html` templates have been removed as
their functionality is now handled by the new `case_page.html` and the
upcoming document rendering logic. The `cases.html` template has also
been removed, indicating a shift towards more granular page views.
Replace the imperative loop that mixed mtime-tracking, transcript
reading, and validation with three clearly-scoped functions:
- compute_last_mtime: pure reduction over all m4as, returns max mtime.
- read_recordings: I/O loop that reads each transcript sidecar,
aborts on missing transcript (legacy "Nicht alle Aufnahmen sind
transkribiert" 400 body), silently skips blank ones.
- build_analysis_input: orchestrator that composes the above with
RFC3339 formatting.
Error bodies are preserved byte-for-byte. Replaces a one-pass loop
with two passes; n <= ~10 in practice - negligible.
Consolidate 5 instances of "locate_case + warn! + 404-return"
boilerplate (case_actions.rs x4, user_web.rs x1) into a single
pub(crate) helper in user_web.rs. The helper takes &CaseId (no
String allocation at call sites) plus a context tag that becomes
a structured-log field instead of being baked into the message.
bulk.rs keeps using the underlying locate_case because its miss
semantics differ (silent skip, not 404).
Replace five duplicated uuid::Uuid::parse_str calls in web handlers
(analyze, document view, delete, reset, case detail) with a
CaseIdPath extractor that validates the URL segment once and
returns the legacy "Invalid case_id" 400 body byte-for-byte.
The extractor uses axum's FromRequestParts and maps any failure
to AppError::BadRequest, so IntoResponse handling is unchanged.
Moves shared types and utility functions to a new `doctate-common`
crate.
This includes:
- API key header constant
- AckResponse and AckStatus types
- Timestamp formatting and parsing utilities
This change centralizes common functionality, reducing duplication and
improving maintainability.
The `server` crate now depends on `doctate-common`.
This commit introduces a new module `analyze::render` to handle the
rendering of Markdown content produced by the LLM into safe HTML.
The LLM output now includes a custom `==text==` highlighting convention
to indicate sections that require doctor review due to potential
transcription errors or incomplete information. This highlighting is
converted into `<mark>` tags in the final HTML.
To ensure security, all LLM-generated Markdown is first HTML-escaped.
This prevents any malicious HTML or script injection from being executed
in the browser. Only the custom `<mark>` tags are preserved as
functional HTML elements.
The process is as follows:
1. The raw Markdown from the LLM is processed.
2. All HTML special characters (`<`, `>`, `&`, `"`, `'`) are escaped.
3. The `==text==` highlights are replaced with `<mark>text</mark>`.
4. The resulting string is parsed as Markdown by `pulldown-cmark`.
5. The parsed Markdown is converted to HTML, which is then safe to
inject into the Askama template using the `|safe` filter.
The `Cargo.toml` and `Cargo.lock` files have been updated to include the
`pulldown-cmark` dependency. The `document.html` template has been
modified to use a `div` with the class `doc-content` instead of a `pre`
tag, allowing the rendered HTML to be displayed correctly. The
`handle_document_view` function now calls the new `md_to_html` rendering
function.
Introduce a new "reset" action for bulk operations and a dedicated
endpoint for individual case resets. These features allow administrators
to revert a case to its raw audio state by deleting derived artifacts
like transcripts, analysis input, and documents. The functionality also
includes renaming `.m4a.failed` files back to `.m4a` to re-trigger
transcription.
This commit also:
- Adds a `reset_case_artefacts` helper function to `case_actions.rs`.
- Implements the `handle_reset_case` endpoint.
- Adds the "Reset" button to the UI for administrators.
- Includes unit and integration tests to verify the new functionality
and access control.
The versioning of analysis input and document files
(`analysis_input_v{N}.json`, `document_v{N}.md`) has been removed. All
analysis inputs will now use `analysis_input.json` and generated
documents will use `document.md`.
This simplifies file management, as there's no longer a need to track
and manage multiple versions of these files within a case directory. The
analysis worker will now overwrite the existing `document.md` if it
exists, ensuring that the latest analysis result is always present. The
`version` field has also been removed from `AnalyzeJob` and
`AnalysisInput`.
The case listing on the "My Cases" page is now grouped by local date,
with labels for "Heute", "Gestern", or the ISO date. This improves
readability and organization.
Additionally, the handling of silent recordings has been refined.
Previously, the absence of usable recordings would result in an error.
Now, the analysis worker gracefully handles this by writing a stub
document and skipping the LLM call. This prevents unnecessary errors and
provides a clearer status for silent cases.
The `dictate.sh` script has been updated to simplify the case directory
lookup logic. Instead of iterating through `open` and `done`
subdirectories, it now directly checks for the case ID and ensures it's
not marked as deleted. This simplifies the script and improves
efficiency.
The `server/Cargo.toml` and `server/Cargo.lock` have been updated to
include the `num_threads` dependency and enable additional features for
the `time` crate, which are necessary for proper local time zone
handling.
Introduces a new `/web/cases/bulk` endpoint to handle multiple case
actions simultaneously.
This change adds the following:
- A new `bulk` module for handling bulk operations.
- The `handle_bulk_action` function in `bulk.rs` to dispatch to specific
actions.
- `bulk_analyze` and `bulk_delete` functions to process the actions.
- Updates `Cargo.toml` and `Cargo.lock` to include necessary
dependencies: `form_urlencoded`, `serde_core`, `serde_html_form`, and
`serde_path_to_error`.
- Modified `axum-extra` features to include `form`.
- Adds checks for deleted cases in `collect_pending` for both analysis
and transcription recovery.
- Renames and modifies `handle_close_case` to `handle_analyze_case` in
`case_actions.rs` to better reflect its functionality.
- Adds a new `handle_delete_case` and `handle_undo_delete` to
`case_actions.rs`.
- Updates `my_cases.html` and `case_detail.html` to support bulk
actions, including checkboxes, a bulk action bar, and an "Undo last
delete" feature.
- Modifies `handle_audio` and `scan_cases` in `web.rs` to respect delete
markers.
- Updates `analyze_test.rs` with new request builders for analyze and
delete actions.
The distinction between `open/` and `done/` directories for cases has
been removed.
All cases for a user now reside directly under the user's directory
(e.g., `<data_path>/<slug>/<case_id>/`).
This simplifies path management and eliminates redundant directory
traversals.
Key changes include:
- Removed `open/` and `done/` subdirectories in path resolution.
- Introduced a `paths::case_dir` function as a single source of truth
for case directory layout.
- Updated various modules (`recovery`, `auth`, `routes`, `transcribe`,
`tests`) to use the new path structure.
- Adjusted templates to reflect the simplified case status
representation.
Introduce a new endpoint for reanalyzing cases. This feature allows
administrators
to rebuild analysis input files and enqueue new analysis jobs. The
system will
then generate a new document version, which will become the displayed
document.
Extract the logic for building `AnalysisInput` into a new function
`build_analysis_input`. This function encapsulates the process of
collecting recordings, reading transcripts, and determining the last
recording modification time.
This change improves code organization and reusability by centralizing
the input building logic.
Introduce a `DocumentTemplate` struct for rendering the document view,
replacing inline HTML.
Introduce a `CaseFlags` struct to encapsulate the logic for determining
various UI states of a case (e.g., `has_document`, `analyzing`,
`can_close`, `llm_missing`).
Update `handle_case_detail` to use `compute_flags` for populating the
`CaseDetailTemplate`.
Update `scan_user_cases` to compute `analyzing` and `has_document` flags
for the `UserCaseView`.
Add new template logic in `case_detail.html` to display actions based on
`CaseFlags`.
Add new template logic in `my_cases.html` to display `analyzing` and
`done-doc` labels for cases.
Create a new `document.html` template.
Add a helper function `any_document_exists` to check for the presence of
a document file.
Adds API endpoints for closing a case, which triggers an analysis job,
and for viewing the generated document.
This also includes:
- New `AppError` variants: `Conflict` and `ServiceUnavailable`.
- Helper functions for file handling, date parsing, and document
searching.
- Unit tests for helper functions.
Brummel