Introduce `display_name` field to `User` struct for human-readable names
in the UI.
This falls back to the user's `slug` if not provided.
Update `AuthenticatedWebUser` and `MyCasesTemplate` to use this new
field for rendering.
Add tests for parsing `display_name` and ensure fallback logic works
correctly.
Update `users.toml.example` to document the new field.
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.
When an LLM analysis fails, a `.analysis_failed.json` marker is created.
If no document exists yet and the auto-trigger is blocked by this
marker,
the case page must display a banner. This banner provides the failure
reason and a button to retry the analysis, ensuring users are not left
in a dead-end state.
The `read_failure_marker` function is made public to allow the web layer
to access this failure information. The `CasePageTemplate` is updated to
include `analysis_failed` data, which conditionally renders the new
`.failure-banner` HTML.
This change prevents cases from becoming unrecoverable due to transient
LLM errors.
Includes a button for administrators to copy all transcripts and the
document markdown to the clipboard.
The data is embedded as JSON in a script tag and pre-sanitized to
prevent
`</script>` tag injection.
The JavaScript handles copying to the clipboard using the modern
Clipboard API,
with a fallback for older browsers.
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.
Adds a new POST endpoint for web-based oneliner overrides and updates
the UI to allow manual editing. The person icon replaces the pencil icon
for doctor-authored titles, signifying manual authorship rather than
editability.
Introduces `OnelinerLocks` to serialize read-modify-write operations on
`oneliner.json`. This prevents race conditions between the manual
override API (`PUT /api/cases/{case_id}/oneliner`) and the transcription
worker's auto-regeneration process.
The manual override now acquires a lock specific to the `case_dir`
before writing. The transcription worker's `update_oneliner` function
also acquires the same lock around its post-LLM re-read-and-write
sequence. This ensures that a doctor's manual edit always takes
precedence, even if it arrives while an auto-regeneration is in
progress.
This change also includes:
- A new `routes::oneliner_override` module for the PUT handler.
- Validation for the oneliner text length and emptiness.
- Integration tests for the override functionality, covering happy path,
error conditions, early latching, race conditions, and parallel PUTs.
This commit introduces a new `Manual` variant to the `OnelinerState`
enum, allowing for manual overrides of the oneliner text. This change
affects the client and server components to handle and display this new
state.
A `OnelinerOverrideRequest` struct is also added for API requests to set
manual oneliners. New tests are included to ensure the `Manual` variant
serializes and deserializes correctly.
The `compute_oneliner_display` function in
`server/src/routes/user_web.rs` is updated to treat `Manual` states the
same as `Ready` states for display purposes. The
`cases_needing_oneliner_in` function in
`server/src/transcribe/recovery.rs` is updated to not retry cases that
are in a `Manual` state.
Adds the csrf_token hidden field to every POST form in the web UI
(logout, bulk, purge-closed, close, reopen, analyze, reset,
delete-recording). Login stays without a token — SameSite=Strict
already blocks the relevant attack shapes and forced-login CSRF
has no impact here.
Shape:
- New askama macro partials/csrf_field.html renders the hidden
input; 3 templates import + {% call csrf::field(csrf_token) %}
inside each <form method="POST">.
- AuthenticatedWebUser carries csrf_token (cloned out of the
session once during extraction) so render handlers don't need a
second store lookup.
- 3 template structs (MyCasesTemplate, CasePageTemplate,
CaseRecordingsTemplate) gain the field; render sites pass
user.csrf_token through.
Safety-net tests:
- Each rendered page must contain the exact session csrf_token in
a hidden input — catches anyone adding a new form without the
macro.
- Happy-path round-trip: fetch page, parse token from HTML, POST
with token → 303. Catches drift between rendered and accepted
token formats.
Replaces `analysis_preview` with `analysis_html` to display the full
markdown-rendered document content instead of just a plain-text preview.
This allows for richer content presentation and enables client-side
expansion for detailed views.
The HTML template has been updated to include a new `.analysis`
container that handles the expand/collapse functionality using
JavaScript. This approach avoids server-side truncation and relies on
CSS for presentation.
Introduce `count_closed_by_date` and `most_recent_date_label` to
efficiently count closed cases for display purposes when `show_closed`
is false.
Modify `group_by_utc_date` to accept a `closed_extra` map, allowing it
to correctly calculate both open and total case counts per day.
Update the `my_cases.html` template to display the new
`open_count/total_count` format for case groups.
Introduce a `preview_lines` setting in `users.toml` to control the
number of visible lines for the analysis preview in the case list. This
feature extracts the first paragraph of the `document.md` file, strips
markdown formatting, and displays it, capped by the configured
`preview_lines`. The actual line clamping is handled client-side via CSS
`line-clamp`.
Before, every Whisper error (5xx, timeout, Minerva down, corrupt audio,
4xx) renamed `<ts>.m4a` to `<ts>.m4a.failed` uniformly, turning transient
outages into permanent sackgassen that only a manual admin reset could
undo. Cases whose every recording was `.m4a.failed` stuck without a
persisted oneliner state; the UI masked them via a fallback in
`compute_oneliner_display`.
The core insight: a recoverable error is not an error. Transient Whisper
failures now leave the audio as plain `.m4a` so the existing page-load
heal (`enqueue_pending_for_user`) re-enqueues it on the next refresh —
which is exactly what happens when Minerva comes back. No new sidecar,
no retry count, no scheduler.
Changes:
- `WhisperError::is_transient` classifies `Http`, 5xx, 408, 429 as
transient; `Io` and other 4xx as permanent.
- Transcribe worker: transient → info log + continue (audio stays .m4a);
permanent → `mark_failed` as before.
- `has_any_transcript` counts `.m4a.failed` as terminal, so
`update_oneliner` runs for failed-only cases and settles
`OnelinerState::Empty` (analogous to the silent-only fix in 4531f85).
- New verdrängender `fehler`-Badge (#c00) in case list and detail when
at least one `.m4a.failed` exists; recording-level message shortened
to plain "Transkription fehlgeschlagen".
Tests:
- New integration: transient 503 leaves `.m4a` intact, heal recovers.
- New integration: `.m4a.failed`-only case settles to
`OnelinerState::Empty` without calling Ollama.
- New unit: `is_transient` table test across relevant status codes.
- New unit: `has_any_transcript` returns true for `.m4a.failed`-only
case and false for pending-only case.
- Existing worker test retargeted from 500 to 400 and renamed; added
companion `worker_leaves_m4a_intact_on_transient_whisper_error`.
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 …"
heal_orphans_if_idle called regenerate_missing_oneliners_for_user
inline on the request task, blocking the browser for up to N×60s
when orphans existed (observed with 16 cases after manual cleanup).
Now: CAS on new OnelinerHealBusy flag + tokio::spawn + BusyGuard
reset-on-drop. Handler returns immediately; the existing
OnelinerUpdated SSE event delivers results via the usual reload.
Startup recovery shares the flag so a concurrent page-load during
boot cannot fire a parallel regen loop against Ollama.
Regression test uses wiremock + timeout(150ms) + .expect(5) to
verify both non-blocking return and dedup of parallel invocations.
GET /web/cases now honours ?show_closed=1: the toggle link flips the
listing between open-only (default) and open+closed (muted styling,
grey "geschlossen" badge, countdown "wird in N Tagen entfernt" when
auto_delete_days > 0). Each closed row shows a Lucide rotate-ccw
reopen button in the same slot where the close button sits on open
cases; selection checkboxes are suppressed so bulk-close cannot touch
closed cases.
GET /web/cases/:id honours ?show_closed=1 too: without the query a
closed case still 404s (keeps the default listing clean), with it the
detail page renders the reopen form in the header. The case_page
template swaps the icon based on is_closed.
The purge-closed bulk button from the earlier commit finally gets a
UI: it appears below the listing when show_closed=1 is active AND at
least one closed case is visible, with a JS confirm() + the
server-side confirm=yes guard. Two integration tests (listing +
detail) cover the happy path.
New module retention::sweep_user_retention is invoked at the top of
handle_my_cases, using the current user's retention policy. Per case:
step 1 auto-closes when the newest .m4a mtime is older than
auto_close_days; step 2 auto-purges when closed_at is older than
auto_delete_days. Order matters - a case auto-closed in the same sweep
has closed_at ~= now and naturally survives the purge check,
preserving the full grace period after a vacation.
Race guard: purge re-reads the close marker immediately before
remove_dir_all so a concurrent upload that reopens the case cancels
the purge. Every automatic action emits an info! line with reason and
threshold; failures warn but never abort the sweep.
Seven integration tests cover both threshold paths, the disable-via-0
escape hatch, the newest-recording rule, the vacation scenario, and
the open-case skip. Tests age the comparison objects (mtime via
filetime, closed_at as handwritten RFC3339) instead of faking "now" -
no clock abstraction needed.
- 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.
Introduce `Generating` state and clarify `Empty` and `Missing` states.
The `Pending` state now specifically refers to transcription being in
progress.
The `Generating` state covers the period after transcription is complete
but before the LLM has produced the final oneliner state, or when a new
state needs to be generated due to new recordings.
The `Missing` state is collapsed into `Empty` as the UI treats them
identically when no title is expected.
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.
Introduce `OllamaError::EmptyResponse` to represent cases where the
Ollama
model returns an empty result due to silence rules or lack of keywords.
This change prevents treating an empty response as a parse error and
logs
it at a lower severity level. A new integration test verifies this
behavior.
Add `recorded_at_iso` and `time_hms_utc` to `CasePageTemplate` to
display the timestamp of the most recent recording.
Introduce a new partial `partials/time_format.js` for consistent date
and time formatting in the browser.
Update templates to use the new partial for rendering timestamps and
group headings.
Introduces a new module `auto_trigger` responsible for opportunistically
initiating LLM analysis jobs. This mechanism scans case directories for
new or updated recordings and transcripts, automatically creating and
queuing analysis jobs when appropriate.
Key components:
- `evaluate_case`: Pure function to determine if a case is ready for
analysis based on recording status, transcriptions, document
modification times, and existing job/failure markers.
- `try_enqueue`: Orchestrates the analysis job creation and queuing
process if `evaluate_case` returns `AutoDecision::Enqueue`.
- `try_enqueue_all_for_user`: Iterates through all user cases to trigger
`try_enqueue` for eligible ones.
- `write_failure_marker`/`remove_failure_marker`: Handles persistent
recording of analysis failures and their cleanup.
This feature aims to reduce manual intervention by automatically
analyzing new or changed case data.
Passes an `is_admin` flag to the `CaseRecordingsTemplate` and
`case_page.html`.
This flag determines whether the full case ID is displayed in the meta
section
for administrative users. It also influences the header display on the
case page
to prioritize the oneliner when available.
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.
This commit separates the case detail page into two distinct routes:
`/web/cases/{case_id}` for the main case information and document, and
`/web/cases/{case_id}/recordings` for a dedicated view of audio files
and their transcripts.
This change improves the organization and clarity of the case viewing
experience by segmenting the related but distinct information into their
own UI sections.
The 73-line function mixed three concerns: directory traversal,
UUID/deletion filtering, and view assembly. Split into:
- scan_user_cases: orchestrator (loop + sort).
- filter_valid_case_dir: gate that returns (case_id, case_path) for
every valid case directory, skipping non-UUID names, files, and
soft-deleted cases.
- compute_case_view: view assembly that returns None for empty
cases (no recordings yet).
Each helper is now individually inspectable; nesting depth drops
from 3-4 to 2 levels. Let-else guards replace nested matches.
Group the four worker handles (analyze/transcribe x busy/tx) into a
new PipelineState struct with a FromRef<AppState> impl. Convert
heal_orphans_if_idle from a free function with 6 parameters into a
method on PipelineState. The two web handlers (handle_my_cases,
handle_case_detail) now take one State<PipelineState> instead of
four separate State extractors.
The original FromRef impls for AnalyzeBusy/Sender and TranscribeBusy/
Sender remain intact so handlers that need only one of them keep
their narrower signature.
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.
Introduce `last_recording_at` to `OnelinerEntry` and use it as the
primary sort key for cases. This ensures that cases with recent
dictation activity are prioritized, even if their initial creation date
is older.
The logic for determining a case's activity has been updated to consider
the most recent `.m4a` file's modification time (`last_recording_at`),
falling back to `updated_at` or `created_at` if necessary.
This change also refactors the timestamp formatting and handling within
the web interface to correctly display and sort cases based on their
actual last activity time, improving user experience and data relevance.
The `now_rfc3339` function is updated to strip sub-second precision for
consistent filename generation.
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.
The `WorkerBusy` type was previously a single `Arc<AtomicBool>` shared
between the analyze and transcribe workers. This commit refactors this
to:
- Introduce `AnalyzeBusy` and `TranscribeBusy` newtype wrappers around
`WorkerBusy` to distinguish between the two flags. This allows
`axum::extract::State` to target them individually.
- Move the `BusyGuard` RAII guard into `src/lib.rs` and make it generic
to work with any `WorkerBusy` instance.
- Update the `main.rs`, `worker.rs`, and `routes/user_web.rs` files to
use the new types and guards, ensuring correct state management for
both pipelines.
- Enhance the transcription recovery scan
(`transcribe::recovery::scan_and_enqueue`) to iterate over user
directories and call `enqueue_pending_for_user` for each, making it
more robust and aligned with the per-user self-healing mechanism.
- Add a check for `transcribe_busy` in the `case_detail.html` template
to correctly display "Transkription läuft…" only when the transcribe
worker is actually active.
The analyze recovery scan has been refactored to iterate through user
directories and enqueue pending analysis jobs more efficiently. The
`WorkerBusy` status has been introduced as an `Arc<AtomicBool>` to track
whether the analyze worker is currently processing a job.
This `WorkerBusy` flag is used in the `analyze::worker::run` function
and managed by a `BusyGuard` RAII struct, ensuring the flag is correctly
set and unset even in case of panics.
The `handle_my_cases` and `handle_case_detail` handlers in `user_web.rs`
now utilize the `WorkerBusy` flag to accurately display the "analyzing"
status and to trigger a self-heal of orphaned analysis inputs when the
worker is idle.
Additionally, the `WorkerBusy` type is now exported from
`server/src/lib.rs` to be accessible by other modules. The test cases
have been updated to include the `WorkerBusy` parameter when spawning
the analyze worker.
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.
Introduce DeleteMarker struct and associated functions for managing
soft-delete markers within case directories. This enables tracking
deleted cases and supports undo functionality.
feat: Add delete marker support to paths
Introduces a `.deleted` file to mark cases as soft-deleted. The marker
contains a `batch` UUID for grouping deletions and a `deleted_at`
timestamp for ordering.
New functions `is_deleted`, `read_delete_marker`, and
`write_delete_marker` are added to manage this marker. The `locate_case`
function is updated to also consider soft-deleted cases as not found.
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.
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.
This commit introduces the foundation for web-based authentication and
user interface. It includes:
- **Session Management**: Securely handling user sessions using
cryptographically generated tokens, cookies with appropriate security
flags, and server-side storage.
- **Login/Logout Functionality**: Endpoints for users to log in with
their credentials and log out, clearing their session.
- **User Interface**: Basic templates for the login page, a list of
cases, and a detailed view of a single case, allowing users to
navigate and view their data.
- **Authorization**: An `AuthenticatedWebUser` extractor to ensure only
logged-in users can access protected web routes.
- **Configuration**: Added a `cookie_secure` option to the configuration
to control the `Secure` flag on session cookies, useful for local
development.
- **Dependencies**: Added necessary dependencies for password hashing,
time handling, and TOML file manipulation.
- **Helper Binary**: Included a `hash-password` binary to simplify
generating bcrypt hashes for user passwords.
Brummel