Public Access
Archive completed meeting assistant changes
PR and Push Build/Test / build-and-test (push) Successful in 9m19s
PR and Push Build/Test / build-and-test (push) Successful in 9m19s
This commit is contained in:
@@ -0,0 +1,16 @@
|
||||
# Proposal
|
||||
|
||||
Meeting Assistant currently records the Windows default microphone endpoint and offers no in-app way to choose a different input. Users with multiple microphones need a stable configuration default and a quick tray-menu override without changing Windows settings.
|
||||
|
||||
## Changes
|
||||
|
||||
- Add an optional `Recording:MicrophoneDeviceId` setting.
|
||||
- Keep using the Windows default capture endpoint when the setting is blank or absent.
|
||||
- Enumerate active microphone capture endpoints for the tray icon menu.
|
||||
- Add a `Microphone` submenu to the tray icon menu with one checked item for the effective microphone.
|
||||
- Let selecting a microphone from the tray menu change the microphone used for the next capture start.
|
||||
|
||||
## Impact
|
||||
|
||||
- Affects Windows audio capture setup and tray menu rendering.
|
||||
- Does not change system loopback capture or transcription provider behavior.
|
||||
+105
@@ -0,0 +1,105 @@
|
||||
## MODIFIED Requirements
|
||||
|
||||
### Requirement: Recording mode captures microphone and computer output
|
||||
Meeting Assistant SHALL capture microphone input and computer output and combine them into one audio stream for transcription.
|
||||
|
||||
Meeting Assistant SHALL capture audio as 16 kHz mono PCM chunks for the existing recording and transcription pipeline.
|
||||
|
||||
Meeting Assistant SHALL capture microphone and system loopback as separate input streams before producing the final mono chunks.
|
||||
|
||||
Meeting Assistant SHALL clean the microphone stream with a local acoustic echo cancellation stage that uses system loopback as the far-end reference.
|
||||
|
||||
Meeting Assistant SHALL produce final mono chunks by adding the cleaned microphone samples and system samples.
|
||||
|
||||
Meeting Assistant SHALL align microphone and system samples through per-source buffers before mixing and SHALL NOT emit normal live audio chunks that contain only one source while the other source is merely delayed.
|
||||
|
||||
When one source stays quiet beyond the alignment timeout, Meeting Assistant SHALL mix the available source with synthetic silence for the missing source instead of blocking transcription.
|
||||
|
||||
Meeting Assistant SHALL allow the final microphone/system mono mix to apply configurable microphone and system gain before combining samples.
|
||||
|
||||
Meeting Assistant SHALL use the active run or launch profile recording options when configuring capture format and final microphone/system gains.
|
||||
|
||||
Meeting Assistant SHALL clamp mixed samples after gain is applied.
|
||||
|
||||
Meeting Assistant SHALL write only the mixed stream to the temporary WAV used by transcription and finalization.
|
||||
|
||||
Meeting Assistant SHALL allow `Recording:MicrophoneDeviceId` to select a Windows microphone capture endpoint.
|
||||
|
||||
When `Recording:MicrophoneDeviceId` is blank or absent, Meeting Assistant SHALL use the Windows default capture endpoint.
|
||||
|
||||
When a microphone is selected from the tray icon menu, Meeting Assistant SHALL use that selected microphone for later recording starts until another microphone is selected or the process exits.
|
||||
|
||||
The tray icon right-click menu SHALL expose a `Microphone` submenu listing active microphone capture endpoints.
|
||||
|
||||
The `Microphone` submenu SHALL mark exactly one effective microphone as checked.
|
||||
|
||||
When no runtime microphone override is selected, the checked microphone SHALL be the configured microphone when it is available, otherwise the Windows default capture endpoint.
|
||||
|
||||
#### Scenario: Both sources produce audio
|
||||
- **WHEN** microphone and computer output audio chunks are available
|
||||
- **THEN** Meeting Assistant mixes them into one PCM stream before transcription
|
||||
|
||||
#### Scenario: Mixed audio uses cleaned microphone and system audio
|
||||
- **GIVEN** the echo canceller cleans a microphone chunk to sample `2000`
|
||||
- **AND** the matching system chunk has sample `10000`
|
||||
- **WHEN** microphone and system chunks are mixed with gains `1` and `1`
|
||||
- **THEN** the mixed sample is `12000`
|
||||
|
||||
#### Scenario: Temporary recording stores only the mixed stream
|
||||
- **GIVEN** Meeting Assistant has mixed microphone and system audio into one PCM chunk
|
||||
- **WHEN** Meeting Assistant appends the chunk to the temporary recording
|
||||
- **THEN** the main temporary WAV contains the mixed PCM
|
||||
- **AND** no microphone or system sidecar WAV is written
|
||||
|
||||
#### Scenario: Launch profile recording options configure capture and gains
|
||||
- **GIVEN** an active launch profile configures sample format and microphone/system mix gains
|
||||
- **WHEN** Meeting Assistant captures and mixes audio for that run
|
||||
- **THEN** the microphone and system capture sources receive that launch profile recording configuration
|
||||
- **AND** the mixed output uses that launch profile's microphone/system gains
|
||||
|
||||
#### Scenario: Delayed sources are buffered before mixing
|
||||
- **GIVEN** microphone audio arrives before matching system audio
|
||||
- **WHEN** matching system audio arrives after a short delay
|
||||
- **THEN** Meeting Assistant emits one mixed chunk for the aligned samples
|
||||
- **AND** it does not emit separate microphone-only and system-only chunks for that delayed pair
|
||||
|
||||
#### Scenario: Quiet system audio does not block microphone transcription
|
||||
- **GIVEN** microphone audio arrives
|
||||
- **AND** system loopback audio does not arrive within the alignment timeout
|
||||
- **WHEN** Meeting Assistant mixes the available audio
|
||||
- **THEN** it emits the microphone audio mixed with silent system audio
|
||||
- **AND** live transcription can continue while system loopback is quiet
|
||||
|
||||
#### Scenario: Continuous microphone audio does not suppress the alignment timeout
|
||||
- **GIVEN** microphone audio keeps arriving
|
||||
- **AND** system loopback audio stays unavailable past the alignment timeout
|
||||
- **WHEN** Meeting Assistant checks the buffered microphone audio
|
||||
- **THEN** it emits the buffered microphone audio mixed with silent system audio
|
||||
- **AND** it does not wait indefinitely for a loopback chunk
|
||||
|
||||
#### Scenario: Device-level capture cannot be verified in tests
|
||||
- **WHEN** automated tests run without live audio devices
|
||||
- **THEN** Meeting Assistant verifies the audio mixer through deterministic source abstractions rather than depending on physical microphone or speaker devices
|
||||
|
||||
#### Scenario: Configured microphone is used for capture
|
||||
- **GIVEN** `Recording:MicrophoneDeviceId` identifies an active microphone endpoint
|
||||
- **WHEN** Meeting Assistant starts microphone capture
|
||||
- **THEN** it captures from that endpoint
|
||||
|
||||
#### Scenario: Blank microphone setting uses Windows default
|
||||
- **GIVEN** `Recording:MicrophoneDeviceId` is blank
|
||||
- **WHEN** Meeting Assistant starts microphone capture
|
||||
- **THEN** it captures from the Windows default capture endpoint
|
||||
|
||||
#### Scenario: Tray menu lists microphones with current selection checked
|
||||
- **GIVEN** active microphone endpoints `integrated microphone` and `other microphone`
|
||||
- **AND** `integrated microphone` is the effective microphone
|
||||
- **WHEN** the taskbar menu is opened
|
||||
- **THEN** it shows a `Microphone` submenu
|
||||
- **AND** the `integrated microphone` item is checked
|
||||
- **AND** the `other microphone` item is unchecked
|
||||
|
||||
#### Scenario: Tray microphone selection changes later capture
|
||||
- **GIVEN** active microphone endpoints `integrated microphone` and `other microphone`
|
||||
- **WHEN** the user selects `other microphone` from the taskbar microphone submenu
|
||||
- **THEN** later recording starts capture from `other microphone`
|
||||
@@ -0,0 +1,9 @@
|
||||
# Tasks
|
||||
|
||||
- [x] Add requirement scenarios for configured microphone selection and tray runtime selection.
|
||||
- [x] Add a failing behavior test for the tray microphone submenu.
|
||||
- [x] Add a failing behavior test for configured/default microphone resolution.
|
||||
- [x] Implement microphone device enumeration, selection state, and capture endpoint resolution.
|
||||
- [x] Render the microphone submenu and execute microphone selection actions.
|
||||
- [x] Update configuration documentation.
|
||||
- [x] Run focused tests and `openspec validate add-runtime-microphone-selection --strict`.
|
||||
@@ -0,0 +1,12 @@
|
||||
## Why
|
||||
Screenshot OCR can identify visible meeting participants before the summary agent runs. When the model provides attendee names directly, Meeting Assistant should use that evidence immediately instead of waiting for later summary refinement.
|
||||
|
||||
## What Changes
|
||||
- Extend screenshot OCR metadata so the model can return a partial attendee list.
|
||||
- Merge OCR-provided attendees into the meeting note without duplicates.
|
||||
- Canonicalize attendee additions through speaker identity aliases before saving.
|
||||
|
||||
## Impact
|
||||
- Updates screenshot OCR prompt/default metadata shape.
|
||||
- Updates OCR result parsing and screenshot OCR completion handling.
|
||||
- Adds behavior tests for parsing attendees and updating meeting notes.
|
||||
+71
@@ -0,0 +1,71 @@
|
||||
## MODIFIED Requirements
|
||||
|
||||
### Requirement: Meeting screenshots are captured into assistant context
|
||||
Meeting Assistant SHALL expose a configurable screenshot hotkey.
|
||||
|
||||
When a meeting is active and the screenshot hotkey is pressed, Meeting Assistant SHALL capture the currently active window.
|
||||
|
||||
The screenshot image SHALL be saved into a configurable attachments folder for the assistant context note. By default, the folder SHALL be `Attachments` beside the assistant context note.
|
||||
|
||||
After the image is saved, Meeting Assistant SHALL append a markdown image link to the assistant context note with a meeting-relative timestamp that correlates to transcript timestamps.
|
||||
|
||||
Meeting Assistant SHALL allow optional screenshot OCR configuration with endpoint URL, API key or key environment variable, model, prompt, and timeout.
|
||||
|
||||
When screenshot OCR is configured, Meeting Assistant SHALL send the screenshot and prompt to the configured OpenAI-compatible Responses endpoint and append the model result after the screenshot link in the assistant context note.
|
||||
|
||||
The screenshot OCR prompt SHALL ask the model to return pixel crop coordinates when it can confidently isolate only the presentation, shared screen, or similarly relevant meeting content.
|
||||
|
||||
When OCR returns valid crop coordinates within the original image bounds, Meeting Assistant SHALL save a cropped PNG beside the original screenshot and SHALL link the cropped image before the OCR result in the assistant context note.
|
||||
|
||||
When OCR returns no crop coordinates or invalid crop coordinates, Meeting Assistant SHALL keep the original screenshot link and OCR result without writing a cropped image.
|
||||
|
||||
When screenshot OCR metadata includes attendee names visible or otherwise deduced from the screenshot, Meeting Assistant SHALL add those attendees to the meeting note.
|
||||
|
||||
Screenshot OCR attendee additions SHALL preserve existing attendees, SHALL NOT create duplicate attendees, and SHALL canonicalize names through speaker identity aliases before saving.
|
||||
|
||||
Screenshot OCR attendee metadata MAY be partial and SHALL NOT remove existing attendees that are absent from the screenshot result.
|
||||
|
||||
When screenshot OCR is not configured, Meeting Assistant SHALL skip OCR and keep the screenshot link.
|
||||
|
||||
The default OCR prompt SHALL explain that the image is from a meeting and ask the model to identify who is talking, who is presenting, what is presented, capture slide text in markdown, convert diagrams to Mermaid when possible, indicate whether visible people are clearly the exact meeting participants or only a partial result, return crop coordinates only for confidently isolated presentation/shared-screen content, return any visible or deduced attendees as metadata, and otherwise describe the scene.
|
||||
|
||||
#### Scenario: Screenshot is linked with meeting timestamp
|
||||
- **GIVEN** a meeting started at `10:00:00`
|
||||
- **WHEN** the user captures a screenshot at `10:03:05`
|
||||
- **THEN** Meeting Assistant saves the screenshot under the configured attachments folder
|
||||
- **AND** appends a markdown image link to assistant context with timestamp `[00:03:05]`
|
||||
|
||||
#### Scenario: OCR result is appended after screenshot
|
||||
- **GIVEN** screenshot OCR is configured
|
||||
- **WHEN** the user captures a screenshot
|
||||
- **THEN** Meeting Assistant appends the screenshot link to assistant context
|
||||
- **AND** appends the OCR result for that screenshot after the link when processing completes
|
||||
|
||||
#### Scenario: OCR crop is saved and linked before OCR text
|
||||
- **GIVEN** screenshot OCR is configured
|
||||
- **AND** OCR returns valid crop coordinates for a shared screen
|
||||
- **WHEN** OCR processing completes
|
||||
- **THEN** Meeting Assistant saves a cropped screenshot beside the original image
|
||||
- **AND** links the cropped screenshot before the OCR text
|
||||
|
||||
#### Scenario: OCR attendees are added to the meeting note
|
||||
- **GIVEN** screenshot OCR is configured
|
||||
- **AND** the current meeting note already has attendees
|
||||
- **WHEN** screenshot OCR metadata returns attendee names from the screenshot
|
||||
- **THEN** Meeting Assistant adds those attendees to the meeting note
|
||||
- **AND** keeps existing attendees
|
||||
- **AND** does not duplicate attendees that match existing names or speaker identity aliases
|
||||
|
||||
#### Scenario: OCR partial attendees do not remove existing attendees
|
||||
- **GIVEN** the current meeting note has attendees `Ada` and `Grace`
|
||||
- **WHEN** screenshot OCR metadata returns only `Ada`
|
||||
- **THEN** Meeting Assistant keeps `Grace` in the meeting note
|
||||
|
||||
#### Scenario: OCR is skipped when not configured
|
||||
- **GIVEN** screenshot OCR is not configured
|
||||
- **WHEN** the user captures a screenshot
|
||||
- **THEN** Meeting Assistant saves and links the screenshot without calling a model endpoint
|
||||
|
||||
#### Scenario: OCR reports whether visible people are complete or partial
|
||||
- **WHEN** Meeting Assistant uses the built-in screenshot OCR prompt
|
||||
- **THEN** the prompt asks the model to state whether the screenshot clearly shows exactly who is in the meeting or only a partial participant result
|
||||
@@ -0,0 +1,5 @@
|
||||
- [x] 1. Add OpenSpec scenario for screenshot OCR attendee additions.
|
||||
- [x] 2. Add failing behavior tests for OCR attendee parsing and meeting-note updates.
|
||||
- [x] 3. Parse `attendees` from screenshot OCR metadata.
|
||||
- [x] 4. Merge OCR attendees into the meeting note through alias-aware canonicalization.
|
||||
- [x] 5. Run focused tests and `openspec validate add-screenshot-ocr-attendees --strict`.
|
||||
@@ -0,0 +1,12 @@
|
||||
## Why
|
||||
Screenshot OCR can fail after a useful screenshot has already been saved to the assistant context. The user should be able to retry OCR for that exact screenshot from the note, matching the existing summary retry workflow.
|
||||
|
||||
## What Changes
|
||||
- Add a retry link when screenshot OCR fails or times out.
|
||||
- Add a local retry endpoint for screenshot OCR.
|
||||
- Rerun OCR for the exact saved screenshot and replace the same assistant-context OCR block.
|
||||
|
||||
## Impact
|
||||
- Updates screenshot OCR failure handling.
|
||||
- Adds local API surface for screenshot OCR retry.
|
||||
- Adds behavior tests for retry link generation and retry execution.
|
||||
+65
@@ -0,0 +1,65 @@
|
||||
## MODIFIED Requirements
|
||||
|
||||
### Requirement: Meeting screenshots are captured into assistant context
|
||||
Meeting Assistant SHALL expose a configurable screenshot hotkey.
|
||||
|
||||
When a meeting is active and the screenshot hotkey is pressed, Meeting Assistant SHALL capture the currently active window.
|
||||
|
||||
The screenshot image SHALL be saved into a configurable attachments folder for the assistant context note. By default, the folder SHALL be `Attachments` beside the assistant context note.
|
||||
|
||||
After the image is saved, Meeting Assistant SHALL append a markdown image link to the assistant context note with a meeting-relative timestamp that correlates to transcript timestamps.
|
||||
|
||||
Meeting Assistant SHALL allow optional screenshot OCR configuration with endpoint URL, API key or key environment variable, model, prompt, and timeout.
|
||||
|
||||
When screenshot OCR is configured, Meeting Assistant SHALL send the screenshot and prompt to the configured OpenAI-compatible Responses endpoint and append the model result after the screenshot link in the assistant context note.
|
||||
|
||||
The screenshot OCR prompt SHALL ask the model to return pixel crop coordinates when it can confidently isolate only the presentation, shared screen, or similarly relevant meeting content.
|
||||
|
||||
When OCR returns valid crop coordinates within the original image bounds, Meeting Assistant SHALL save a cropped PNG beside the original screenshot and SHALL link the cropped image before the OCR result in the assistant context note.
|
||||
|
||||
When OCR returns no crop coordinates or invalid crop coordinates, Meeting Assistant SHALL keep the original screenshot link and OCR result without writing a cropped image.
|
||||
|
||||
When screenshot OCR fails or times out, Meeting Assistant SHALL write the failure status into the assistant context note with a retry link for that exact screenshot.
|
||||
|
||||
When the screenshot OCR retry link is activated, Meeting Assistant SHALL rerun OCR for the saved screenshot and replace that screenshot's OCR block in the assistant context note.
|
||||
|
||||
When screenshot OCR is not configured, Meeting Assistant SHALL skip OCR and keep the screenshot link.
|
||||
|
||||
The default OCR prompt SHALL explain that the image is from a meeting and ask the model to identify who is talking, who is presenting, what is presented, capture slide text in markdown, convert diagrams to Mermaid when possible, indicate whether visible people are clearly the exact meeting participants or only a partial result, return crop coordinates only for confidently isolated presentation/shared-screen content, and otherwise describe the scene.
|
||||
|
||||
#### Scenario: Screenshot is linked with meeting timestamp
|
||||
- **GIVEN** a meeting started at `10:00:00`
|
||||
- **WHEN** the user captures a screenshot at `10:03:05`
|
||||
- **THEN** Meeting Assistant saves the screenshot under the configured attachments folder
|
||||
- **AND** appends a markdown image link to assistant context with timestamp `[00:03:05]`
|
||||
|
||||
#### Scenario: OCR result is appended after screenshot
|
||||
- **GIVEN** screenshot OCR is configured
|
||||
- **WHEN** the user captures a screenshot
|
||||
- **THEN** Meeting Assistant appends the screenshot link to assistant context
|
||||
- **AND** appends the OCR result for that screenshot after the link when processing completes
|
||||
|
||||
#### Scenario: OCR crop is saved and linked before OCR text
|
||||
- **GIVEN** screenshot OCR is configured
|
||||
- **AND** OCR returns valid crop coordinates for a shared screen
|
||||
- **WHEN** OCR processing completes
|
||||
- **THEN** Meeting Assistant saves a cropped screenshot beside the original image
|
||||
- **AND** links the cropped screenshot before the OCR text in assistant context
|
||||
|
||||
#### Scenario: OCR failure can be retried for the same screenshot
|
||||
- **GIVEN** screenshot OCR is configured
|
||||
- **AND** OCR fails or times out for a captured screenshot
|
||||
- **WHEN** Meeting Assistant writes the OCR failure status
|
||||
- **THEN** the assistant context includes a retry link for that exact screenshot
|
||||
- **WHEN** the retry link is activated
|
||||
- **THEN** Meeting Assistant reruns OCR against the saved screenshot
|
||||
- **AND** replaces that screenshot's OCR block with the retry result
|
||||
|
||||
#### Scenario: OCR is skipped when not configured
|
||||
- **GIVEN** screenshot OCR is not configured
|
||||
- **WHEN** the user captures a screenshot
|
||||
- **THEN** Meeting Assistant saves and links the screenshot without calling a model endpoint
|
||||
|
||||
#### Scenario: OCR reports whether visible people are complete or partial
|
||||
- **WHEN** Meeting Assistant uses the built-in screenshot OCR prompt
|
||||
- **THEN** the prompt asks the model to state whether the screenshot clearly shows exactly who is in the meeting or only a partial participant result
|
||||
@@ -0,0 +1,5 @@
|
||||
- [x] 1. Add OpenSpec scenario for screenshot OCR retry.
|
||||
- [x] 2. Add failing behavior tests for OCR failure retry links and retry execution.
|
||||
- [x] 3. Preserve retryable OCR blocks on failure/timeout and include retry links.
|
||||
- [x] 4. Add local retry endpoint for screenshot OCR.
|
||||
- [x] 5. Run focused tests, full tests, and `openspec validate add-screenshot-ocr-retry --strict`.
|
||||
@@ -0,0 +1,8 @@
|
||||
## Why
|
||||
The transcript marker for switching transcription profiles currently tells the summarizer that the profile changed, but not that speaker recognition state was reset. That can make later transcript interpretation less clear.
|
||||
|
||||
## What Changes
|
||||
- Extend the profile-switch transcript marker to state that speaker recognition and identities were reset.
|
||||
|
||||
## Impact
|
||||
- Updates the active profile-switch recording behavior and its test coverage.
|
||||
+36
@@ -0,0 +1,36 @@
|
||||
## MODIFIED Requirements
|
||||
|
||||
### Requirement: Active recording can switch launch profiles
|
||||
Meeting Assistant SHALL allow a launch profile hotkey or named-profile recording toggle request to switch the active meeting to that profile while recording capture is active.
|
||||
|
||||
When switching profiles during an active meeting, Meeting Assistant SHALL keep the existing meeting note, transcript, assistant context, summary path, user notes, calendar metadata, projects, attendees, and assistant-context state.
|
||||
|
||||
When switching profiles during an active meeting, Meeting Assistant SHALL NOT create new meeting artifacts, SHALL NOT collect calendar metadata again, and SHALL NOT run the summary pipeline for the old profile segment.
|
||||
|
||||
When switching profiles during an active meeting, Meeting Assistant SHALL stop and drain the current speech recognition pipeline, append a transcript marker indicating the target profile and that speaker recognition and identities were reset, start a new speech recognition pipeline using the target profile's resolved options, and continue writing live transcription to the same transcript file.
|
||||
|
||||
When audio is captured while the old speech recognition pipeline is draining, Meeting Assistant SHALL buffer that audio and send it to the new profile's speech recognition pipeline after it is ready.
|
||||
|
||||
When switching profiles during an active meeting, Meeting Assistant SHALL clear run-local speaker label mappings for future transcript segments because backend speaker IDs can change across speech recognition processes. Already-written named transcript segments SHALL remain unchanged.
|
||||
|
||||
#### Scenario: Active meeting switches to named profile
|
||||
- **GIVEN** a meeting was started with the default launch profile
|
||||
- **WHEN** the user triggers launch profile `english` while recording is active
|
||||
- **THEN** Meeting Assistant keeps the existing meeting artifacts
|
||||
- **AND** drains the old speech recognition pipeline without running summary generation
|
||||
- **AND** appends a transcript marker for the profile switch
|
||||
- **AND** the transcript marker states that speaker recognition and identities were reset
|
||||
- **AND** starts transcription with the resolved `english` profile
|
||||
- **AND** continues writing transcript segments to the same transcript file
|
||||
|
||||
#### Scenario: Captured audio is buffered while switching
|
||||
- **GIVEN** a meeting is switching from one launch profile to another
|
||||
- **WHEN** audio chunks are captured before the new speech recognition pipeline is ready
|
||||
- **THEN** Meeting Assistant buffers those chunks
|
||||
- **AND** sends the buffered chunks to the new profile's speech recognition pipeline after it starts
|
||||
|
||||
#### Scenario: Switching clears future speaker mappings only
|
||||
- **GIVEN** a live speaker label was mapped to a named speaker before switching profiles
|
||||
- **WHEN** Meeting Assistant switches to another launch profile
|
||||
- **THEN** already-written transcript text keeps the named speaker
|
||||
- **AND** later transcript segments from the new pipeline do not reuse the old backend speaker label mapping
|
||||
@@ -0,0 +1,4 @@
|
||||
- [x] 1. Add OpenSpec scenario for the clarified profile-switch marker.
|
||||
- [x] 2. Add failing behavior coverage for the marker text.
|
||||
- [x] 3. Update the profile-switch marker.
|
||||
- [x] 4. Run focused tests and `openspec validate clarify-profile-switch-marker --strict`.
|
||||
@@ -0,0 +1,12 @@
|
||||
## Why
|
||||
Users sometimes add screenshots or image references directly to the meeting note while a meeting is in progress. The summary agent should see OCR for those manually added images even when they were not captured through the Meeting Assistant screenshot hotkey.
|
||||
|
||||
## What Changes
|
||||
- Scan the meeting note after transcription and before summarization for Obsidian and Markdown image embeds.
|
||||
- Add matching image references and OCR output to the assistant context without modifying the meeting note or copying image files.
|
||||
- Wait for this OCR pass before moving the assistant context into summarization.
|
||||
|
||||
## Impact
|
||||
- Adds a pre-summary screenshot OCR pass over user-authored meeting note image embeds.
|
||||
- Reuses the existing screenshot OCR client and pending OCR wait path.
|
||||
- Does not perform crop extraction or attendee updates for meeting-note images.
|
||||
+70
@@ -0,0 +1,70 @@
|
||||
## MODIFIED Requirements
|
||||
|
||||
### Requirement: Meeting screenshots are captured into assistant context
|
||||
Meeting Assistant SHALL expose a configurable screenshot hotkey.
|
||||
|
||||
When a meeting is active and the screenshot hotkey is pressed, Meeting Assistant SHALL capture the currently active window.
|
||||
|
||||
The screenshot image SHALL be saved into a configurable attachments folder for the assistant context note. By default, the folder SHALL be `Attachments` beside the assistant context note.
|
||||
|
||||
After the image is saved, Meeting Assistant SHALL append a markdown image link to the assistant context note with a meeting-relative timestamp that correlates to transcript timestamps.
|
||||
|
||||
Meeting Assistant SHALL allow optional screenshot OCR configuration with endpoint URL, API key or key environment variable, model, prompt, and timeout.
|
||||
|
||||
When screenshot OCR is configured, Meeting Assistant SHALL send the screenshot and prompt to the configured OpenAI-compatible Responses endpoint and append the model result after the screenshot link in the assistant context note.
|
||||
|
||||
The screenshot OCR prompt SHALL ask the model to return pixel crop coordinates when it can confidently isolate only the presentation, shared screen, or similarly relevant meeting content.
|
||||
|
||||
When OCR returns valid crop coordinates within the original image bounds, Meeting Assistant SHALL save a cropped PNG beside the original screenshot and SHALL link the cropped image before the OCR result in the assistant context note.
|
||||
|
||||
When OCR returns no crop coordinates or invalid crop coordinates, Meeting Assistant SHALL keep the original screenshot link and OCR result without writing a cropped image.
|
||||
|
||||
After transcription finishes and before summarization starts, Meeting Assistant SHALL scan the meeting note for user-authored Obsidian image embeds and Markdown image embeds.
|
||||
|
||||
When configured screenshot OCR is enabled and the meeting note contains image embeds, Meeting Assistant SHALL append each resolvable image to the assistant context note, state that the image came from the meeting note, preserve the original embed text for cross-reference, and run OCR for the linked image.
|
||||
|
||||
Meeting-note image OCR SHALL NOT copy the image file, SHALL NOT write crop images, SHALL NOT add attendees from OCR metadata, and SHALL NOT modify the meeting note.
|
||||
|
||||
Meeting Assistant SHALL wait for meeting-note image OCR to finish or time out before transitioning the assistant context to summarizing.
|
||||
|
||||
When screenshot OCR is not configured, Meeting Assistant SHALL skip OCR and keep the screenshot link.
|
||||
|
||||
The default OCR prompt SHALL explain that the image is from a meeting and ask the model to identify who is talking, who is presenting, what is presented, capture slide text in markdown, convert diagrams to Mermaid when possible, indicate whether visible people are clearly the exact meeting participants or only a partial result, return crop coordinates only for confidently isolated presentation/shared-screen content, and otherwise describe the scene.
|
||||
|
||||
#### Scenario: Screenshot is linked with meeting timestamp
|
||||
- **GIVEN** a meeting started at `10:00:00`
|
||||
- **WHEN** the user captures a screenshot at `10:03:05`
|
||||
- **THEN** Meeting Assistant saves the screenshot under the configured attachments folder
|
||||
- **AND** appends a markdown image link to assistant context with timestamp `[00:03:05]`
|
||||
|
||||
#### Scenario: OCR result is appended after screenshot
|
||||
- **GIVEN** screenshot OCR is configured
|
||||
- **WHEN** the user captures a screenshot
|
||||
- **THEN** Meeting Assistant appends the screenshot link to assistant context
|
||||
- **AND** appends the OCR result for that screenshot after the link when processing completes
|
||||
|
||||
#### Scenario: OCR crop is saved and linked before OCR text
|
||||
- **GIVEN** screenshot OCR is configured
|
||||
- **AND** OCR returns valid crop coordinates for a shared screen
|
||||
- **WHEN** OCR processing completes
|
||||
- **THEN** Meeting Assistant saves a cropped screenshot beside the original image
|
||||
- **AND** links the cropped screenshot before the OCR text in assistant context
|
||||
|
||||
#### Scenario: Meeting note image embeds are OCRed before summarization
|
||||
- **GIVEN** screenshot OCR is configured
|
||||
- **AND** the meeting note contains `![[whiteboard.png]]`
|
||||
- **AND** the meeting note contains ``
|
||||
- **WHEN** transcription finishes
|
||||
- **THEN** Meeting Assistant appends both images to the assistant context as images from the meeting note
|
||||
- **AND** includes the original embed text for each image
|
||||
- **AND** runs OCR for each image without copying files, writing crop images, adding attendees, or modifying the meeting note
|
||||
- **AND** waits for this OCR to finish or time out before transitioning to summarizing
|
||||
|
||||
#### Scenario: OCR is skipped when not configured
|
||||
- **GIVEN** screenshot OCR is not configured
|
||||
- **WHEN** the user captures a screenshot
|
||||
- **THEN** Meeting Assistant saves and links the screenshot without calling a model endpoint
|
||||
|
||||
#### Scenario: OCR reports whether visible people are complete or partial
|
||||
- **WHEN** Meeting Assistant uses the built-in screenshot OCR prompt
|
||||
- **THEN** the prompt asks the model to state whether the screenshot clearly shows exactly who is in the meeting or only a partial participant result
|
||||
@@ -0,0 +1,5 @@
|
||||
- [x] 1. Add OpenSpec scenario for meeting-note image embed OCR before summarization.
|
||||
- [x] 2. Add failing behavior tests for meeting-note image OCR and pre-summary waiting.
|
||||
- [x] 3. Implement image embed discovery and assistant-context OCR entries without modifying the meeting note.
|
||||
- [x] 4. Hook the scan before summary state transition and wait for completion.
|
||||
- [x] 5. Run focused tests, full tests, and `openspec validate ocr-meeting-note-image-embeds --strict`.
|
||||
@@ -0,0 +1,14 @@
|
||||
## Why
|
||||
When several Teams meetings are plausible in Outlook, a standalone "current meeting" lookup can pick the wrong appointment or no appointment. The recording-start notification already represents one specific cached calendar meeting, so accepting that notification should start the recording with that meeting's metadata.
|
||||
|
||||
## What Changes
|
||||
- Carry meeting title, attendees, agenda, and scheduled end in cached calendar prompt candidates.
|
||||
- Start recordings accepted from a meeting-start notification with the accepted candidate's metadata instead of running a separate Outlook current-meeting lookup.
|
||||
- Preserve the normal workflow lifecycle events and rules for prompted starts.
|
||||
- Exclude canceled Outlook appointments from prompt candidates and standalone current-meeting metadata lookup.
|
||||
|
||||
## Impact
|
||||
- Updates the calendar prompt scheduler and recording controller seam.
|
||||
- Extends Windows Outlook calendar prompt extraction to include metadata already used by meeting notes.
|
||||
- Filters canceled Outlook appointments before prompting or selecting metadata.
|
||||
- Adds tests for prompt-supplied metadata and workflow rule execution.
|
||||
+120
@@ -0,0 +1,120 @@
|
||||
## MODIFIED Requirements
|
||||
|
||||
### Requirement: Outlook Teams meetings can prompt recording start
|
||||
Meeting Assistant SHALL enable scheduled Outlook Classic calendar checks for recording-start prompts by default.
|
||||
|
||||
When scheduled recording prompts are enabled on Windows, Meeting Assistant SHALL periodically read the user's Outlook Classic calendar appointments for the current local day through COM into an in-memory cache.
|
||||
|
||||
Meeting Assistant SHALL default the Outlook calendar sync interval to 30 minutes when scheduled recording prompts are enabled.
|
||||
|
||||
Meeting Assistant SHALL schedule recording-start prompts from the cached calendar appointments rather than querying Outlook for each prompt.
|
||||
|
||||
Meeting Assistant SHALL consider Teams appointments from Outlook calendar data as initial prompt candidates. The detection MAY be extended later for other meeting providers.
|
||||
|
||||
Meeting Assistant SHALL exclude canceled Outlook appointments from recording-start prompt candidates.
|
||||
|
||||
When a Teams appointment reaches its scheduled start window, Meeting Assistant SHALL show a native Windows app notification asking whether to record the meeting, with affirmative and negative actions.
|
||||
|
||||
On Windows, the recording-start notification SHALL request reminder-style toast behavior and remain actionable for 5 minutes.
|
||||
|
||||
Meeting Assistant SHALL prompt at most once per calendar appointment during a local day, regardless of whether the user accepts, declines, or ignores the notification.
|
||||
|
||||
If the user accepts the recording prompt while no recording is active, Meeting Assistant SHALL start a new recording normally.
|
||||
|
||||
If the user accepts the recording prompt while another recording is active, Meeting Assistant SHALL stop the active recording normally and then start the prompted meeting recording.
|
||||
|
||||
When stopping an active recording for an accepted prompt, Meeting Assistant SHALL use the normal stop path so empty or too-short recordings are removed according to existing settings and other completed recordings continue normal transcription, speaker recognition, and summary processing.
|
||||
|
||||
When the user accepts a recording prompt, Meeting Assistant SHALL start the recording with the accepted cached appointment's metadata and SHALL NOT perform a separate current-meeting metadata lookup for that prompted start.
|
||||
|
||||
Prompted-start metadata SHALL include the accepted appointment title, attendees, agenda, and scheduled end when those values are available from the cached appointment.
|
||||
|
||||
Prompted starts SHALL run the normal meeting workflow `created` rules before applying the accepted appointment metadata.
|
||||
|
||||
After `created` rules run, prompted starts SHALL apply the accepted appointment metadata and then run the normal `collecting metadata` to `transcribing` state-transition workflow rules with that metadata available in the meeting note.
|
||||
|
||||
#### Scenario: Teams meeting start prompts the user
|
||||
- **GIVEN** scheduled Outlook recording prompts are enabled
|
||||
- **AND** Meeting Assistant has synced Outlook Classic Teams appointments for today
|
||||
- **WHEN** the appointment reaches its scheduled start window
|
||||
- **THEN** Meeting Assistant shows a native Windows app notification asking whether to record the meeting
|
||||
- **AND** the notification remains actionable for 5 minutes
|
||||
- **AND** marks that appointment as prompted for the day
|
||||
|
||||
#### Scenario: Canceled Teams meeting does not prompt recording
|
||||
- **GIVEN** scheduled Outlook recording prompts are enabled
|
||||
- **AND** Meeting Assistant has synced a canceled Outlook Classic Teams appointment for today
|
||||
- **WHEN** the canceled appointment reaches its scheduled start window
|
||||
- **THEN** Meeting Assistant does not show a recording prompt for that appointment
|
||||
|
||||
#### Scenario: Back-to-back cached Teams meetings prompt without another Outlook sync
|
||||
- **GIVEN** scheduled Outlook recording prompts are enabled
|
||||
- **AND** Meeting Assistant has synced two Teams appointments for today that start ten minutes apart
|
||||
- **WHEN** each appointment reaches its scheduled start window
|
||||
- **THEN** Meeting Assistant shows a recording prompt for each appointment
|
||||
- **AND** does not require another Outlook calendar sync between the prompts
|
||||
|
||||
#### Scenario: User accepts prompt while idle
|
||||
- **GIVEN** scheduled Outlook recording prompts are enabled
|
||||
- **AND** no meeting recording is active
|
||||
- **WHEN** the user accepts a Teams meeting recording prompt
|
||||
- **THEN** Meeting Assistant starts recording normally
|
||||
|
||||
#### Scenario: User accepts prompt while already recording
|
||||
- **GIVEN** scheduled Outlook recording prompts are enabled
|
||||
- **AND** a meeting recording is active
|
||||
- **WHEN** the user accepts a Teams meeting recording prompt
|
||||
- **THEN** Meeting Assistant stops the active recording normally
|
||||
- **AND** starts a new recording normally after the stop request
|
||||
|
||||
#### Scenario: Accepted prompt supplies meeting metadata
|
||||
- **GIVEN** scheduled Outlook recording prompts are enabled
|
||||
- **AND** Meeting Assistant has cached two current Teams appointments with different metadata
|
||||
- **WHEN** the user accepts the recording prompt for one appointment
|
||||
- **THEN** Meeting Assistant starts the recording with the accepted appointment's metadata
|
||||
- **AND** does not perform a standalone current-meeting metadata lookup for that recording
|
||||
- **AND** runs `created` workflow rules before writing the cached appointment metadata
|
||||
- **AND** runs `collecting metadata` to `transcribing` workflow rules after writing the cached appointment metadata
|
||||
|
||||
#### Scenario: Prompt is disabled
|
||||
- **GIVEN** scheduled Outlook recording prompts are disabled
|
||||
- **WHEN** a Teams appointment reaches its scheduled start
|
||||
- **THEN** Meeting Assistant does not query Outlook for recording prompt candidates
|
||||
- **AND** does not show a recording prompt
|
||||
|
||||
### Requirement: Windows Outlook enrichment is optional
|
||||
Meeting Assistant SHALL gate Outlook Classic COM enrichment behind the Windows compilation target.
|
||||
|
||||
When the Windows build starts a meeting and Outlook Classic has exactly one current Teams appointment, Meeting Assistant SHALL copy the appointment title to the meeting note and copy the appointment agenda and scheduled end time to the assistant-context frontmatter.
|
||||
|
||||
Meeting Assistant SHALL exclude canceled Outlook appointments from current Teams appointment metadata lookup.
|
||||
|
||||
Meeting Assistant SHALL copy the appointment attendees to the meeting note only when the raw appointment attendee count is less than or equal to the configured `Recording:MaxMetadataAttendeeImportCount`. The default maximum SHALL be 30 attendees.
|
||||
|
||||
The agenda SHALL be extracted from the appointment body content before the Teams join separator or Teams join text.
|
||||
|
||||
#### Scenario: Current Teams appointment enriches meeting artifacts
|
||||
- **WHEN** a Windows build starts a meeting while Outlook Classic exposes exactly one current Teams appointment
|
||||
- **THEN** Meeting Assistant uses the appointment subject as the meeting title
|
||||
- **AND** writes the appointment attendees into meeting note frontmatter when the raw attendee count is within the configured import limit
|
||||
- **AND** writes the appointment agenda into assistant-context frontmatter
|
||||
- **AND** writes the appointment end time as `scheduled_end` into assistant-context frontmatter
|
||||
|
||||
#### Scenario: Canceled appointment is ignored during metadata lookup
|
||||
- **GIVEN** Outlook Classic exposes one canceled current Teams appointment
|
||||
- **AND** Outlook Classic exposes one active current Teams appointment at the same time
|
||||
- **WHEN** a Windows build starts a meeting
|
||||
- **THEN** Meeting Assistant selects the active appointment metadata
|
||||
|
||||
#### Scenario: Oversized attendee list is not imported
|
||||
- **GIVEN** the configured metadata attendee import limit is 30
|
||||
- **WHEN** a Windows build starts a meeting while Outlook Classic exposes exactly one current Teams appointment with 31 attendees
|
||||
- **THEN** Meeting Assistant uses the appointment subject as the meeting title
|
||||
- **AND** does not write the appointment attendees into meeting note frontmatter
|
||||
- **AND** writes the appointment agenda into assistant-context frontmatter
|
||||
- **AND** writes the appointment end time as `scheduled_end` into assistant-context frontmatter
|
||||
|
||||
#### Scenario: Outlook is unavailable or ambiguous
|
||||
- **WHEN** Outlook Classic is unavailable or more than one current Teams appointment is found
|
||||
- **THEN** Meeting Assistant starts the recording with the default generated meeting title and empty agenda
|
||||
- **AND** omits `scheduled_end` from assistant-context frontmatter
|
||||
@@ -0,0 +1,6 @@
|
||||
- [x] 1. Add OpenSpec scenario for prompt-accepted metadata.
|
||||
- [x] 2. Add failing behavior coverage for prompted metadata starts.
|
||||
- [x] 3. Pass prompted metadata through the scheduler/controller/coordinator start path.
|
||||
- [x] 4. Populate cached Outlook prompt candidates with metadata.
|
||||
- [x] 5. Exclude canceled Outlook appointments from recording prompts and metadata lookup.
|
||||
- [x] 6. Run focused tests, full tests, and `openspec validate use-prompted-calendar-metadata --strict`.
|
||||
@@ -55,6 +55,18 @@ Meeting Assistant SHALL clamp mixed samples after gain is applied.
|
||||
|
||||
Meeting Assistant SHALL write only the mixed stream to the temporary WAV used by transcription and finalization.
|
||||
|
||||
Meeting Assistant SHALL allow `Recording:MicrophoneDeviceId` to select a Windows microphone capture endpoint.
|
||||
|
||||
When `Recording:MicrophoneDeviceId` is blank or absent, Meeting Assistant SHALL use the Windows default capture endpoint.
|
||||
|
||||
When a microphone is selected from the tray icon menu, Meeting Assistant SHALL use that selected microphone for later recording starts until another microphone is selected or the process exits.
|
||||
|
||||
The tray icon right-click menu SHALL expose a `Microphone` submenu listing active microphone capture endpoints.
|
||||
|
||||
The `Microphone` submenu SHALL mark exactly one effective microphone as checked.
|
||||
|
||||
When no runtime microphone override is selected, the checked microphone SHALL be the configured microphone when it is available, otherwise the Windows default capture endpoint.
|
||||
|
||||
#### Scenario: Both sources produce audio
|
||||
- **WHEN** microphone and computer output audio chunks are available
|
||||
- **THEN** Meeting Assistant mixes them into one PCM stream before transcription
|
||||
@@ -101,6 +113,29 @@ Meeting Assistant SHALL write only the mixed stream to the temporary WAV used by
|
||||
- **WHEN** automated tests run without live audio devices
|
||||
- **THEN** Meeting Assistant verifies the audio mixer through deterministic source abstractions rather than depending on physical microphone or speaker devices
|
||||
|
||||
#### Scenario: Configured microphone is used for capture
|
||||
- **GIVEN** `Recording:MicrophoneDeviceId` identifies an active microphone endpoint
|
||||
- **WHEN** Meeting Assistant starts microphone capture
|
||||
- **THEN** it captures from that endpoint
|
||||
|
||||
#### Scenario: Blank microphone setting uses Windows default
|
||||
- **GIVEN** `Recording:MicrophoneDeviceId` is blank
|
||||
- **WHEN** Meeting Assistant starts microphone capture
|
||||
- **THEN** it captures from the Windows default capture endpoint
|
||||
|
||||
#### Scenario: Tray menu lists microphones with current selection checked
|
||||
- **GIVEN** active microphone endpoints `integrated microphone` and `other microphone`
|
||||
- **AND** `integrated microphone` is the effective microphone
|
||||
- **WHEN** the taskbar menu is opened
|
||||
- **THEN** it shows a `Microphone` submenu
|
||||
- **AND** the `integrated microphone` item is checked
|
||||
- **AND** the `other microphone` item is unchecked
|
||||
|
||||
#### Scenario: Tray microphone selection changes later capture
|
||||
- **GIVEN** active microphone endpoints `integrated microphone` and `other microphone`
|
||||
- **WHEN** the user selects `other microphone` from the taskbar microphone submenu
|
||||
- **THEN** later recording starts capture from `other microphone`
|
||||
|
||||
### Requirement: Stopping recording drains captured audio through transcription
|
||||
Meeting Assistant SHALL stop capturing new audio when recording mode is stopped, but it SHALL allow already captured audio to finish running through the configured speech recognition pipeline before the recording session completes.
|
||||
|
||||
@@ -180,7 +215,7 @@ When switching profiles during an active meeting, Meeting Assistant SHALL keep t
|
||||
|
||||
When switching profiles during an active meeting, Meeting Assistant SHALL NOT create new meeting artifacts, SHALL NOT collect calendar metadata again, and SHALL NOT run the summary pipeline for the old profile segment.
|
||||
|
||||
When switching profiles during an active meeting, Meeting Assistant SHALL stop and drain the current speech recognition pipeline, append a transcript marker indicating the target profile, start a new speech recognition pipeline using the target profile's resolved options, and continue writing live transcription to the same transcript file.
|
||||
When switching profiles during an active meeting, Meeting Assistant SHALL stop and drain the current speech recognition pipeline, append a transcript marker indicating the target profile and that speaker recognition and identities were reset, start a new speech recognition pipeline using the target profile's resolved options, and continue writing live transcription to the same transcript file.
|
||||
|
||||
When audio is captured while the old speech recognition pipeline is draining, Meeting Assistant SHALL buffer that audio and send it to the new profile's speech recognition pipeline after it is ready.
|
||||
|
||||
@@ -192,6 +227,7 @@ When switching profiles during an active meeting, Meeting Assistant SHALL clear
|
||||
- **THEN** Meeting Assistant keeps the existing meeting artifacts
|
||||
- **AND** drains the old speech recognition pipeline without running summary generation
|
||||
- **AND** appends a transcript marker for the profile switch
|
||||
- **AND** the transcript marker states that speaker recognition and identities were reset
|
||||
- **AND** starts transcription with the resolved `english` profile
|
||||
- **AND** continues writing transcript segments to the same transcript file
|
||||
|
||||
@@ -199,7 +235,7 @@ When switching profiles during an active meeting, Meeting Assistant SHALL clear
|
||||
- **GIVEN** a meeting is switching from one launch profile to another
|
||||
- **WHEN** audio chunks are captured before the new speech recognition pipeline is ready
|
||||
- **THEN** Meeting Assistant buffers those chunks
|
||||
- **AND** sends the buffered chunks to the new speech recognition pipeline after it starts
|
||||
- **AND** sends the buffered chunks to the new profile's speech recognition pipeline after it starts
|
||||
|
||||
#### Scenario: Switching clears future speaker mappings only
|
||||
- **GIVEN** a live speaker label was mapped to a named speaker before switching profiles
|
||||
@@ -216,6 +252,8 @@ When a new meeting is actively recording while an older stopped meeting is still
|
||||
|
||||
The taskbar icon right-click menu SHALL expose recording controls based on the current state and configured launch profiles.
|
||||
|
||||
The taskbar icon right-click menu SHALL expose an Exit action in every recording state.
|
||||
|
||||
When Meeting Assistant is idle or only processing older stopped meetings, the menu SHALL allow starting a meeting recording for each configured launch profile.
|
||||
|
||||
When a meeting is actively recording, the menu SHALL allow stopping the recording and continuing transcription/summary generation.
|
||||
@@ -224,6 +262,10 @@ When a meeting is actively recording, the menu SHALL allow canceling the recordi
|
||||
|
||||
When a meeting is actively recording, the menu SHALL allow switching to each configured launch profile other than the current active profile.
|
||||
|
||||
Selecting Exit while Meeting Assistant is idle SHALL stop the application without an additional confirmation prompt.
|
||||
|
||||
Selecting Exit while Meeting Assistant is recording, transcribing, recognizing speakers, or summarizing SHALL show a confirmation dialog before stopping the application.
|
||||
|
||||
#### Scenario: Idle tray menu can start configured profiles
|
||||
- **GIVEN** launch profiles `default` and `english` are configured
|
||||
- **AND** no meeting recording is active
|
||||
@@ -243,6 +285,21 @@ When a meeting is actively recording, the menu SHALL allow switching to each con
|
||||
- **WHEN** a newer meeting is actively recording
|
||||
- **THEN** the taskbar icon indicates recording
|
||||
|
||||
#### Scenario: Tray menu always exposes Exit
|
||||
- **GIVEN** Meeting Assistant is running
|
||||
- **WHEN** the taskbar menu is opened
|
||||
- **THEN** it offers an Exit action
|
||||
|
||||
#### Scenario: Idle Exit stops immediately
|
||||
- **GIVEN** no recording, transcription, speaker recognition, or summary work is running
|
||||
- **WHEN** the user selects Exit from the taskbar menu
|
||||
- **THEN** Meeting Assistant stops the application without an additional confirmation prompt
|
||||
|
||||
#### Scenario: In-progress Exit asks for confirmation
|
||||
- **GIVEN** Meeting Assistant is recording, transcribing, recognizing speakers, or summarizing
|
||||
- **WHEN** the user selects Exit from the taskbar menu
|
||||
- **THEN** Meeting Assistant asks for confirmation before stopping the application
|
||||
|
||||
### Requirement: Recording inactivity safeguard stops forgotten meetings
|
||||
Meeting Assistant SHALL track transcript inactivity during an active recording from the later of meeting start or the most recent live transcript segment that contains text.
|
||||
|
||||
@@ -305,3 +362,4 @@ When a recording stops normally and its meeting note, transcript, and assistant
|
||||
- **WHEN** the recording stops normally
|
||||
- **THEN** Meeting Assistant deletes the run artifacts
|
||||
- **AND** does not run summary generation
|
||||
|
||||
|
||||
@@ -80,6 +80,8 @@ Meeting Assistant SHALL gate Outlook Classic COM enrichment behind the Windows c
|
||||
|
||||
When the Windows build starts a meeting and Outlook Classic has exactly one current Teams appointment, Meeting Assistant SHALL copy the appointment title to the meeting note and copy the appointment agenda and scheduled end time to the assistant-context frontmatter.
|
||||
|
||||
Meeting Assistant SHALL exclude canceled Outlook appointments from current Teams appointment metadata lookup.
|
||||
|
||||
Meeting Assistant SHALL copy the appointment attendees to the meeting note only when the raw appointment attendee count is less than or equal to the configured `Recording:MaxMetadataAttendeeImportCount`. The default maximum SHALL be 30 attendees.
|
||||
|
||||
The agenda SHALL be extracted from the appointment body content before the Teams join separator or Teams join text.
|
||||
@@ -91,6 +93,12 @@ The agenda SHALL be extracted from the appointment body content before the Teams
|
||||
- **AND** writes the appointment agenda into assistant-context frontmatter
|
||||
- **AND** writes the appointment end time as `scheduled_end` into assistant-context frontmatter
|
||||
|
||||
#### Scenario: Canceled appointment is ignored during metadata lookup
|
||||
- **GIVEN** Outlook Classic exposes one canceled current Teams appointment
|
||||
- **AND** Outlook Classic exposes one active current Teams appointment at the same time
|
||||
- **WHEN** a Windows build starts a meeting
|
||||
- **THEN** Meeting Assistant selects the active appointment metadata
|
||||
|
||||
#### Scenario: Oversized attendee list is not imported
|
||||
- **GIVEN** the configured metadata attendee import limit is 30
|
||||
- **WHEN** a Windows build starts a meeting while Outlook Classic exposes exactly one current Teams appointment with 31 attendees
|
||||
@@ -115,6 +123,8 @@ Meeting Assistant SHALL schedule recording-start prompts from the cached calenda
|
||||
|
||||
Meeting Assistant SHALL consider Teams appointments from Outlook calendar data as initial prompt candidates. The detection MAY be extended later for other meeting providers.
|
||||
|
||||
Meeting Assistant SHALL exclude canceled Outlook appointments from recording-start prompt candidates.
|
||||
|
||||
When a Teams appointment reaches its scheduled start window, Meeting Assistant SHALL show a native Windows app notification asking whether to record the meeting, with affirmative and negative actions.
|
||||
|
||||
On Windows, the recording-start notification SHALL request reminder-style toast behavior and remain actionable for 5 minutes.
|
||||
@@ -127,6 +137,14 @@ If the user accepts the recording prompt while another recording is active, Meet
|
||||
|
||||
When stopping an active recording for an accepted prompt, Meeting Assistant SHALL use the normal stop path so empty or too-short recordings are removed according to existing settings and other completed recordings continue normal transcription, speaker recognition, and summary processing.
|
||||
|
||||
When the user accepts a recording prompt, Meeting Assistant SHALL start the recording with the accepted cached appointment's metadata and SHALL NOT perform a separate current-meeting metadata lookup for that prompted start.
|
||||
|
||||
Prompted-start metadata SHALL include the accepted appointment title, attendees, agenda, and scheduled end when those values are available from the cached appointment.
|
||||
|
||||
Prompted starts SHALL run the normal meeting workflow `created` rules before applying the accepted appointment metadata.
|
||||
|
||||
After `created` rules run, prompted starts SHALL apply the accepted appointment metadata and then run the normal `collecting metadata` to `transcribing` state-transition workflow rules with that metadata available in the meeting note.
|
||||
|
||||
#### Scenario: Teams meeting start prompts the user
|
||||
- **GIVEN** scheduled Outlook recording prompts are enabled
|
||||
- **AND** Meeting Assistant has synced Outlook Classic Teams appointments for today
|
||||
@@ -135,6 +153,12 @@ When stopping an active recording for an accepted prompt, Meeting Assistant SHAL
|
||||
- **AND** the notification remains actionable for 5 minutes
|
||||
- **AND** marks that appointment as prompted for the day
|
||||
|
||||
#### Scenario: Canceled Teams meeting does not prompt recording
|
||||
- **GIVEN** scheduled Outlook recording prompts are enabled
|
||||
- **AND** Meeting Assistant has synced a canceled Outlook Classic Teams appointment for today
|
||||
- **WHEN** the canceled appointment reaches its scheduled start window
|
||||
- **THEN** Meeting Assistant does not show a recording prompt for that appointment
|
||||
|
||||
#### Scenario: Back-to-back cached Teams meetings prompt without another Outlook sync
|
||||
- **GIVEN** scheduled Outlook recording prompts are enabled
|
||||
- **AND** Meeting Assistant has synced two Teams appointments for today that start ten minutes apart
|
||||
@@ -155,6 +179,15 @@ When stopping an active recording for an accepted prompt, Meeting Assistant SHAL
|
||||
- **THEN** Meeting Assistant stops the active recording normally
|
||||
- **AND** starts a new recording normally after the stop request
|
||||
|
||||
#### Scenario: Accepted prompt supplies meeting metadata
|
||||
- **GIVEN** scheduled Outlook recording prompts are enabled
|
||||
- **AND** Meeting Assistant has cached two current Teams appointments with different metadata
|
||||
- **WHEN** the user accepts the recording prompt for one appointment
|
||||
- **THEN** Meeting Assistant starts the recording with the accepted appointment's metadata
|
||||
- **AND** does not perform a standalone current-meeting metadata lookup for that recording
|
||||
- **AND** runs `created` workflow rules before writing the cached appointment metadata
|
||||
- **AND** runs `collecting metadata` to `transcribing` workflow rules after writing the cached appointment metadata
|
||||
|
||||
#### Scenario: Prompt is disabled
|
||||
- **GIVEN** scheduled Outlook recording prompts are disabled
|
||||
- **WHEN** a Teams appointment reaches its scheduled start
|
||||
@@ -366,3 +399,4 @@ Meeting Assistant SHALL provide a diagnostic endpoint that opens the workflow ru
|
||||
- **GIVEN** the rules editor chat window content fits without scrolling or is already near the bottom
|
||||
- **WHEN** a new user or assistant message is appended
|
||||
- **THEN** the conversation scrolls to the bottom of the newly rendered message content
|
||||
|
||||
|
||||
@@ -4,32 +4,22 @@
|
||||
TBD - created by archiving change define-meeting-assistant-v1. Update Purpose after archive.
|
||||
## Requirements
|
||||
### Requirement: Meeting Assistant generates meeting outputs
|
||||
The summary note SHALL keep frontmatter links to meeting artifacts and SHALL copy `title`, `start_time`, `end_time`, `attendees`, and `projects` from the meeting note when available. If the meeting note has no title, the summary agent SHALL be able to provide a title when writing the summary.
|
||||
The settings/logs agent SHALL instruct meeting-note correction workflows to keep project knowledge consistent when the corrected meeting note has project references.
|
||||
|
||||
When the summary agent calls `write_summary` with a non-empty `title` parameter, Meeting Assistant SHALL update the current meeting note title and write that title to the summary note frontmatter.
|
||||
When a corrected meeting note adds a new project reference, the settings/logs agent SHALL inspect the corrected note broadly enough to find project-relevant information that should be written to that project.
|
||||
|
||||
When the summary agent calls `write_summary` without a `title` parameter or with a blank `title` parameter, Meeting Assistant SHALL keep the existing meeting note title and summary title behavior.
|
||||
When a corrected meeting note changes specific content for an existing project reference, the settings/logs agent SHALL check whether corresponding project knowledge needs the same correction.
|
||||
|
||||
The summary instructions SHALL tell the summary agent to provide a concise `title` parameter to `write_summary` when the meeting note still has a generated default title and the meeting purpose is clear from context.
|
||||
For each affected project, when an `AGENTS.md` file exists directly in the project folder, the settings/logs agent SHALL follow those project instructions before updating the project. When no project `AGENTS.md` exists, the settings/logs agent SHALL use judgment to decide what project file updates are warranted by the note correction.
|
||||
|
||||
#### Scenario: Summary agent renames default-titled meeting
|
||||
- **GIVEN** the current meeting note has a generated default title
|
||||
- **AND** the meeting purpose is clear from transcript, user notes, or assistant context
|
||||
- **WHEN** the summary agent writes the summary
|
||||
- **THEN** the summary instructions tell the agent to provide a concise `title` parameter
|
||||
- **AND** Meeting Assistant updates the meeting note title and summary note title to the provided title
|
||||
|
||||
#### Scenario: Summary title parameter is omitted
|
||||
- **GIVEN** the current meeting note has an existing title
|
||||
- **WHEN** the summary agent writes the summary without a title parameter
|
||||
- **THEN** Meeting Assistant keeps the existing meeting note title
|
||||
- **AND** writes the existing title to the summary note frontmatter
|
||||
|
||||
#### Scenario: Summary title parameter is blank
|
||||
- **GIVEN** the current meeting note has an existing title
|
||||
- **WHEN** the summary agent writes the summary with a blank title parameter
|
||||
- **THEN** Meeting Assistant keeps the existing meeting note title
|
||||
- **AND** writes the existing title to the summary note frontmatter
|
||||
#### Scenario: Settings/logs agent syncs corrected meeting notes to projects
|
||||
- **GIVEN** the settings/logs agent corrects a meeting note with project references
|
||||
- **WHEN** a referenced project has an `AGENTS.md`
|
||||
- **THEN** the settings/logs instructions tell the agent to follow that project's instructions before updating the project
|
||||
- **WHEN** a corrected note adds a new project reference
|
||||
- **THEN** the instructions tell the agent to review the corrected note for project-relevant information to add to that project
|
||||
- **WHEN** a corrected note changes specific information for an existing project reference
|
||||
- **THEN** the instructions tell the agent to check whether project knowledge needs a matching correction
|
||||
|
||||
### Requirement: Meeting screenshots are captured into assistant context
|
||||
Meeting Assistant SHALL expose a configurable screenshot hotkey.
|
||||
@@ -50,6 +40,14 @@ When OCR returns valid crop coordinates within the original image bounds, Meetin
|
||||
|
||||
When OCR returns no crop coordinates or invalid crop coordinates, Meeting Assistant SHALL keep the original screenshot link and OCR result without writing a cropped image.
|
||||
|
||||
After transcription finishes and before summarization starts, Meeting Assistant SHALL scan the meeting note for user-authored Obsidian image embeds and Markdown image embeds.
|
||||
|
||||
When configured screenshot OCR is enabled and the meeting note contains image embeds, Meeting Assistant SHALL append each resolvable image to the assistant context note, state that the image came from the meeting note, preserve the original embed text for cross-reference, and run OCR for the linked image.
|
||||
|
||||
Meeting-note image OCR SHALL NOT copy the image file, SHALL NOT write crop images, SHALL NOT add attendees from OCR metadata, and SHALL NOT modify the meeting note.
|
||||
|
||||
Meeting Assistant SHALL wait for meeting-note image OCR to finish or time out before transitioning the assistant context to summarizing.
|
||||
|
||||
When screenshot OCR is not configured, Meeting Assistant SHALL skip OCR and keep the screenshot link.
|
||||
|
||||
The default OCR prompt SHALL explain that the image is from a meeting and ask the model to identify who is talking, who is presenting, what is presented, capture slide text in markdown, convert diagrams to Mermaid when possible, indicate whether visible people are clearly the exact meeting participants or only a partial result, return crop coordinates only for confidently isolated presentation/shared-screen content, and otherwise describe the scene.
|
||||
@@ -73,6 +71,16 @@ The default OCR prompt SHALL explain that the image is from a meeting and ask th
|
||||
- **THEN** Meeting Assistant saves a cropped screenshot beside the original image
|
||||
- **AND** links the cropped screenshot before the OCR text in assistant context
|
||||
|
||||
#### Scenario: Meeting note image embeds are OCRed before summarization
|
||||
- **GIVEN** screenshot OCR is configured
|
||||
- **AND** the meeting note contains `![[whiteboard.png]]`
|
||||
- **AND** the meeting note contains ``
|
||||
- **WHEN** transcription finishes
|
||||
- **THEN** Meeting Assistant appends both images to the assistant context as images from the meeting note
|
||||
- **AND** includes the original embed text for each image
|
||||
- **AND** runs OCR for each image without copying files, writing crop images, adding attendees, or modifying the meeting note
|
||||
- **AND** waits for this OCR to finish or time out before transitioning to summarizing
|
||||
|
||||
#### Scenario: OCR is skipped when not configured
|
||||
- **GIVEN** screenshot OCR is not configured
|
||||
- **WHEN** the user captures a screenshot
|
||||
@@ -131,3 +139,4 @@ The summary-agent instructions SHALL tell the agent to keep the one-line summary
|
||||
- **WHEN** the summary agent calls `write_summary` with a one-line summary containing a line break
|
||||
- **THEN** Meeting Assistant refuses the write
|
||||
- **AND** does not mark the summary as written
|
||||
|
||||
|
||||
@@ -125,6 +125,24 @@ When Azure Speech is the configured speech recognition pipeline, Meeting Assista
|
||||
|
||||
When Azure Speech is the configured speech recognition pipeline, Meeting Assistant SHALL use the live Azure conversation transcription segments as the finished transcript without running pyannote finalization.
|
||||
|
||||
When Azure Speech reports a transient connectivity interruption, Meeting Assistant SHALL keep accepting captured audio into the active in-process pipeline buffer.
|
||||
|
||||
When Azure Speech is reconnecting, Meeting Assistant SHALL write a transcript marker in the form `<Reconnecting... n/m>`.
|
||||
|
||||
When Azure Speech emits the next real transcript segment after reconnecting, Meeting Assistant SHALL replace the latest reconnect marker with that transcript segment.
|
||||
|
||||
When Azure Speech cannot reconnect after the configured immediate retry attempts, Meeting Assistant SHALL write a transcript marker explaining that Azure Speech is disconnected, recording can continue, and transcription/summarization will continue after Azure reconnects.
|
||||
|
||||
After Azure Speech reconnects through a new SDK session, Meeting Assistant SHALL clear live speaker-label assumptions for future Azure speaker labels.
|
||||
|
||||
When Azure Speech is still unavailable after recording stops and transcription cannot drain before the configured stop-processing timeout, Meeting Assistant SHALL persist the stopped meeting as a durable transcription backlog item that references the completed mixed WAV and meeting artifacts.
|
||||
|
||||
When a stopped meeting is persisted to the durable transcription backlog, Meeting Assistant SHALL release the active recording slot so another meeting can be recorded while the stopped meeting waits for Azure Speech to become available.
|
||||
|
||||
When Azure Speech becomes available again, Meeting Assistant SHALL retry durable backlog items, rewrite the transcript from the recorded WAV, run the normal post-transcription meeting completion and summary flow, and remove the backlog item after successful completion.
|
||||
|
||||
When Meeting Assistant starts, it SHALL preserve WAV files that are referenced by durable transcription backlog items instead of deleting them as stale temporary recordings.
|
||||
|
||||
#### Scenario: Azure Speech pipeline is configured
|
||||
- **WHEN** the configured provider is `azure-speech`
|
||||
- **THEN** Meeting Assistant streams captured PCM chunks to Azure AI Speech conversation transcription through the configured speech recognition pipeline without changing recording control or transcript persistence code
|
||||
@@ -145,6 +163,32 @@ When Azure Speech is the configured speech recognition pipeline, Meeting Assista
|
||||
- **WHEN** the configured provider is `azure-speech` and live Azure transcript segments exist
|
||||
- **THEN** Meeting Assistant uses the live Azure conversation transcript segments as the finished transcript
|
||||
|
||||
#### Scenario: Azure reconnect marker is replaced by next transcript line
|
||||
- **GIVEN** Azure Speech reports a transient connectivity interruption
|
||||
- **WHEN** Meeting Assistant writes `<Reconnecting... 1/5>` and Azure later emits a transcript segment
|
||||
- **THEN** Meeting Assistant replaces the reconnect marker with the transcript segment
|
||||
- **AND** keeps later transcript lines intact
|
||||
|
||||
#### Scenario: Azure disconnected marker keeps meeting recording alive
|
||||
- **GIVEN** Azure Speech cannot reconnect after the configured immediate retry attempts
|
||||
- **WHEN** meeting audio continues to be captured
|
||||
- **THEN** Meeting Assistant writes a transcript marker explaining that Azure Speech is disconnected
|
||||
- **AND** keeps buffering captured audio in the active process for later transcription
|
||||
|
||||
#### Scenario: Stopped Azure meeting is queued durably while offline
|
||||
- **GIVEN** Azure Speech cannot finish transcription before the recording stop-processing timeout
|
||||
- **WHEN** the user stops the meeting
|
||||
- **THEN** Meeting Assistant persists a durable backlog item for the stopped meeting
|
||||
- **AND** keeps the completed mixed WAV referenced by that backlog item
|
||||
- **AND** returns to an idle recording state so another meeting can start
|
||||
|
||||
#### Scenario: Durable Azure backlog resumes after connectivity returns
|
||||
- **GIVEN** a stopped Azure meeting exists in the durable transcription backlog
|
||||
- **WHEN** Azure Speech can transcribe the recorded WAV
|
||||
- **THEN** Meeting Assistant rewrites the transcript from the recorded WAV
|
||||
- **AND** runs meeting completion and summarization
|
||||
- **AND** removes the durable backlog item and its temporary WAV after successful completion
|
||||
|
||||
### Requirement: FunASR can provide speaker-attributed streaming transcription
|
||||
Meeting Assistant SHALL provide a FunASR speech recognition pipeline that streams PCM audio to a configured FunASR WebSocket endpoint.
|
||||
|
||||
@@ -521,3 +565,4 @@ When pyannote secondary validation is enabled, Meeting Assistant SHALL start a n
|
||||
- **WHEN** Meeting Assistant starts
|
||||
- **THEN** it begins preparing the configured pyannote runtime image and model cache without waiting for the first validation request
|
||||
- **AND** application startup is not blocked by the warm-up task
|
||||
|
||||
|
||||
Reference in New Issue
Block a user