mirror of
https://github.com/hanzoai/insights.git
synced 2026-11-03 00:52:32 +00:00
zeekay
1b367e2b62
The tree was a debranded snapshot of upstream taken around 2026-02-20, and upstream has moved about five months since. This replaces it with upstream master, mechanically re-derived: bin/debrand does the rename, and the pipeline and squashed migrations are restored from the shipped tree. Not a merge. The previous import replaced the tree wholesale in a single commit, so there is no shared content history to merge against. Reproducing the rename on the new tree is what actually converges. What survives: .hanzo/workflows, the Dockerfiles and bin/docker* entrypoints, compose files, LLM.md, and insights/migrations. The squashed initial migration is load-bearing — the live database records it by name, so upstream's ~918 individual migrations cannot come back. Nine products are dropped as unreferenced. Twenty-one more that we do not run are kept anyway because the core app still imports them; unpicking those is a refactor and does not belong in a rebase. This base does not build yet, and the reasons are not in the rename: upstream now wants Python 3.13.13 against our 3.12.12 and Django 5.2 against our 4.2, and the dependency manifests still name upstream packages that we republish under our own names. Those are decisions, not renames.
234 lines
11 KiB
YAML
234 lines
11 KiB
YAML
# MCP tool definition — tool entries are scaffolded from the OpenAPI schema.
|
|
# The tool list and operation IDs are kept in sync automatically:
|
|
# pnpm --filter=@hanzo/mcp run scaffold-yaml -- --sync-all
|
|
#
|
|
# To enable a tool, set enabled: true and add required scopes + annotations.
|
|
# All other fields (title, description, enrich_url, etc.) are yours to configure.
|
|
category: Session replays
|
|
feature: replay
|
|
url_prefix: /replay
|
|
ui_apps:
|
|
session-recording:
|
|
type: detail
|
|
view_prop: recording
|
|
session-summary:
|
|
type: detail
|
|
view_prop: data
|
|
tools:
|
|
create-session-summaries-individually:
|
|
operation: create_session_summaries_individually
|
|
enabled: false
|
|
session-recording-bulk-delete:
|
|
operation: session_recordings_bulk_delete_create
|
|
enabled: true
|
|
scopes:
|
|
- session_recording:write
|
|
annotations:
|
|
readOnly: false
|
|
destructive: true
|
|
idempotent: true
|
|
title: Bulk delete session recordings
|
|
description: >
|
|
Delete a batch of session recordings by session ID, up to 100 per call. Deletion is permanent and cannot be
|
|
undone — confirm with the user before deleting. Prefer this over `session-recording-delete` whenever more
|
|
than one recording needs deleting: find the target IDs with `query-session-recordings-list`, then delete in
|
|
batches. Pass `date_from` (e.g. '-30d') when the recordings' age is known — it makes the lookup much faster.
|
|
IDs with no matching recording are skipped, so a `deleted_count` below `total_requested` is normal when some
|
|
recordings were already deleted or never existed.
|
|
session-recording-delete:
|
|
operation: session_recordings_destroy
|
|
enabled: true
|
|
scopes:
|
|
- session_recording:write
|
|
annotations:
|
|
readOnly: false
|
|
destructive: true
|
|
idempotent: true
|
|
title: Delete session recording
|
|
description: >
|
|
Delete a session recording by ID. This permanently removes the recording data. Use for privacy or compliance
|
|
workflows. To delete more than one recording, use `session-recording-bulk-delete` instead of calling this
|
|
repeatedly.
|
|
session-recording-get:
|
|
operation: session_recordings_retrieve
|
|
enabled: true
|
|
scopes:
|
|
- session_recording:read
|
|
annotations:
|
|
readOnly: true
|
|
destructive: false
|
|
idempotent: true
|
|
enrich_url: '{id}'
|
|
title: Get session recording
|
|
description: >
|
|
Get a specific session recording by ID. Returns full recording metadata including duration, interaction
|
|
counts, console log counts, viewing status, and a compact person summary (id, name, distinct IDs). The
|
|
person's full property bag is not included — use `persons-retrieve` when you need a person's properties.
|
|
Session recordings are reachable from events, errors, and persons via the `$session_id` property on events.
|
|
Any `$session_id` value from an event can be passed as the `id` parameter to this tool. Note: a
|
|
`$session_id` on an event does not guarantee a recording exists — session replay may not be enabled for that
|
|
project or session. A 404 means no recording was captured. If the user wants to understand what happened
|
|
without watching the recording, check `vision-observations-list` for an existing Replay Vision AI summary,
|
|
or run a summarizer scanner via `vision-scanners-scan-session` (see the investigating-replay skill; scanning
|
|
is slow). If a recording is missing (404) or the user asks why recordings aren't being captured, diagnose
|
|
with `execute-sql`: query `$recording_status`, `$session_recording_start_reason`, `$replay_sample_rate`, and
|
|
`$sdk_debug_recording_script_not_loaded` from the events table (filter by `$session_id` for a specific
|
|
session, or sample recent events for project-wide issues).
|
|
ui_app: session-recording
|
|
response:
|
|
exclude:
|
|
- person.properties
|
|
session-recording-playlist-create:
|
|
operation: session_recording_playlists_create
|
|
enabled: true
|
|
scopes:
|
|
- session_recording_playlist:write
|
|
annotations:
|
|
readOnly: false
|
|
destructive: false
|
|
idempotent: false
|
|
title: Create session recording playlist
|
|
description: >
|
|
Create a new session recording playlist. Set type to 'collection' for a manually curated list or 'filters'
|
|
for a saved filter view. Collections cannot have filters, and filter playlists must include at least one
|
|
filter criterion.
|
|
exclude_params:
|
|
- created_at
|
|
- created_by
|
|
- last_modified_at
|
|
- last_modified_by
|
|
- recordings_counts
|
|
- is_synthetic
|
|
- _create_in_folder
|
|
session-recording-playlist-get:
|
|
operation: session_recording_playlists_retrieve
|
|
enabled: true
|
|
scopes:
|
|
- session_recording_playlist:read
|
|
annotations:
|
|
readOnly: true
|
|
destructive: false
|
|
idempotent: true
|
|
title: Get session recording playlist
|
|
description: >
|
|
Get a specific session recording playlist by short_id. Returns full playlist metadata including name,
|
|
description, filters, type, and recording counts.
|
|
session-recording-playlist-update:
|
|
operation: session_recording_playlists_partial_update
|
|
enabled: true
|
|
scopes:
|
|
- session_recording_playlist:write
|
|
annotations:
|
|
readOnly: false
|
|
destructive: false
|
|
idempotent: true
|
|
title: Update session recording playlist
|
|
description: >
|
|
Update an existing session recording playlist by short_id. Can update name, description, pinned status, and
|
|
filters. Set deleted to true to soft-delete. The type field cannot be changed after creation. When updating
|
|
a filters-type playlist, you must include the existing filters alongside other field changes, otherwise the
|
|
update will fail.
|
|
exclude_params:
|
|
- created_at
|
|
- created_by
|
|
- last_modified_at
|
|
- last_modified_by
|
|
- recordings_counts
|
|
- is_synthetic
|
|
- _create_in_folder
|
|
- type
|
|
session-recording-playlists-destroy:
|
|
operation: session_recording_playlists_destroy
|
|
enabled: false
|
|
session-recording-playlists-list:
|
|
operation: session_recording_playlists_list
|
|
enabled: true
|
|
scopes:
|
|
- session_recording_playlist:read
|
|
annotations:
|
|
readOnly: true
|
|
destructive: false
|
|
idempotent: true
|
|
list: true
|
|
title: List session recording playlists
|
|
description: >
|
|
List session recording playlists in the project. Returns both user-created and synthetic (system-generated)
|
|
playlists with their metadata and recording counts.
|
|
session-recording-playlists-recordings-create:
|
|
operation: session_recording_playlists_recordings_create
|
|
enabled: false
|
|
session-recording-playlists-recordings-destroy:
|
|
operation: session_recording_playlists_recordings_destroy
|
|
enabled: false
|
|
session-recording-playlists-recordings-retrieve:
|
|
operation: session_recording_playlists_recordings_retrieve
|
|
enabled: false
|
|
session-recording-playlists-update:
|
|
operation: session_recording_playlists_update
|
|
enabled: false
|
|
session-recording-summaries-list:
|
|
operation: single_session_summaries_list
|
|
enabled: true
|
|
scopes:
|
|
- session_recording:read
|
|
annotations:
|
|
readOnly: true
|
|
destructive: false
|
|
idempotent: true
|
|
list: true
|
|
title: List session summaries
|
|
description: >
|
|
List stored AI-generated session summaries for the project, one row per session (latest summary kept). Use
|
|
to discover which sessions have already been summarized and to filter for sessions with specific problems —
|
|
`has_exceptions=true`, `outcome=failure`, or a `session_ids` narrowing (e.g. the IDs returned by
|
|
`query-session-recordings-list`). Returns lightweight rows without the full summary JSON — use
|
|
`session-recording-summary-get` for the per-segment / per-action detail. This reads persisted summaries
|
|
only; it does not trigger generation, so a session with no stored summary simply won't appear. Note: this
|
|
reads the legacy session-summary store, which is being retired — for new summaries the forward path is
|
|
Replay Vision summarizer scanners (`vision-observations-list` / `vision-scanners-observations-list`).
|
|
session-recording-summary-get:
|
|
operation: single_session_summaries_retrieve
|
|
enabled: true
|
|
scopes:
|
|
- session_recording:read
|
|
annotations:
|
|
readOnly: true
|
|
destructive: false
|
|
idempotent: true
|
|
enrich_url: '{session_id}'
|
|
title: Get session summary
|
|
description: >
|
|
Get the latest stored AI summary for a single session by `session_id` (any `$session_id` from an event).
|
|
Returns the full summary JSON — segments with a named timeline, per-action abandonment / confusion /
|
|
exception flags, segment outcomes, the headline `session_outcome`, and optional sentiment — plus
|
|
`exception_event_ids`, the `extra_summary_context` used at generation time, and `run_metadata` (LLM model,
|
|
whether visual confirmation was applied). 404 if no summary has been generated for the session yet. This
|
|
reads the legacy session-summary store, which is being retired — to create a new summary, use a Replay
|
|
Vision summarizer scanner via `vision-scanners-scan-session` rather than this read endpoint.
|
|
session-recordings-list:
|
|
operation: session_recordings_list
|
|
enabled: false
|
|
session-recordings-partial-update:
|
|
operation: session_recordings_partial_update
|
|
enabled: false
|
|
session-recordings-update:
|
|
operation: session_recordings_update
|
|
enabled: false
|
|
wrappers:
|
|
query-session-recordings-list:
|
|
schema_ref: AssistantRecordingsQuery
|
|
enabled: true
|
|
scopes:
|
|
- session_recording:read
|
|
annotations:
|
|
readOnly: true
|
|
destructive: false
|
|
idempotent: true
|
|
title: List session recordings
|
|
description_file: ./prompts/query-session-recordings-list.md
|
|
system_prompt_hint: Session replay metadata and activity
|
|
exclude_properties:
|
|
- response
|
|
- modifiers
|
|
url_prefix: /replay
|