diff --git a/README.md b/README.md index 42afe70..fe29fb0 100644 --- a/README.md +++ b/README.md @@ -240,6 +240,10 @@ Full field and workflow reference: [`skills/docket/SKILL.md`](skills/docket/SKIL ## Digests +

+ The dashboard home page: a digest with a summary, highlights, source chips, a 'since the previous digest' card and metric tiles, with a Tasks card and a timeline of digests on the side +

+ Ask your agent *"make a digest"* (or *"зроби дайджест"*). The `docket:digest` skill reads your merge requests, pull requests, Notion tickets, local commits and docket items, checks every status at the source, and publishes the result — @@ -256,6 +260,24 @@ the digest can be split into groups such as work, learning and side projects. Wh (the `docket:digest-setup` skill writes it); the digests themselves sync to paired devices. Details: [`docs/digests.md`](docs/digests.md). +- **What changed** since the previous digest is computed when it is published — + new items, status changes, what dropped out — not left to the agent's memory. +- **Who does what:** every item can name its owner (you, a teammate, the + agent); **By person** turns the digest into numbered next steps per person. +- **Depth where it matters:** routine items stay one line; blocked, failing or + stale ones carry the agent's analysis of the actual cause and next step. +- **Hand it off by number:** tell any agent *"take 7"* — `digest_take` gives it + the brief and a task claimed in its name; it closes the task with the reason. +- **Seen** hides an item until its status changes; marks sync across devices. +- **Yours to shape:** groups, people, presets (*"digest work"*, *"digest + week"*), environment checks, mail and chat via MCP, a daily run — and the + skill keeps short notes on what you keep correcting. + +

+ Digest items grouped into Work, Learning and Side projects, each row numbered, with status, owner and a change badge + The same digest by person, with one blocked ticket expanded to show the agent's analysis +

+ ## CLI ```text diff --git a/docs/assets/digest-area.jpg b/docs/assets/digest-area.jpg new file mode 100644 index 0000000..c3c9b96 Binary files /dev/null and b/docs/assets/digest-area.jpg differ diff --git a/docs/assets/digest-home.jpg b/docs/assets/digest-home.jpg new file mode 100644 index 0000000..c306877 Binary files /dev/null and b/docs/assets/digest-home.jpg differ diff --git a/docs/assets/digest-people.jpg b/docs/assets/digest-people.jpg new file mode 100644 index 0000000..feb0b4e Binary files /dev/null and b/docs/assets/digest-people.jpg differ diff --git a/docs/index.html b/docs/index.html index 1d91f1c..14dc91d 100644 --- a/docs/index.html +++ b/docs/index.html @@ -273,6 +273,7 @@
- 3.0 + 3.1
- Upgrading from 2.x? The store format changes on the first write. A copy of the old - one is kept beside it and docket restore --from-v7 puts it back, so the upgrade is - reversible — but it is worth reading the two paragraphs under - Breaking / migration before - you run it. Projects your items are filed under also get more specific names in 3.0. + New: digests. Ask your agent for a digest and the dashboard's home page shows + what needs you, what shipped and what is stuck across your merge requests, pull requests, issues, + tickets and notes — with what changed since last time, who does each next step, and a number you + can hand to any agent. See it ↓ · From 3.0 it is a drop-in upgrade; coming + from 2.x, read Breaking / migration first.
@@ -361,6 +362,45 @@

One list, many projects

+
+

New in 3.1

+

A digest of your work, on the home page

+

Say make a digest to your agent. It reads your GitLab merge requests, GitHub pull requests and issues, Notion or Jira tickets, notes and mail — read-only, with the logins it already has — checks every status at the source, and publishes. Docket never holds those credentials; it keeps what the agent wrote and shows it here.

+ +
+ + + +
+
+
The dashboard home page: a digest with a summary, highlights, source chips, a 'since the previous digest' card listing status changes, and metric tiles; a Tasks card and a timeline of digests on the side
+

The latest digest: what matters, what changed since the previous one — computed, not guessed — and the task list at a glance.

+
+
+
Digest items grouped into Work, Learning and Side projects, with filter chips; each row has a number, a status pill, its owner and a 'was draft' change badge
+

Grouped by area, filtered with a click. Every row is numbered, linked to its source, and one click from becoming a task.

+
+
+
The same digest laid out by person: the user's own steps first, one item expanded to show a markdown analysis of a blocked ticket
+

By person: numbered next steps for you, for each teammate, and for the agent. Blocked or stale items carry a real analysis, not just a status.

+
+ +
+
+

Hand it off by number

+

Tell any agent take 7. It gets the full brief and a task claimed in its name, so everyone sees who is on it — and when it is done it closes the task with the reason.

+
+
+

Seen means seen

+

Mark an item seen and it stays out of the way until its status changes — an open MR you dismissed comes back the moment it merges. Marks sync across devices.

+
+
+

Yours to configure

+

Sources, groups, people, presets (digest work, digest week), environment checks and a daily run live in your own config — and the skill learns what you keep correcting.

+
+
+
+

Why not just a text file

What it adds beyond "just a list"

@@ -378,7 +418,7 @@

Scoped to your project

See what's open, on arrival

-

An optional Claude Code SessionStart hook injects what's open in this project — at most 7 items, under 120 tokens, nothing when there's nothing. It fails open: if docket is down, your session is unaffected.

+

An optional Claude Code SessionStart hook injects what's open in this project — at most 7 items, under 120 tokens, nothing when there's nothing — plus one line about your latest digest. It fails open: if docket is down, your session is unaffected.

@@ -500,7 +540,7 @@

Try it

4

Open the web UI

-

Go to http://localhost:8787 — it started itself the moment step 3 ran. Check on it from a terminal any time:

+

Go to http://localhost:8787 — it started itself the moment step 3 ran. The home page shows your latest digest (ask your agent to make a digest); the list itself is at /tasks. Check on it from a terminal any time:

$ docket status
 Mode: local
 Store: ~/.docket (from the default location)
@@ -616,16 +656,17 @@ 

It holds your only copy, so it is built like it

A todo list is not important — until it is the only record of what you were doing. Every write goes to disk atomically and durably, is checked against the exact bytes it read, and refuses rather than guesses when two processes disagree. 3.0 went through a full release-readiness audit before it shipped; all 27 blockers are closed, - each with a regression test verified to fail against the code it replaced. + each with a regression test verified to fail against the code it replaced. 3.1 adds digests without touching the store format.

-
510
tests, run on Node 18–24 and macOS
+
555
tests, run on Node 18–24 and macOS
20k
random sync topologies, all converging
3
runtime dependencies
0
accounts, trackers, telemetry

- What changed in 3.0 · + What changed in 3.1 · + How digests work · Security model · Reporting a vulnerability

@@ -646,15 +687,16 @@

It holds your only copy, so it is built like it