Make F1 open the complete User Guide
This commit is contained in:
Georg Bauer
@@ -1,230 +1,275 @@
|
|||||||
# DS4Server Help
|
# DS4Server User Guide
|
||||||
|
|
||||||
DS4Server runs supported DwarfStar language models locally on your Mac. Chats,
|
DS4Server is a native macOS application for running supported DwarfStar models
|
||||||
project references, and settings stay on this computer.
|
locally. Model files, chats, project references, settings, checkpoints, and
|
||||||
|
agent-extension data stay on this Mac.
|
||||||
|
|
||||||
## Projects and chats
|
## Getting started
|
||||||
|
|
||||||
Choose **Add project** to give the coding agent access to a folder. The agent's
|
1. Open **View > Model Manager** (`⇧⌘M`). Download a supported model and any
|
||||||
file tools are bounded to that project. Use **File > New Chat** (`⌘N`) to start
|
acceleration artifact you intend to use, or verify an artifact already on
|
||||||
a chat in the active project. Chats are saved after their first message and can
|
disk. A model cannot run until its complete file passes verification.
|
||||||
be renamed, pinned, archived, compacted, rebuilt, or deleted from the sidebar.
|
2. Choose **Add project** and select the folder the agent should work in. The
|
||||||
An active chat has a green dot beside its title. You can switch chats or start
|
project remains in its original location; DS4Server stores only its reference
|
||||||
another one while it works; each chat keeps its own transcript, queued prompts,
|
and chat data.
|
||||||
tools, approvals, context, and interactive UI state. Model inference shares the
|
3. Choose **File > New Chat** (`⌘N`). Select a thinking profile and a shell
|
||||||
single loaded runtime so model weights are not duplicated, while independent
|
permission mode in the composer.
|
||||||
tool work continues concurrently.
|
4. Enter a request and send it. **Thinking** is the DS4 default, **Direct** omits
|
||||||
|
hidden reasoning, and **Think Max** appears only when that model profile has
|
||||||
|
the required long context.
|
||||||
|
|
||||||
The composer status row shows the current project and, for Git repositories,
|
The selected model is shared by the app and the optional local HTTP endpoint.
|
||||||
the current local branch. An unsaved draft can be moved with the project menu;
|
Preferences are saved locally and generation settings are scoped by model and
|
||||||
saved chats keep their original project. Use the branch menu to switch local
|
thinking profile where the controls indicate that.
|
||||||
branches when that project's chats are idle. The thinking menu is preselected
|
|
||||||
to the active model's default mode and loads that model-and-thinking profile:
|
|
||||||
**Thinking** is the DS4 default, while **Direct** answers without hidden
|
|
||||||
reasoning. **Think Max** is available when its profile uses at least 393216
|
|
||||||
context tokens, matching DS4's long-context requirement.
|
|
||||||
|
|
||||||
The **Git** pane shows added, changed, and deleted files from the current
|
## Projects, chats, and context
|
||||||
worktree, including separate staged and worktree markers. Select files to stage,
|
|
||||||
unstage, or commit them, or commit the existing staged set. Committing with no
|
|
||||||
selection or staged files asks before staging and committing every change. File
|
|
||||||
names open a colored diff that can switch between unified and side-by-side
|
|
||||||
layouts. The fetch, pull, and push actions use the `origin` remote and report
|
|
||||||
authentication, hook, conflict, and other Git errors without hiding them.
|
|
||||||
|
|
||||||
Quitting with active chats asks for confirmation. Confirming stops their model
|
The sidebar switches projects and chats. Project controls add, rename, or delete
|
||||||
and tool work; canceling leaves every chat running.
|
a project reference. Deleting one removes its DS4Server sessions and
|
||||||
|
checkpoints, but never deletes the referenced folder. An unsaved draft can move
|
||||||
|
to another project; a saved chat remains attached to its original project.
|
||||||
|
|
||||||
Use **File > Export Chat as Markdown** (`⇧⌘S`) to save the visible conversation,
|
Chat controls can rename, pin, archive, restore, compact, rebuild, export, or
|
||||||
including reasoning and tool results. System-only messages are omitted.
|
delete a conversation. Archived chats remain under the project's archive until
|
||||||
|
restored or deleted. Deleting a chat permanently removes its transcript and KV
|
||||||
|
checkpoint. **File > Export Chat as Markdown** (`⇧⌘S`) saves the visible
|
||||||
|
conversation, including reasoning and tool results but excluding internal
|
||||||
|
system messages.
|
||||||
|
|
||||||
## Writing and editing
|
Send another prompt while a response is active to queue it for that chat.
|
||||||
|
**Stop** cancels current model and agent work. You can work in several chats at
|
||||||
|
once: each keeps its own transcript, prompt queue, tools, approvals, context,
|
||||||
|
and interactive surfaces. Independent tool work may overlap, but model
|
||||||
|
inference is serialized through one shared runtime so weights are not duplicated.
|
||||||
|
Quitting with active chats asks whether to stop them first.
|
||||||
|
|
||||||
Enter a prompt at the bottom of the Chat view. While a response is running,
|
The context indicator shows used and available tokens. Near the limit,
|
||||||
additional prompts are queued. **Stop** cancels generation and active agent
|
DS4Server compacts older model context while retaining the full visible
|
||||||
work. The Edit menu follows the focused text control and supports undo, redo,
|
transcript. Saved chats also keep local KV checkpoints for fast continuation.
|
||||||
cut, copy, paste, and select all. Transcript text can be selected and copied.
|
A checkpoint belongs to the exact model, quantization, context size, and runtime
|
||||||
|
configuration that created it. After one of those changes, DS4Server reports a
|
||||||
|
context rebuild, prefills the saved transcript, and writes a compatible
|
||||||
|
replacement without losing messages. **Rebuild context on next use** requests
|
||||||
|
the same safe rebuild manually.
|
||||||
|
|
||||||
The context indicator beside the composer shows used and available tokens.
|
## Agent capabilities and safety
|
||||||
DS4Server automatically compacts long chats near the context limit; the full
|
|
||||||
visible transcript remains available.
|
|
||||||
|
|
||||||
## Checkpoints and model changes
|
The coding agent can use native tools to list a directory, read files, search
|
||||||
|
file contents, write or edit files, inspect Git state, and maintain Dev Brain.
|
||||||
|
It can also run shell commands and use web search or visit pages when the task
|
||||||
|
needs them. Content search is not filename discovery: until DS4Server ships a
|
||||||
|
native filename glob tool, recursive filename lookup may require an approved
|
||||||
|
shell command. A directory listing remains a non-recursive view of one folder.
|
||||||
|
|
||||||
Each saved chat keeps a local KV checkpoint so its next turn can resume without
|
Tool calls are checked against typed schemas before execution. Unknown tools,
|
||||||
prefilling the whole conversation. A checkpoint belongs to the exact model,
|
missing or extra fields, malformed calls, and invalid values return structured
|
||||||
quantization, context size, and executor configuration that created it.
|
errors instead of running. Results appear in the transcript. Copy actions expose
|
||||||
|
their complete text, and large output may also be saved to a local file rather
|
||||||
|
than filling the transcript. **Stop** cancels active generation and cancellable
|
||||||
|
tool work.
|
||||||
|
|
||||||
If the selected model, model file, quantization, context size, or relevant
|
The shell permission mode is stored with each chat:
|
||||||
runtime configuration changes, DS4Server cannot safely resume that checkpoint.
|
|
||||||
It reports that the context is being rebuilt, prefills the saved transcript,
|
|
||||||
and writes a compatible replacement. No chat messages are lost. **Rebuild
|
|
||||||
context on next use** performs the same safe rebuild manually.
|
|
||||||
|
|
||||||
## Models
|
- **Heuristic** applies DS4Server's built-in command-risk checks.
|
||||||
|
- **AI based** asks the local model to classify a shell command in a separate
|
||||||
|
one-shot request. A risky result shows its reason. If classification fails or
|
||||||
|
is invalid, approval is required.
|
||||||
|
|
||||||
Open **View > Model Manager** (`⇧⌘M`) to download, resume, verify, or remove
|
An approval dialog shows the command and working directory. **Allow once** runs
|
||||||
supported model artifacts. Preferences choose the active model and control
|
that operation; **Deny** returns the refusal to the agent. Destructive, network,
|
||||||
generation, context, speculative decoding, Metal execution, SSD expert
|
privileged, application-control, credential, and outside-trusted-path commands
|
||||||
streaming, steering, checkpoint storage, diagnostics, and the local endpoint.
|
require approval as applicable. Dev Brain's configured vault is trusted like
|
||||||
Generation values are stored per model and thinking mode. Acceleration and SSD
|
the project for ordinary path checks, but does not bypass those risk classes.
|
||||||
values are stored per model, while the Prompt section's system prompt is shared
|
|
||||||
by every profile.
|
|
||||||
|
|
||||||
Model files are large. Verification checks the complete artifact before it is
|
### Ralph loops
|
||||||
used. Removing a model never removes projects or chat history.
|
|
||||||
|
|
||||||
## Agent tools and approvals
|
Ask the agent to use a Ralph loop when a bounded task benefits from repeated
|
||||||
|
autonomous passes, for example, “Use a Ralph loop with at most 12 rounds to fix
|
||||||
|
and verify this parser.” Ralph is an agent tool, not a view or slash command.
|
||||||
|
Its default is 8 rounds and its allowed range is 1–64.
|
||||||
|
|
||||||
The local agent can inspect and edit project files, search text, and run shell
|
Each round receives the same objective in a fresh model context, inspects the
|
||||||
commands. Operations that can affect data outside the ordinary project workflow
|
current project, and leaves file changes on disk. The next round receives only
|
||||||
show an approval dialog. Read the command and working directory before choosing
|
the previous validated report, applicable workspace instructions, and available
|
||||||
**Allow once**. Choose **Deny** to return the refusal to the agent.
|
skills. The current model settings and permission mode still apply. Ralph stops
|
||||||
|
on completion, a reported blocker, a failed round, cancellation, or the round
|
||||||
|
limit; a worker's completion report is evidence to review, not independent
|
||||||
|
certification. Ralph workers cannot start nested Ralph loops.
|
||||||
|
|
||||||
The permission selector at the bottom of each chat is stored with that session.
|
### Workspace instructions and standard skills
|
||||||
**Heuristic** uses the built-in command checks. **AI based** asks the local model
|
|
||||||
to classify each shell command in an isolated one-shot request; risky commands
|
|
||||||
show the model's reason in the normal approval dialog. If that check fails or
|
|
||||||
returns an invalid answer, DS4Server requires approval. Preferences choose the
|
|
||||||
default for new sessions. When Dev Brain is enabled, its configured vault is
|
|
||||||
treated like the project for path-risk checks; destructive, network, privilege,
|
|
||||||
application-control, and credential risks still require approval.
|
|
||||||
|
|
||||||
Tool calls and results appear in the transcript. Use their copy actions for the
|
DS4Server reads global instructions from
|
||||||
complete, untruncated text; large outputs can also be opened from their saved
|
`~/Library/Application Support/de.rfc1437.ds4server/AGENTS.md`, then project
|
||||||
file. Calls are checked against typed schemas before execution, so unknown
|
instructions from root to the working directory. In each directory,
|
||||||
tools, missing or extra fields, invalid values, and malformed tool syntax are
|
`AGENTS.local.md` overlays `AGENTS.md`. Deeper guidance wins over broader
|
||||||
returned to the agent as structured errors instead of being executed.
|
guidance, while system, developer, and direct user instructions remain higher
|
||||||
|
priority. Additions, changes, and removals are tracked during a chat and restored
|
||||||
|
after compaction; an unreadable changed file leaves its last readable version in
|
||||||
|
effect with a notice.
|
||||||
|
|
||||||
## Ralph loops
|
Manually installed standard skills live at
|
||||||
|
`~/.agents/skills/<name>/SKILL.md`. DS4Server initially gives the agent each
|
||||||
|
valid skill's name, description, and location; the agent reads the full skill
|
||||||
|
only when the task matches. These roots are readable but not writable through
|
||||||
|
agent file tools. Start a fresh chat after changing the manually installed skill
|
||||||
|
set so its prompt and tool roots agree.
|
||||||
|
|
||||||
For a bounded task that benefits from repeated autonomous passes, ask the agent
|
### Dev Brain
|
||||||
to use a Ralph loop, for example: “Use a Ralph loop with at most 12 rounds to
|
|
||||||
fix and verify this parser.” This is an agent tool, not a slash command or a
|
|
||||||
separate view. The normal default is 8 rounds and the allowed range is 1–64.
|
|
||||||
|
|
||||||
Ralph runs in the foreground. Each round receives the same immutable objective
|
Dev Brain is a project-backed Obsidian wiki for durable, source-cited engineering
|
||||||
in a fresh model context, inspects the current project as its source of truth,
|
knowledge. In **Preferences > Dev Brain**, select an existing vault containing
|
||||||
and ends with one structured report. File changes remain on disk between
|
`.obsidian`, enable it, and save. Ask the agent to build, refresh, search, or
|
||||||
rounds, but earlier conversation does not: only the previous validated report,
|
validate the wiki. DS4Server manages its contract files and explicitly marked
|
||||||
applicable workspace instructions, and available skills are handed to the next
|
topic pages, not Obsidian settings, hidden files, attachments, or unrelated
|
||||||
worker. This limits accumulated context while allowing the next round to
|
notes. Verified pages can support answers; stale or needs-review pages are leads
|
||||||
continue, verify, or repair the work.
|
that the agent must recheck against project source. Disabling Dev Brain removes
|
||||||
|
its tools and guidance without deleting the vault.
|
||||||
|
|
||||||
The current chat's model settings and permission mode still apply. Risky shell
|
## Agent extensions
|
||||||
commands and visible browser actions can therefore pause for the usual
|
|
||||||
approval. **Stop** cancels the loop and its active work. Ralph also stops when a
|
|
||||||
worker reports completion or a blocker, a child round fails, or the round limit
|
|
||||||
is reached. Completion is a worker report rather than independent
|
|
||||||
certification; review its evidence or ask the parent agent to verify it when
|
|
||||||
that distinction matters. Ralph workers cannot start nested Ralph loops.
|
|
||||||
|
|
||||||
## Workspace instructions and standard skills
|
**Preferences > Agent Extensions** installs and manages portable Codex plugins:
|
||||||
|
|
||||||
DS4Server applies workspace guidance from these locations:
|
1. Enter an HTTPS Git repository URL and, optionally, a branch, tag, or commit.
|
||||||
|
2. Choose **Install**. The repository must contain
|
||||||
|
`.codex-plugin/plugin.json` and provide at least a skills directory or a
|
||||||
|
supported lifecycle-hooks manifest.
|
||||||
|
3. Inspect the displayed description, source URL, requested ref, resolved
|
||||||
|
commit, author, version, skill count, and hook names.
|
||||||
|
4. Enable the extension. An extension with command hooks first asks for explicit
|
||||||
|
trust. Its programs run with your user permissions even though DS4Server
|
||||||
|
invokes them without a shell and limits their environment, runtime, input,
|
||||||
|
and output.
|
||||||
|
5. Use **Update** to fetch the configured source/ref, disable the toggle to stop
|
||||||
|
future use, or **Uninstall** to remove the installed package and its stored
|
||||||
|
extension data. Hook failures appear on the extension row.
|
||||||
|
|
||||||
- `~/Library/Application Support/de.rfc1437.ds4server/AGENTS.md` applies to all
|
Enable, disable, and update changes apply to subsequent matching hook events.
|
||||||
projects.
|
A current chat does not retroactively receive a `SessionStart` event. Because a
|
||||||
- `AGENTS.md` in the project root applies to that project.
|
chat's native tool roots are initialized for that session, start a fresh chat
|
||||||
- `AGENTS.md` and `AGENTS.local.md` in nested directories apply after the agent
|
after adding, updating, enabling, or disabling extension skills. An app restart
|
||||||
successfully reads, writes, or edits a file in that part of the project.
|
is not otherwise required.
|
||||||
|
|
||||||
Instructions are ordered from broad to specific. A deeper file takes
|
Extension skills are versioned inside their plugin and are managed with its
|
||||||
precedence over broader guidance, and `AGENTS.local.md` is the final overlay for
|
toggle, update, and uninstall actions. They are separate from manually installed
|
||||||
its directory. DS4Server records additions, changes, and removals during an
|
standard skills under `~/.agents/skills`. Installed packages, per-extension
|
||||||
ongoing chat and restores the applicable instruction set after context
|
data, and `registry.json` live under
|
||||||
compaction. Files that cannot be read safely produce a context notice; if the
|
`~/Library/Application Support/de.rfc1437.ds4server/extensions/`.
|
||||||
file was already tracked, its last readable version remains in effect.
|
|
||||||
Workspace instructions cannot override system, developer, or direct user
|
|
||||||
instructions.
|
|
||||||
|
|
||||||
Reusable standard skills are discovered from
|
## A2UI interactive surfaces
|
||||||
`~/.agents/skills/<name>/SKILL.md`. Each `SKILL.md` starts with YAML frontmatter:
|
|
||||||
|
|
||||||
```yaml
|
A2UI is an interactive or graphical response the agent can generate when it is
|
||||||
---
|
more useful than prose. It is not another model and is not a tool you operate
|
||||||
name: review-release
|
directly. Enable or disable it in Preferences. Ask for an interactive chart,
|
||||||
description: Review a release against this project's checklist.
|
table, form, map, or other surface, then open the **A2UI** view (`⌘2`) if the app
|
||||||
---
|
does not switch there automatically.
|
||||||
```
|
|
||||||
|
|
||||||
The directory name must match `name`; names use lowercase letters, digits, and
|
Buttons can send events back to the agent. Text fields, checkboxes, sliders,
|
||||||
single hyphens. DS4Server initially gives the agent only each valid skill's
|
date/time inputs, and choice pickers update the surface's data. Tabs and modals
|
||||||
name, description, and path. When a task matches, the agent reads the complete
|
organize content. Previous and next actions navigate saved surface history;
|
||||||
file and any needed resources from that skill directory. Standard skill files
|
**Dismiss** removes the current saved surface after confirmation. Ordinary model
|
||||||
are readable but not writable through agent tools. Install only skills you
|
prose remains in the Chat transcript. Video and audio controls open native
|
||||||
trust, place them manually before starting a chat, and start a new chat after
|
playback windows.
|
||||||
changing the installed set. There is currently no built-in skill installer or
|
|
||||||
extension marketplace.
|
|
||||||
|
|
||||||
## Dev Brain
|
The embedded catalog currently supports:
|
||||||
|
|
||||||
Dev Brain is a project-backed wiki for durable engineering knowledge. It lets
|
- Content: Markdown/text, images and avatars, icons, video, audio, and dividers.
|
||||||
the coding agent compile architecture, behavior, decisions, invariants,
|
- Layout: rows, columns, lists, cards, modals, and tabs.
|
||||||
workflows, and relationships once, then retrieve that verified context in later
|
- Controls: buttons, text fields, checkboxes, sliders, date/time inputs, and
|
||||||
chats. Registered projects remain authoritative; Dev Brain is not a general
|
single- or multiple-choice pickers.
|
||||||
memory store and never replaces checking changed source code.
|
- Visual and research components: bar, line, area, stacked-bar, pie, donut, and
|
||||||
|
heatmap charts; tables; metrics; timelines; maps; mind maps; and forms.
|
||||||
|
|
||||||
To set it up:
|
## The rest of the app
|
||||||
|
|
||||||
1. Create or choose a dedicated Obsidian vault. The folder must already contain
|
### Models and preferences
|
||||||
**.obsidian**.
|
|
||||||
2. Open **Preferences > Dev Brain**, choose the vault, enable Dev Brain, and
|
|
||||||
save.
|
|
||||||
3. In a project chat, ask the agent to build or refresh Dev Brain. Tell it the
|
|
||||||
questions and areas that matter most so it can maintain **purpose.md** and
|
|
||||||
compile a small set of useful topic pages instead of summarizing every file.
|
|
||||||
|
|
||||||
Useful requests include “Build Dev Brain for these projects,” “Refresh Dev
|
**Model Manager** downloads, resumes, verifies, and removes managed model and
|
||||||
Brain after my recent changes,” “What does Dev Brain know about the cache
|
acceleration artifacts. Removing an artifact does not remove projects or chats.
|
||||||
invariants?”, and “Check the wiki, then verify this against the source.” The
|
Preferences select the active model and its default thinking profile. Generation
|
||||||
agent gets the real vault folder from Dev Brain, then uses its normal list,
|
values are stored per model and thinking mode; acceleration and SSD settings are
|
||||||
read, search, write, and edit tools on the Markdown. A dedicated validation tool
|
stored per model; the custom system prompt is shared across profiles. Other
|
||||||
checks the result and refreshes the disposable local SQLite search index.
|
sections control A2UI, permission defaults, endpoint settings, Git diff display,
|
||||||
|
Dev Brain, extensions, checkpoint storage, and diagnostics.
|
||||||
|
|
||||||
The vault remains ordinary Obsidian Markdown:
|
### Main views, sidebar, and branches
|
||||||
|
|
||||||
- **purpose.md** records its scope, priorities, and recurring questions.
|
**Chat** shows the conversation, **A2UI** shows interactive surfaces, **Git**
|
||||||
- **schema.md** is the detailed contract the agent follows when maintaining it.
|
shows the current worktree, and **Stats** reports model, generation, HTTP, SSD,
|
||||||
- **index.md** is a generated catalog of every managed topic page.
|
and KV-cache activity. **View > Show Sidebar** (`⌘B`) hides or restores the
|
||||||
- **log.md** is an append-only history of material updates.
|
project sidebar. The composer status shows the active project and its local Git
|
||||||
- Topic pages live under **projects/**, **subsystems/**, **concepts/**,
|
branch. Branch switching is available while that project's chats are idle.
|
||||||
**decisions/**, **invariants/**, and **workflows/** as needed.
|
|
||||||
|
|
||||||
Every topic cites exact project files and a Git revision or content hash.
|
### Git
|
||||||
**Verified** pages may support answers. **Stale** pages are navigation leads
|
|
||||||
whose evidence changed, and **needs-review** pages contain visible uncertainty;
|
|
||||||
the agent must recheck project sources before relying on either. After editing,
|
|
||||||
the agent runs validation. Unsafe paths and invalid page structure or provenance
|
|
||||||
are errors to repair in place. Broken links are reported as warnings: the valid
|
|
||||||
page stays on disk, so the agent can make a small edit or create the missing
|
|
||||||
page without regenerating its work. Validation rebuilds **index.md**
|
|
||||||
deterministically instead of asking the model to keep it synchronized.
|
|
||||||
|
|
||||||
DS4Server may modify only the four contract files and topic pages explicitly
|
The Git view separates staged and worktree changes. Select files to stage,
|
||||||
marked as Dev Brain-managed. Standard agent file tools can access the vault but
|
unstage, or commit; selecting a file opens a colored unified or side-by-side
|
||||||
cannot modify Obsidian settings, hidden files, or unrelated notes. You can
|
diff. Committing with no selected or staged files asks before staging and
|
||||||
inspect, edit, link, and version the managed Markdown normally; invalid manual
|
committing every change. Fetch, pull, and push use the `origin` remote and report
|
||||||
edits are reported rather than silently trusted. Disabling Dev Brain removes its
|
authentication, hook, conflict, and other Git errors.
|
||||||
folder, search, and validation guidance from the built-in coding agent without
|
|
||||||
deleting the vault.
|
|
||||||
|
|
||||||
## Views and sidebar
|
### Local API
|
||||||
|
|
||||||
Use **View > Show Sidebar** (`⌘B`) to hide or restore the project sidebar. The
|
|
||||||
Chat view shows the transcript, A2UI shows the latest interactive surface, and
|
|
||||||
Stats reports model, generation, HTTP, SSD, and KV-cache activity.
|
|
||||||
|
|
||||||
## Local HTTP endpoint
|
|
||||||
|
|
||||||
Preferences can enable an OpenAI- and Anthropic-compatible endpoint on
|
Preferences can enable an OpenAI- and Anthropic-compatible endpoint on
|
||||||
`127.0.0.1` (port `4000` by default). Endpoint conversations are owned by their
|
`127.0.0.1`, port `4000` by default. Endpoint conversations belong to their
|
||||||
client and do not appear in the project sidebar. CORS is off by default and
|
client and do not appear in the sidebar. CORS is off by default; enable it only
|
||||||
should only be enabled for trusted local browser clients.
|
for trusted browser clients on this Mac. Saving changed endpoint settings
|
||||||
|
restarts the local listener.
|
||||||
|
|
||||||
## Data and recovery
|
### Data and recovery
|
||||||
|
|
||||||
Application data is stored under `~/Library/Application Support/de.rfc1437.ds4server/`.
|
Application data is under
|
||||||
Deleting a project from DS4Server removes its saved sessions and checkpoints,
|
`~/Library/Application Support/de.rfc1437.ds4server/`: `config.yaml` stores
|
||||||
but never deletes the referenced project folder. Deleting a session removes its
|
preferences, `data.sqlite3` stores projects and chats, `models/` stores managed
|
||||||
transcript and checkpoint permanently.
|
artifacts, `kv-cache/` stores checkpoints and metrics data, `extensions/` stores
|
||||||
|
plugins, and `browser/` stores the agent browser profile. Project source remains
|
||||||
|
where you selected it.
|
||||||
|
|
||||||
|
Removing a model can be recovered by downloading or restoring and verifying the
|
||||||
|
same artifact. A context incompatible with changed runtime settings is rebuilt
|
||||||
|
from the saved transcript. Deleted project references, chats, extension data,
|
||||||
|
and their checkpoints are not restored by DS4Server; use your own backup if you
|
||||||
|
need recovery from deletion.
|
||||||
|
|
||||||
|
## Troubleshooting
|
||||||
|
|
||||||
|
- **No model selected or model unavailable:** select a model in Preferences,
|
||||||
|
then download and verify all required artifacts in Model Manager.
|
||||||
|
- **Verification failed:** retry verification or download. DS4Server will not
|
||||||
|
load incomplete or hash-mismatched weights.
|
||||||
|
- **Context is rebuilding:** the saved checkpoint no longer matches current
|
||||||
|
model/runtime settings. Let the transcript prefill finish; messages remain.
|
||||||
|
- **Extension install failed:** use an HTTPS Git URL and verify the repository
|
||||||
|
contains a valid portable plugin manifest plus skills or supported hooks.
|
||||||
|
- **Extension hook failed:** read the error on its Preferences row, repair or
|
||||||
|
update the extension, then retry the matching event. Trust is required before
|
||||||
|
command hooks can run.
|
||||||
|
- **Tool approval denied:** the operation was not run. Send a safer request or
|
||||||
|
repeat it and approve only after checking the command and working directory.
|
||||||
|
- **A2UI is unavailable:** enable A2UI in Preferences and ask the agent for an
|
||||||
|
interactive surface in a new prompt.
|
||||||
|
|
||||||
|
## Keyboard shortcuts
|
||||||
|
|
||||||
|
These are the shortcuts registered by the native DS4Server menu. On Macs whose
|
||||||
|
top row controls brightness or media, use `fn-F1` when macOS requires it;
|
||||||
|
DS4Server does not override the system keyboard mapping.
|
||||||
|
|
||||||
|
| Shortcut | Action |
|
||||||
|
| --- | --- |
|
||||||
|
| `F1` | DS4Server User Guide |
|
||||||
|
| `⌘,` | Preferences |
|
||||||
|
| `⇧⌘M` | Model Manager |
|
||||||
|
| `⌘N` | New Chat |
|
||||||
|
| `⇧⌘S` | Export Chat as Markdown |
|
||||||
|
| `⌘B` | Show or hide the sidebar |
|
||||||
|
| `⌘1` | Chat view |
|
||||||
|
| `⌘2` | A2UI view |
|
||||||
|
| `⌘3` | Git view |
|
||||||
|
| `⌘4` | Stats view |
|
||||||
|
| `⌘Z` | Undo |
|
||||||
|
| `⇧⌘Z` | Redo |
|
||||||
|
| `⌘X` | Cut |
|
||||||
|
| `⌘C` | Copy |
|
||||||
|
| `⌘V` | Paste |
|
||||||
|
| `⌘A` | Select All |
|
||||||
|
| `⌘Q` | Quit DS4Server |
|
||||||
|
|||||||
@@ -104,15 +104,7 @@ pub(crate) fn install() -> Result<NativeMenu, String> {
|
|||||||
let a2ui = view_item(SHOW_A2UI, "A2UI", Code::Digit2, false);
|
let a2ui = view_item(SHOW_A2UI, "A2UI", Code::Digit2, false);
|
||||||
let git = view_item(SHOW_GIT, "Git", Code::Digit3, false);
|
let git = view_item(SHOW_GIT, "Git", Code::Digit3, false);
|
||||||
let stats = view_item(SHOW_STATS, "Stats", Code::Digit4, false);
|
let stats = view_item(SHOW_STATS, "Stats", Code::Digit4, false);
|
||||||
let open_help = MenuItem::with_id(
|
let open_help = help_item();
|
||||||
HELP,
|
|
||||||
"DS4Server Help",
|
|
||||||
true,
|
|
||||||
Some(Accelerator::new(
|
|
||||||
Some(Modifiers::SUPER | Modifiers::SHIFT),
|
|
||||||
Code::Slash,
|
|
||||||
)),
|
|
||||||
);
|
|
||||||
let undo = edit_item(UNDO, "Undo", Code::KeyZ, None);
|
let undo = edit_item(UNDO, "Undo", Code::KeyZ, None);
|
||||||
let redo = edit_item(REDO, "Redo", Code::KeyZ, Some(Modifiers::SHIFT));
|
let redo = edit_item(REDO, "Redo", Code::KeyZ, Some(Modifiers::SHIFT));
|
||||||
let cut = edit_item(CUT, "Cut", Code::KeyX, None);
|
let cut = edit_item(CUT, "Cut", Code::KeyX, None);
|
||||||
@@ -279,6 +271,14 @@ fn edit_item(
|
|||||||
)
|
)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
fn help_item() -> MenuItem {
|
||||||
|
MenuItem::with_id(HELP, "DS4Server User Guide", true, Some(help_accelerator()))
|
||||||
|
}
|
||||||
|
|
||||||
|
fn help_accelerator() -> Accelerator {
|
||||||
|
Accelerator::new(None, Code::F1)
|
||||||
|
}
|
||||||
|
|
||||||
#[cfg(test)]
|
#[cfg(test)]
|
||||||
mod tests {
|
mod tests {
|
||||||
use super::*;
|
use super::*;
|
||||||
@@ -299,4 +299,14 @@ mod tests {
|
|||||||
assert_eq!(stats.id().0, SHOW_STATS);
|
assert_eq!(stats.id().0, SHOW_STATS);
|
||||||
assert!(!stats.is_checked());
|
assert!(!stats.is_checked());
|
||||||
}
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn user_guide_uses_unmodified_f1() {
|
||||||
|
let accelerator = help_accelerator();
|
||||||
|
let item = help_item();
|
||||||
|
|
||||||
|
assert_eq!(item.text(), "DS4Server User Guide");
|
||||||
|
assert_eq!(accelerator.key(), Code::F1);
|
||||||
|
assert!(accelerator.modifiers().is_empty());
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user