* Add DownloadedDependency abstraction to facilitate handling of downloaded
and hash-verified dependencies.
In CI, missing hashes raise an exception.
For users, unverified downloads log a warning.
* Add DownloadedDependencyHashDatabase which manages a URL-keyed database
of sha256 hashes. It can be conveniently updated incrementally through a
script (src/solidlsp/resources/downloaded_dependency_hashes.json),
provided that language server implementations provide DownloadedDependency
instances statically
Applied in EclipseJDTLS:
* Replace the untyped nested-dict runtime dependency descriptors with DownloadedDependency instances
* Move the JDTLS version-pinning constants into DependencyProvider
* Replace the platform dependency dicts with the VSCodeJavaConfig dataclass
Utils:
* Add FileUtils.ArchiveType to type archive types that were previously plain str
* Add is_running_in_ci() to ls_utils
Updated memory on adding a language server accordingly.
Adds first-class support for xAI's Grok Build CLI, following the
existing client-integration pattern (Claude Code, CodeBuddy, Codex):
- grok context: single-project, shaped like claude-code.yml, with the
file-tool exclusions appropriate for a CLI agent that has its own
read/edit/shell tools. structured_tool_output is left at the auto
default (as in the codex and codebuddy contexts); claude-code's
explicit false is a Claude-Code-specific bug workaround that is not
carried over.
- serena setup grok: registers Serena as a user-scoped MCP server via
"grok mcp add" after detecting a compatible grok CLI.
- serena-hooks --client=grok: Grok-native PreToolUse output
({decision, reason}) instead of the Claude-style hookSpecificOutput
envelope; grep/read detection extended to Grok's tool names and
shell payloads (target_file/targetFile path keys, non-string command
values handled defensively). The payload-parsing refinements live in
the remind hook's client-agnostic parsing and apply to all hook
clients: a non-string command value previously raised, and
target_file/targetFile paths were not recognized.
- Docs (030_clients.md #grok), unit tests for setup/hooks/context, and
scripts/live_test_grok.py - a zero-inference, state-preserving live
smoke test against a real grok installation (documented in
CONTRIBUTING.md). Its M5 check verifies the structured-output wire
shape: the grok context (auto default) serves an output schema and
structuredContent for string-returning tools, while the claude-code
context (explicit false workaround) serves plain text only.
* Apply common functionality already used in JetBrainsFindDeclarationTool
* Remove location-based tool (counteracts Serena's principle to eschew line numbers)
* Apply renaming to use "find declaration" instead of "find defining symbol"
Subprocesses were not cleaned up, in particular.
* Rename SerenaAgent.shutdown to on_shutdown, because it is really a shutdown handler;
it did not perform a shutdown.
* Add new method shutdown which is now called from both sites (and which performs
the full shutdown)
* Manage the process instance used for the dashboard viewer and shut it down
explicitly.
* Initialise all variables used during shutdown immeditaly (avoiding errors when
shutdown is triggered during init)
* Improved symbol retrieval tool responses
1. FindSymbol (LS and JB) now has max_matches. Both tools now perform grouping like other symbol retrieval tools
2. When a result exceeds max_answer_chars, the caller may pass a shortened message. This is used in references and overview tools
* Progressive shortening for tool results that exceed max_answer_chars
Change _limit_length to accept an optional list of closures instead of
a single shortened_result string. Each closure produces a progressively
shorter version of the result, tried in order until one fits. The last
closure is assumed to always fit and is used unconditionally.
* Extended grouper
More flexible grouping logic was needed to achieve the above results. Grouper also no longer
mutates the input (using deepcopy)
---------
Co-authored-by: Dominik Jain <dominik.jain@oraios-ai.de>
Black dependency created a dependabot warning and couldn't be bumped since it collided with pathspec dependencies. Since ruff can also format, black is not needed. But we now have these small format changes, mostly in test files
- Added typed dicts for most responses in jetbrains_types.py
- Fix bug in code_editor (location key no longer existed, found by mypy after adding the types)
Should be merged after next version of plugin release
Added an overview (landing page showing current and available config) and advanced stats windows, controlled by top-right menu
Stats calculation is no longer optional, but we use a trivial token estimator by default
* In addition to exclusion, support notion of "optional tools" that
are disabled by default and enabled only upon request
* Unify the handling of inclusions/exclusions across
- SerenaConfig
- ProjectConfig
- SerenaAgentContext
- SerenaAgentMode
* Make ToolRegistry a singleton and simplify all related operations
- Moved symbol-reading related prompt to system prompt (from planning) since it's always need
- Use relative_path as kwarg in all tools (models get confused by different kwarg names)
- Identify and list memories without .md extension appearing
Also:
1. find_references now cannot return bodies, instead content around the reference is included
2. find_reference_snippets tool removed since it's no longer necessary
Dominik Jain