* feat(docker): official image with all runtime deps pre-installed
Multi-stage build using uv for the EvoScientist core + all messaging-channel
extras, plus Node.js 24 LTS (for npx-based MCP servers) and uv (for runtime
Python MCP installs) in the runtime layer. Runs as non-root user evosci,
with workspace, app data, and config (XDG_CONFIG_HOME) all consolidated
under a single /home/evosci/.evoscientist volume so a single mount
persists everything across container restarts.
Includes a docker-compose.yml starter, a build/push GitHub Actions
workflow targeting ghcr.io with multi-arch (amd64/arm64) and PR-only
build verification, a .dockerignore, and a new Docker section in the
README documenting mounts, derivation recipes for the unbundled stt /
oauth / TinyTeX extras, and proxy/cert handling expectations.
* fix(docker): pin trixie base + drop redundant python image
Switch builder and runtime from `python:3.11-slim-bookworm` to a single
`ghcr.io/astral-sh/uv:python3.11-trixie-slim` base — trixie drops several
CRITICAL vulnerabilities that bookworm carries today, and reusing the uv
image for runtime eliminates the separate `COPY --from=…/uv` line.
* chore(docker): pin GitHub Actions to commit SHAs in workflow
Replace mutable major-version tags with full commit SHAs (with the
corresponding semver tag in a trailing comment) so a compromised /
retagged action release can't silently change what runs in the publish
pipeline.
* chore(deps): enable Dependabot version updates for Dockerfile pins
Adds a weekly `docker` ecosystem that watches the Dockerfile's `FROM` /
`COPY --from=` references — including the ARG-bound `BASE_IMAGE` and
`NODE_IMAGE` digests — and opens one grouped PR per cadence bumping
both the @sha256 digest and the trailing version comment. This keeps
the otherwise-frozen pins flowing with Debian point releases and
upstream patches.
* fix(docker): use nodejs alias stage so NODE_IMAGE ARG actually resolves
`COPY --from=${NODE_IMAGE}` left the dollar-curly literal at parse time
under buildkit 29.x — it expands ARGs in `FROM` but reads `--from=` as a
static stage/image name. Introduce a tiny `FROM ${NODE_IMAGE} AS nodejs`
alias and `COPY --from=nodejs …` against it, which preserves the
ARG-driven Dependabot updates without tripping the parser.
* fix(docker): harden venv ownership and PATH ordering
- Drop `--chown` on the `/opt/venv` COPY so the venv stays root-owned.
The runtime user only needs read+execute (default Unix perms allow
that); making it user-owned let the agent rewrite its own
dependencies, which defeats the sandboxing premise. All persistent
agent state already lives under /home/evosci/.evoscientist/.
- Reorder PATH so /opt/venv/bin precedes the user-writable
UV_TOOL_BIN_DIR. Otherwise a stray binary dropped into the latter
(e.g. via `uv tool install`) could shadow the canonical
`evosci` / `python` / `pip` shipped with the image.
* docs: update README
* docs(docker): warn about non-root UID and `curl | sh` for derived images
- The image runs as `evosci` (UID 1000), so a host-side `./workspace`
bind mount fails if the host user has a different UID — same gotcha
that bites onboarding's `mcp.yaml` write. Add an !IMPORTANT block
with the two practical fixes (`chown -R 1000:1000` once, or
`--user "$(id -u):$(id -g)"` on each run).
- The TinyTeX derivation snippet pipes an unpinned remote installer
into `sh`. Add a one-line pointer to fetching a pinned release
tarball from `rstudio/tinytex-releases` for users who'd rather not
trust the upstream script blindly. The official installer is kept
as the default since that's what TinyTeX itself recommends.
* chore(docker): cancel in-flight workflow runs + flag iMessage as host-only
- Add `concurrency: cancel-in-progress: true` to the docker workflow
so successive pushes on the same ref supersede the prior run rather
than queueing in parallel — multi-arch buildx is the slowest job in
CI, no point burning minutes on superseded builds.
- Spell out that the docker image installs the `all-chanels` extra and
call out iMessage as a deliberate host-only exclusion: it requires
the `imsg` CLI bridging to macOS's Messages.app, which no Linux
container config can satisfy.
* fix(onboard): detect installed skill packs via install manifest
Onboarding's _step_skills only inspected USER_SKILLS_DIR and matched
recommended entries by directory-name hint, so a pack like
EvoScientist/EvoSkills@skills (which explodes into paper-writing/,
evo-memory/, etc. under GLOBAL_SKILLS_DIR) was never detected and kept
appearing as not-yet-installed.
skills_manager now writes a per-tier .installed.yaml mapping skill
directory name -> original install source on every install, removes the
entry on uninstall, and exposes installed_sources(). _step_skills checks
both tiers and treats a recommended source as installed when present in
any manifest -- so packs are recognized regardless of how their child
dirs are named.
* fix(onboard): write install manifest atomically
Stage to a sibling temp file, fsync, then os.replace into place. A crash
mid-write can no longer leave a half-written .installed.yaml behind,
which would otherwise wipe out pack detection until the next reinstall.
* style: fmt
* fix(onboard): catch decode errors when loading install manifest
read_text() can raise UnicodeDecodeError on a hand-edited or corrupt .installed.yaml; pin encoding="utf-8" and add UnicodeError to the except clause so the function honors its "returns {} on any error" contract.
* refactor(cli): replace channel module globals with ChannelRuntime
Removes _cli_agent / _cli_thread_id from EvoScientist/cli/channel.py
and threads a ChannelRuntime via CommandContext.channel_runtime so
/model and /channel rebind without poking module-level state.
* fix(cli): address coderabbit review
- _auto_start_channel: bind ChannelRuntime only after
_start_channels_bus_mode succeeds, so a startup failure no longer
leaves a stale binding pointing at channels that never started.
- _sync_tui_command_completion (TUI) and the Rich CLI command-completion
paths: rebind the runtime on thread rotation, not just agent swap, so
/new and /resume keep ChannelRuntime in sync with the running thread
(matches the serve-mode hook contract).
- test_hook_syncs_channel_runtime: pin ctx.thread_id explicitly so a
bare MagicMock attribute can't silently mutate runtime.thread_id.
- New regression test covering the rebind-on-thread-rotation contract.
* fix(sessions): ensure migration sweep runs before yielding checkpointer to prevent race conditions
* fix(sessions): enhance migration sweep with progress indication and ETA estimation
* Implement PruningCheckpointer for efficient checkpoint management and add comprehensive tests
- Introduced `PruningCheckpointer` to manage checkpoint pruning after each `aput()`, ensuring only the latest checkpoints are retained based on a configurable limit.
- Added migration sweep functionality to clean up legacy checkpoints and prevent database bloat.
- Enhanced `get_checkpointer()` to utilize the new `PruningCheckpointer` and trigger migration sweeps when necessary.
- Developed a suite of integration tests for `PruningCheckpointer`, covering various scenarios including pruning behavior, concurrent writes, and retention policies.
- Implemented tests for migration sweep functionality, ensuring proper partitioning and user version management.
- Added diagnostic helper `db_stats` to provide insights into the database state, including thread and checkpoint counts.
* feat(sessions): enhance pruning logic to handle legacy DBs without writes table
* fix(tests): prevent atexit hook leakage in TestMigrationSweep
* feat(tests): enhance TestPruningCheckpointer to validate put+prune serialization
* feat(tests): refactor mock path implementation for get_db_path in test cases
* feat(context-window): add model context window patch table and apply function
* fix(tests): clean up formatting in context window tests
* fix(tests): update context window tests for Claude model exceptions
* feat: Refactor system prompt structure and enhance documentation for clarity
* refactor: Improve clarity and consistency in prompt documentation
* refactor(tests): Improve readability of first-person avoidance test assertion
* refactor: Remove redundant datetime imports and enhance prompt documentation
* feat: Enhance ModelPickerWidget for Ollama integration
- Implemented a sentinel row for "Custom Ollama model..." in ModelPickerWidget, allowing users to input arbitrary model names.
- Updated action handling in ModelPickerWidget to manage transitions between list and input modes.
- Added async model discovery for Ollama models, integrating with the /model command to fetch locally installed models.
- Created tests for Ollama model discovery and ModelPickerWidget behavior, ensuring proper functionality and user experience.
- Refactored validate_ollama_connection and discover_ollama_models for improved error handling and response management.
* fix: Simplify code by removing unnecessary line breaks in ModelPickerWidget and test cases
* fix: Restore globals on set_chat_model failure to prevent half-switched session
* fix: Improve error handling in ModelCommand by restoring globals on failure
* fix(chat): resolve model switch lag by tracking model/provider key for cache invalidation
* style: format set_chat_model function for improved readability
* fix(chat): improve model switching logic to prevent unnecessary cache rebuilds
* fix(model): ensure globals are restored on agent load failure to prevent model switch issues
* feat(cli): migrate command handling to CommandManager and enhance UI interactions
* feat(cli): add /clear and /help commands to enhance user experience
* feat(cli): implement /new and /resume commands with interactive session management
* Refactor MCP and Skills Command Handling
- Moved the interactive picker style to a centralized widget for consistency across MCP and Skills commands.
- Updated the MCP command to remove the old command dispatch logic, delegating to the new InstallMCPCommand.
- Enhanced the Skills command to utilize a new interactive picker for skill selection, improving user experience.
- Implemented cancellation handling in the picker to differentiate between user cancellations and empty selections.
- Added comprehensive tests for the new command structures and picker functionalities to ensure reliability.
* refactor(cli): streamline CommandManager dispatch and remove deprecated command set
* refactor(cli): enhance error handling and state management in ChannelCommand and RichCLICommandUI
* refactor(cli): update lifecycle callback terminology and improve async prompt handling in RichCLICommandUI
* refactor(cli): enhance SlashCommandCompleter to dynamically fetch workspace directory for autocompletion
* refactor(cli): unify quit handling in RichCLICommandUI with shared _stop helper
* refactor(cli): remove hardcoded slash commands and utilize command manager for dynamic completion
* refactor(cli): update MCP and skills command files for improved clarity and organization
* refactor(mcp_ui): remove unnecessary newline in _show_mcp_config function
* perf(cli): cut startup time of `evosci --help` from ~2.2s to ~0.3s
Module-level imports were eagerly pulling in langchain.chat_models (with
the whole anthropic/openai/google stack), langgraph, textual, and
prompt_toolkit on every invocation — even for `--help` or `config list`.
Defer those with PEP 562 `__getattr__`, using `lazy_loader.attach` (SPEC-1,
the scientific-python standard) where it's a clean attach pattern:
- `EvoScientist/llm/__init__.py`: attach `models` lazily so importing
`context_window` from this package no longer drags in langchain.
- `EvoScientist/stream/__init__.py`: attach display/events lazily; split
the shared Rich `Console` singleton into a new lightweight
`stream/console.py` so callers that only need `console` skip the
`stream.events` → `langchain_core.messages` chain.
- `EvoScientist/cli/__init__.py`: hand-rolled `__getattr__` (reaches into
`..stream.state`, which `lazy_loader` doesn't cover) so `commands` and
`app` are the only eager loads.
- `EvoScientist/cli/commands.py`: move `cmd_interactive`/`cmd_run` to
in-function imports so prompt_toolkit + textual only load when the
interactive path actually runs.
- `EvoScientist/cli/_constants.py`: read `AGENT_NAME` on demand so
`build_metadata` doesn't eagerly import `sessions` (langgraph/aiosqlite).
Adds `lazy-loader>=0.5` as a dependency.
* feat(cli): defer MCP tool loading with live per-server progress
The CLI was blocking ~5 s on MCP tool enumeration before the first
prompt appeared. Move the agent construction off the event loop and
surface per-server progress so the user can interact immediately and see
what's happening.
MCP client:
- Add an `on_progress` callback to `load_mcp_tools` / `aload_mcp_tools`
/ `_load_tools` emitting `start` / `success` / `error` events per
server.
- Fan connection attempts out with `asyncio.gather` so latency no longer
scales linearly with server count; cap simultaneous attempts at
`_MAX_CONCURRENT_CONNECTIONS` (8) via a semaphore so a big stdio fleet
doesn't spawn every subprocess at once.
Agent wiring:
- Plumb `on_mcp_progress` through `create_cli_agent` / `_load_agent` /
`load_mcp_and_build_kwargs` so CLI and TUI can plug in collectors.
CLI (`cmd_interactive`):
- Run `_load_agent` in a background thread via `asyncio.to_thread`; the
prompt and banner render immediately.
- `_await_agent_ready()` awaits the task before each agent-using site
(first turn, channel messages, `/channel`, `/compact`). Raises if
called without a prior `_start_agent_load` instead of silently
reloading without the SQLite checkpointer.
- Pre-prime the progress dict from `load_mcp_config()` so the
bottom-toolbar's `N/M` denominator is stable from the first render.
- Wrap `session.prompt_async` in `patch_stdout(raw=True)` so
`console.print` from the worker-thread progress callback lands cleanly
above the prompt as inline chat messages instead of stomping the
prompt cursor.
TUI (`EvoTextualInteractiveApp`):
- Same background load + `_await_agent_ready()` gates on every
`self._agent` read.
- New `MCPLoaderWidget` mounted at the top of `#input-shell` shows a
header with `N/M` and one live row per server (spinner → ✓ / ✗ with
tool count or error detail). On completion:
- all-clean loads auto-dismiss ~2.5 s later;
- cache hits (no events ever fired) dismiss immediately rather than
flashing a misleading "0/N loaded";
- failures keep the widget mounted so the user can read the errors.
- `dismissed` property lets the app clear its ref so late events from
slow servers become no-ops. The error branch of `_on_agent_loaded`
also settles the widget so a load failure can't leave the spinner
animating forever.
- Chat input is `disabled` while MCP resolves — no placeholder hack, no
"waiting…" system message.
Shared:
- Hoist braille spinner frames to `status_bar.SPINNER_FRAMES` and import
them in the TUI widget so CLI and TUI animate in sync.
Tests:
- Extend `test_agent_mcp_cache` fakes to accept the new `on_progress`
kwarg.
- New `TestLoadToolsProgressCallback` in `test_mcp_client` exercises the
event sequence for success/failure/mixed fleets, verifies a buggy
callback doesn't break the load, and asserts the semaphore caps
in-flight connections.
* style: ruff
* chore: update uv.lock
* chore: uv.lock
* fix: coderabbit issues
* style: fmt
* fix: move _await_agent_ready inside try block
* fix(tui): auto-dismiss MCP loader widget on failure
The widget was designed to stay mounted on failure so the user could
read error detail, but since it's pinned above the input it never went
away in practice — just permanent banner clutter.
Auto-dismiss on failure too, with a longer grace (12s vs 2.5s) so the
error summary stays readable.
* fix: address second coderabbit pass
- Channel handlers (CLI + TUI): catch agent-load failures so the
channel request doesn't hang; CLI moves `_await_agent_ready()`
inside the existing try/except, TUI catches explicitly and calls
`_set_channel_response` with the error.
- Stale background loads: `prev.cancel()` only stops the asyncio
wrapper, not the thread running `_load_agent`. Added a generation
token (`agent_load_id` / `self._agent_load_id`) and gated both
progress and completion callbacks on it so a superseded load can't
clobber the current session's state or UI.
- TUI prompt lifecycle: added `_agent_load_pending()` and gated the
`_process_channel_message` / `_handle_command` finally blocks on it
so `/new` or `/resume` invoked from a command keeps the prompt
disabled until the fresh load settles.
- TUI readiness failures: `_run_turn` and `_handle_command` now
catch exceptions from `_await_agent_ready()` and surface a
"Agent failed to load: …" system message instead of letting the
exception escape into Textual's traceback panel.
* refactor(cli): share background agent loader between CLI and TUI
The CLI and TUI were carrying near-identical copies of the same
background-load state machine: the `agent_task`, the `agent_load_id`
generation token, the gated progress/completion callbacks, and the
per-server progress dict. Every CodeRabbit finding on that lifecycle
had to be fixed in both files.
Extract it into `cli/_agent_loader.py`:
- `MCPProgressTracker` — owns the `server -> (state, detail)` dict;
exposes `prime`, `record`, `snapshot`, `totals`.
- `BackgroundAgentLoader` — owns `agent`, the in-flight task, and the
generation token. Exposes `start(**loader_kwargs)`, `await_ready()`,
`is_pending`. Internally gates all progress/completion callbacks by
generation so a superseded load can't clobber the current session.
UI-specific rendering plugs in via `on_progress` / `on_success` /
`on_failure` callbacks.
Both surfaces now just wire their UI hooks; the loader file holds no
Rich / prompt_toolkit / Textual dependencies. Net -345 lines from
`interactive.py` + `tui_interactive.py`; +20 unit tests pinning the
lifecycle (generation filtering, cache-hit short-circuit, failure
reset, progress ordering).
* refactor(cli): make _on_done the sole authority for agent state transitions
await_ready no longer sets self.agent — it just awaits the task and
reads what _on_done already wrote. Eliminates the dual-write overlap
(asyncio guarantees done-callbacks fire in registration order).
* fix(tui): let users type during MCP load, only block on send
Remove prompt-disabling during background agent load — the TUI now
matches the CLI approach where the input stays enabled and only gates
on await_ready() at submit time. The MCPLoaderWidget still provides
visual feedback that loading is in progress.
* fix(loader): preserve real load error on await_ready; dedup failure message
CodeRabbit flagged two issues with the new loader:
1. After a failed load, `_on_done` nulled `self._task`, so the next
`await_ready()` hit the "before start()" branch and the CLI wrapper
remapped it to a misleading "checkpointer not available" message —
losing the real exception (bad MCP config, network, etc.).
Keep `_task` set on failure so `await_ready` re-raises the real
exception. Added `needs_restart` so TUI's auto-retry check stays a
one-liner and doesn't need to reach into task internals.
2. TUI reported each load failure twice: once from
`_on_agent_load_failure` (the done-callback) and once from each
caller of `_await_agent_ready` (`_run_turn`,
`_process_channel_message`, `_handle_command`) catching the re-raise.
`_on_agent_load_failure` is now the sole local reporter; callers
just handle control flow (return cleanly, set channel response to
unblock remote).
* fix(cli): wire /model handler through the agent loader
The /model command from main (merged via f1f0d7c) still reached for
`state["agent"]` (CLI) and `self._agent` (TUI) — both removed by the
background-loader refactor. CLI raised KeyError on first invocation;
TUI raised AttributeError. Writes to the old fields also had no effect
because every other code path now reads from `agent_loader.agent`, so
the model switch would have silently failed.
Route everything through the loader: `await _await_agent_ready()` up
front so /model doesn't race with the initial background load, build
the `CommandContext` with the current agent, and sync `ctx.agent` back
into `agent_loader.agent` (plus channel globals) when the command
replaces it.
* fix(cli): isolate progress callback, capture awaited agent, gate by requires_agent
Three CodeRabbit findings on the loader + command dispatch path:
- Wrap ``_on_progress`` in try/except inside the loader's gated wrapper
so a buggy UI adapter can't bubble into ``loader_fn`` and fail the
whole background load. The MCP client already protects this, but
defence-in-depth keeps the loader self-contained.
- In CLI channel + main-loop streaming, capture the agent returned by
``_await_agent_ready()`` and pass that into ``run_streaming`` rather
than reading ``agent_loader.agent`` after a subsequent ``await``.
A concurrent ``/new``/``/resume``/``/model`` could have swapped it.
- Add ``requires_agent: ClassVar[bool] = False`` to ``Command`` and
mark ``/compact``, ``/model``, ``/channel`` as ``True``. TUI dispatch
sites (channel and keyboard) now check ``cmd_manager.resolve(...)``
and only wait for readiness when the command actually needs the
agent. ``/mcp add``, ``/skills``, ``/new`` etc. no longer deadlock
behind a failing MCP load they are meant to fix.
* fix(cli): guard sync-back, subcommand-aware gating, /model adopt-path
Three CodeRabbit findings on command dispatch:
- ``_handle_command`` unconditionally synced ``ctx.agent`` back into
``agent_loader``. For non-agent commands ``ctx.agent`` is ``None``,
so ``/threads`` / ``/mcp`` / ``/skills`` (etc.) could clobber a valid
loaded agent — and rebind channel globals to ``None``. Guard the
sync on ``ctx.agent is not None``.
- ``/channel status`` and ``/channel stop`` don't touch ``ctx.agent``
but the class-level ``requires_agent = True`` blocked them behind
agent readiness. Added ``Command.needs_agent(args)`` (defaults to
``requires_agent``) so ``/channel`` can override with subcommand
awareness; kept the class flag for the common case.
- ``/model`` builds a new agent from scratch, it never reads the
existing one — gating it on readiness meant a broken provider
blocked the command that would fix it. Flipped it to
``requires_agent = False`` and added ``BackgroundAgentLoader.adopt``
so the UI can seat the replacement and supersede any in-flight
load (the generation token keeps a late completion from clobbering
the adopted agent).
Bonus cleanup: ``CommandManager.resolve`` now returns
``(command, args)`` so callers can invoke ``needs_agent`` without
re-implementing ``shlex`` parsing.
---------
Co-authored-by: Xi Zhang <106144707+X-iZhang@users.noreply.github.com>
* feat: add support for session resumption with --resume flag and enhance thread ID resolution
* refactor(tests): streamline help output testing for --resume flag
* feat: enhance session resume functionality with improved thread ID resolution and SQL wildcard handling
* feat: improve error handling for resume hint retrieval in interactive modes
* refactor: streamline logging for print_resume_hint failure in interactive mode
* feat: implement deferred scrolling for Markdown-heavy content in interactive mode
* fix(mcp): forward proxy and CA bundle env vars to stdio subprocesses
The MCP SDK's stdio transport inherits only a minimal allowlist (HOME,
PATH, USER, …) from the parent, stripping http_proxy/https_proxy and
SSL_CERT_FILE/REQUESTS_CA_BUNDLE/etc. Behind a proxy or with a custom CA
bundle, stdio MCP servers silently hang on outbound requests while the
same server over HTTP transport works. Auto-forward the proxy and cert
vars when present; user-configured env still takes precedence.
* fix(mcp): use `uv tool install` so MCP packages survive uv sync
Source installs previously used `uv pip install --python $VENV <pkg>`,
which lands in the evosci venv but is not recorded in pyproject.toml or
uv.lock. A subsequent `uv sync` (typical after `git pull`) reconciles
the venv to the lockfile and removes the MCP package, forcing users to
re-run onboard.
Prefer `uv tool install <pkg>` for the non-uv-tool install path: the
binary symlink in ~/.local/bin survives uv sync and evosci upgrades,
and the MCP server gets its own isolated env (no dep conflicts).
Verify the expected CLI entry point resolves afterward; if not (package
has no console-script), fall through to the old uv-pip path so
command-less packages still work.
The uv-tool-env path (`uv tool install evoscientist --with <pkg>`) is
unchanged — it was already durable via uv's receipt.
* fix(mcp): gate standalone uv tool install on verify_command
Previously `install_pip_package` would route every install through
`uv tool install <pkg>` when `verify_command` was None, returning
success as long as the uv subprocess exited 0. Library callers
(`evoscientist[oauth]`, `lark-oapi`, etc.) expect the package to land
in the active venv so they can import it — a standalone uv tool env
is not importable, so the import fails at the next line.
Gate the `uv tool install <pkg>` branch on `verify_command` being
set: that signals the caller wants a durable CLI binary, which is
what `uv tool install` produces. Library callers omit it and go
straight to the pip-install-into-venv path.
Also: log info messages on every fall-through so stale-binary and
entry-point-missing failure modes are debuggable, and document the
--with → standalone recovery path.
* fix(mcp): resolve MCP binaries to `uv tool dir --bin`, not `.venv/bin`
Under `uv run`, the project venv's `bin/` comes first on PATH, so
`shutil.which("arxiv-mcp-server")` returns a stale `.venv/bin/` copy
left over from an earlier install instead of the fresh symlink that
`uv tool install` just placed in `~/.local/bin`. The venv copy gets
written to mcp.yaml and is then wiped by the next `uv sync` — exactly
the failure mode the durability fix was meant to prevent.
Query `uv tool dir --bin` directly and prefer binaries found there
over `shutil.which`. Same change to the post-install verify in
`install_pip_package` so a venv shadow can't falsely short-circuit
the fallback.
* refactor(mcp): split install_pip_package into install_library + install_cli_tool
`verify_command` was doing double duty: naming the CLI binary to check
*and* signaling "this is a CLI install, use the standalone `uv tool
install` path." Callers routed library installs through the CLI branch
any time they forgot to pass it, and the resulting standalone uv tool
env wasn't importable from the active venv.
Separate the two use cases into distinct functions, each with one
install strategy per environment shape. Shared logic lives in private
`_install_with_uv_tool_env` / `_install_via_pip` helpers.
- install_library(pkg): uv-tool-env --with → pip. Never uses standalone
`uv tool install <pkg>` (not importable from active venv).
- install_cli_tool(pkg, *, verify_command): uv-tool-env --with →
standalone `uv tool install` → pip. `verify_command` is now required.
Callers pick the right function at the call site: registry.py picks
based on whether `entry.command` is set; onboard.py call sites all
install libraries.
* fix(channel/qq): deliver HITL approval prompts reliably
QQ approval prompts were silently dropped when the markdown send hit
a QQ server-side error (e.g. template not configured, content audit)
because the fallback path only matched TypeError / specific string
patterns, and the plain-text retry reused the already-consumed
msg_seq which QQ then rejects as duplicate.
- Consume a fresh msg_seq for the plain-text fallback send
- Recognize QQ server error codes (304014/304023/304003/40034059)
and CN fragments ("模版"/"审核") as markdown-fallback triggers
- Promote send failure logs from debug to warning/error with
chat_id/msg_id/seq so real-world errors can be diagnosed
- Extend test_qq_channel with a server-error-code fallback case
* style(channel/qq): apply ruff formatter to approval-delivery fix
* Fix
* chore(release): update version to v0.0.8 and dependencies in project files
* feat(models): add new model entries for Claude Opus 4-7 and update version handling
* Refactor code structure for improved readability and maintainability
* refactor(paths): unify global data directory to ~/.evoscientist and update related paths
* refactor(paths): update legacy session migration to respect XDG_CONFIG_HOME
* refactor(tests): clear XDG_CONFIG_HOME in legacy session migration tests for deterministic behavior
- Added model_selection.png to illustrate model selection process.
- Added prompt.png for visual representation of prompts used in surveys.
- Added skill_selection.png to depict skill selection criteria.
* feat(prompt): enhance user interaction with multiple-choice and free-text questions
* refactor(paths): rename MEMORY_DIR to MEMORIES_DIR for consistency
* style(tests): format code for better readability in test cases
* feat(prompt): add validation for 'other' option in user prompt
* feat(prompt): refactor validation logic for user prompts and add skip option
* feat(style): refactor to use shared _PICKER_STYLE from interactive module
* feat(backends): rename MergedReadOnlyBackend to MergedSkillsBackend and update documentation for clarity
refactor(paths): simplify ensure_dirs function to create only memory directory eagerly
fix(prompts): update skills availability description for accuracy
test(paths): adjust test to reflect skills directory creation on demand
* refactor(tests): format assertion for skills directory existence in ensure_dirs test
* Add status bar and compact summary widgets with context window resolution
- Implemented a shared status bar for CLI and TUI frontends, including helpers for managing session metrics and context windows.
- Created a `CompactSummaryWidget` for displaying manual summaries in a collapsible format.
- Introduced a `CompactingWidget` to indicate ongoing compacting processes.
- Added a base class `TimedStatusWidget` for widgets that require a timer.
- Developed context window resolution helpers to retrieve context window sizes from various model attributes.
- Enhanced tests for context window resolution and status bar functionalities, ensuring accurate behavior across different scenarios.
- Updated existing tests to cover new features and maintain code quality.
* refactor(Channel): simplify lambda function in _send_with_retry method
* feat: enhance context editing logic and improve error handling in StreamState
* refactor(Channel): streamline lambda function in _send_with_retry method
* feat: rename auto-approve option to auto-mode for unattended execution; update checkpoint queries to filter by agent name; improve compatibility validation logic
* feat: rename auto-approve option to auto-mode; update related logic and tests for improved unattended execution
* fix: correct formatting of console message for MCP server configuration status
* feat: add check for None summary_message in _apply_summarization_event to prevent errors
* feat: enhance _load_checkpoint_messages to validate message format and apply summarization event
* chore(assets): update wechat_group image file
* Refactor code structure for improved readability and maintainability
* feat(backends): enhance MergedReadOnlyBackend with improved ls, grep, and glob methods
* fix(docs): update WeChat QR code image link in README files
* feat(skills): enhance skill management to support global and workspace tiers
* style: apply ruff format to skills_cmd and commands/implementation/skills
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(skills): improve uninstall_skill to prevent removal of built-in skills
* fix(docs): update skill installation documentation for clarity on global and user directories
* fix(skills): enhance uninstall_skill to validate skill directory before removal
* fix(skills): improve error handling in install_skill and uninstall_skill for directory creation and validation
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(ccproxy): update Responses API handling and patch system role conversion
* fix(ccproxy): streamline _agenerate method in system to developer patch
* fix(ccproxy): improve handling of None output in Codex compatibility patch
* fix(llm): patch _stream/_astream for OpenAI-compatible content flattening
_patch_openai_compat_content() only patched _generate/_agenerate but
EvoSci CLI uses streaming paths. This extends the content flattening
to _stream/_astream so strict OpenAI-compatible relays receive plain
string content during streaming calls.
Closes#142
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(test): use asyncio.run() instead of pytest-asyncio for CI compat
CI does not have pytest-asyncio installed, so async tests must use
asyncio.run() wrapper instead of @pytest.mark.asyncio decorator.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(test): use @pytest.mark.anyio for async tests (CI compat)
CI does not have pytest-asyncio. Use @pytest.mark.anyio consistent
with existing async tests in the project.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add Moonshot and Kimi Coding Plan as LLM providers
Add two new providers for Moonshot AI:
- `moonshot`: OpenAI-compatible direct API (api.moonshot.cn/v1) with
kimi-k2.5, kimi-k2-thinking, moonshot-v1-auto/128k/32k/8k models
- `kimi-coding`: Anthropic-compatible Kimi Coding Plan endpoint
(api.kimi.com/coding/) with User-Agent header for compatibility
Both providers disable thinking to avoid multi-turn tool calling
errors caused by LangChain dropping reasoning_content from history.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* chore: update Moonshot thinking comment and add provider assertions
- Add clarifying comment for disabling thinking on all Moonshot models
- Add moonshot and kimi-coding assertions to test_entries_has_all_providers
* fix: exclude Moonshot and Kimi Coding from content patch
Tested and verified both APIs support standard list content format:
- Moonshot (OpenAI-compatible): supports list content, no patch needed
- Kimi Coding (Anthropic-compatible): supports list content, no patch needed
Only apply _patch_openai_compat_content to strict providers like DeepSeek.
* fix: set _original_provider in routed provider branches
Ensure _original_provider is set before provider is reassigned to
'openai' or 'anthropic', so the no-patch exclusion for Moonshot
and Kimi Coding works correctly.
* style: translate Moonshot comments to English
* style: translate comment to English to fix ruff lint error
* merge: resolve conflicts
* chore: revert uv.lock and translate Chinese comments to English
Revert unrelated uv.lock dependency changes and replace Chinese code
comments with English for codebase consistency per review feedback.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* style: fix ruff format for models.py
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: ypd <ypd@ypddeMac-mini.local>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Xi Zhang <106144707+X-iZhang@users.noreply.github.com>
Co-authored-by: Xiaohui Yan <xhcloud@gmail.com>
Co-authored-by: X-iZhang <zacharyzhang2022@gmail.com>
* fix: support XDG_CONFIG_HOME for sessions.db on Windows
Fixes SQLite database opening failure on Windows systems with non-ASCII
usernames (e.g., Chinese characters). The get_db_path() function now
supports the XDG_CONFIG_HOME environment variable, consistent with
get_config_dir() in settings.py.
Closes#101
* fix: auto-resolve Windows Unicode path for sqlite3 via 8.3 short path
Refactor get_db_path() to reuse get_config_dir() (XDG_CONFIG_HOME
support) and add _to_short_path() helper that converts the config
directory to its Windows 8.3 short form via GetShortPathNameW. This
automatically resolves sqlite3 failures on Windows systems with
non-ASCII usernames (e.g., Chinese characters) without requiring
manual environment variable configuration.
The short-path conversion is best-effort: it targets the directory
(which exists after mkdir) rather than the db file, and falls back
gracefully on non-Windows, non-NTFS, or when 8.3 naming is disabled.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Xi Zhang <106144707+X-iZhang@users.noreply.github.com>
Co-authored-by: X-iZhang <zacharyzhang2022@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(cli): add --debug flag for verbose logging in serve mode
* feat(cli): add log_level config field with priority over env var
Replace dead `debug` parameter in `main()` with a proper `log_level`
config field in EvoScientistConfig. Enables `EvoSci config set log_level
debug` with priority: config file > EVOSCIENTIST_LOG_LEVEL env var.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
dinos