feat(office): add progressive skills and direct dsoffice commands
This commit is contained in:
1 parent
fddd704c7f
commit
379f9cd47b
308 files changed
+5344
-1012
No files matched your search
@@ -27,6 +27,10 @@ uv run --project python/sdk pytest
|
||||
|
||||
`python/sdk/tests/test_bundled_runtime.py` exercises available bundled carriers and skips a carrier when its artifact has not been built. For repository-wide test policy, see [Testing](../docs/testing.md).
|
||||
|
||||
LibreOffice Kit CI owns visible Office content checks through its installed Node API and CLI on macOS, Windows, and Linux when matching engine packages are published. Harness verifies the relocated Office sidecar through the installed-wheel smoke; the Python tests reject white, transparent, reversed, and text-free output.
|
||||
|
||||
Set `DSH_OFFICE_TEST_ARTIFACTS` to a new directory to retain the installed-wheel smoke's Office inputs, PNGs, manifests, and failure diagnostics. CI uploads these files on success and failure; temporary runtime files are excluded.
|
||||
|
||||
That suite drives fake runtime peers. `scripts/smoke-python-runtime.py` drives the packaged runtime instead. The `python-runtime` CI jobs build Linux x64 and Windows x64 on pull requests, and Linux arm64 plus both macOS architectures on master pushes. Each selected target installs the matching SDK and runtime wheels into a new Python 3.10 virtual environment, runs outside the checkout with `PYTHONPATH` and `DSH_RUNTIME_MODE` unset, proves that both modules and the executable came from those distributions, and then runs every keyless scenario. A focused local source-SDK run can select one built executable and scenario:
|
||||
|
||||
```sh
|
||||
@@ -34,13 +38,13 @@ uv run --project python/sdk python scripts/smoke-python-runtime.py \
|
||||
--scenario sdk-minimal --exe dist-exe/deepseek-harness-sdk-runtime-macos-arm64
|
||||
```
|
||||
|
||||
SDK scenarios compare committed expected output under `scripts/snapshots/python-sdk-single-exe/`. `minimal/model-visible.json` pins the Linux/macOS `sdk-minimal` profile's assembled system prompts, advertised tool schemas, and model-visible messages; `minimal/win-x64/model-visible.json` pins its PowerShell counterpart. A plugin that contributes an unintended system section or user message therefore fails the job, and every message the profile emits is compared. `advanced/` pins direct tool calls, child agents, and workflows; `advanced-ptc/` pins program calls and nested denials. Both compare SDK results and session logs across every target. `restart/` launches two complete SDK runtime processes against one persistence root and snapshots their isolated model histories, high-level results, and separate durable logs across every target. `sdk-minimal-in-history` reuses the persistent-shell and editor scenario with a section that changes after the first successful shell call. `minimal-in-history/prompt-history.json` pins both prompt versions, the unchanged leading prompt in later requests, appended SDK system-message events, and `request/context.systemPromptUpdate`; tool schemas stay fixed and the editor file is checked independently. `sdk-dynamic-tools` pins native tool additions and removals in `dynamic-tools/tool-history.json`, including historical header references and agreement between Python SDK results, notifications, and persisted events. Rerun the owning scenario with `--update-snapshots` and review that diff before committing it.
|
||||
SDK scenarios compare committed expected output under `scripts/snapshots/python-sdk-single-exe/`. `minimal/model-visible.json` pins the Linux/macOS `sdk-minimal` profile's assembled system prompts, advertised tool schemas, and model-visible messages; `minimal/win-x64/model-visible.json` pins its PowerShell counterpart. `authoring/model-visible.json` pins the Linux/macOS Office authoring catalog and dependency result; `authoring/win-x64/model-visible.json` pins the Windows catalog, including the ACL diagnostic skill. A plugin that contributes an unintended system section or user message therefore fails the job, and every message the profile emits is compared. `advanced/` pins one complex process's SDK result and parent/child session logs across every target. `restart/` launches two complete SDK runtime processes against one persistence root and snapshots their isolated model histories, high-level results, and separate durable logs across every target. `sdk-minimal-in-history` reuses the persistent-shell and editor scenario with a section that changes after the first successful shell call. `minimal-in-history/prompt-history.json` pins both prompt versions, the unchanged leading prompt in later requests, appended SDK system-message events, and `request/context.systemPromptUpdate`; tool schemas stay fixed and the editor file is checked independently. `sdk-dynamic-tools` pins native tool additions and removals in `dynamic-tools/tool-history.json`, including historical header references and agreement between Python SDK results, notifications, and persisted events. Rerun the owning scenario with `--update-snapshots` and review that diff before committing it.
|
||||
|
||||
`scheduler-recovery/` records a failed tool turn and a subsequent completed turn. It preserves the original `UNKNOWN` turn error, the first tool's completed result, and `TOOL_OUTCOME_UNKNOWN` / `TOOL_NOT_STARTED` results for the remaining calls. `sdk-snapshot` and `all` include this case; `--scenario sdk-recovery` runs it alone.
|
||||
|
||||
The `advanced`, `advanced-ptc`, and `restart` comparisons match native delivery qualifiers against each input's own Session generation, including SDK events and notifications. Captured and other delivery generations retain their numeric values. Each side must use one generation across its Session roles, and fresh logs must identify the current writer. Without `--update-snapshots`, comparison writes no files. Refresh writes current-writer outputs and preserves earlier Session generations.
|
||||
The `advanced` and `restart` comparisons match native delivery qualifiers against each input's own Session generation, including SDK events and notifications. Captured and other delivery generations retain their numeric values. Each side must use one generation across its Session roles, and fresh logs must identify the current writer. Comparison never rewrites committed recordings.
|
||||
|
||||
Trusted pull requests and master pushes also run `--scenario sdk-live --installed-wheel` on each selected native target. That scenario performs two tool-using turns against `https://api.deepseek.com`: it checks the created file immediately, replaces its content with a host-only random challenge, and requires the second turn to copy the changed content into a fresh receipt without modifying the source. Both turns must complete with a standalone sentinel acknowledgement and a model-requested tool call; the acknowledgement may precede or follow explanation, and external byte comparisons check the files. Missing repository secrets fail instead of self-skipping. Fork and Dependabot pull requests run the complete keyless installed-wheel path but receive no key.
|
||||
Trusted pull requests and master pushes also run `--scenario sdk-live --installed-wheel` on each selected native target. That scenario performs two tool-using turns against `https://api.deepseek.com`: it checks the created file immediately, replaces its content with a host-only random challenge, and requires the second turn to copy the changed content into a fresh receipt without modifying the source. Both turns must complete with the exact sentinel answer and a model-requested tool call; external byte comparisons check the files. Missing repository secrets fail instead of self-skipping. Fork and Dependabot pull requests run the complete keyless installed-wheel path but receive no key.
|
||||
|
||||
An interactive smoke test needs `DEEPSEEK_API_KEY` in the environment or repository-root `.env`:
|
||||
|
||||
|
||||
Reference in new issue
Block a user