Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: address final model experience review

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-14 00:22:52 +08:00
parent a4417f4924
commit eed43abe66
32 changed files with 291 additions and 278 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
packages/support/llm-replay/README.md
View File

@@ -46,11 +46,7 @@ Named `name` / `inject` / `Config` / `apply`, with **no default export**: the co
## Model Experience
### Keyless test stream
**What the model sees**: The real loop still assembles its normal system prompt, tools, prefix, and history, but no provider model receives them. Recorded assistant chunks are replayed as the response and then enter later history exactly like live output.
**Token effect**: Zero billed or tokenizer-evaluated model tokens. Fixture output creates deterministic retained test context for later replay steps.
None, as this keyless test adapter sends no request to a provider model; it only replays recorded assistant chunks into the test loop.
## Known Limitations and Deferred Work

6
packages/support/subagent-mock/README.md
View File

@@ -21,11 +21,7 @@ Aborting the required request signal or disposing before `result` settles flips
## Model Experience
### Deterministic test result
**What the model sees**: No child model runs. When exercised through `dsh-tool-subagent`, the parent sees the mock provider's configured reply or stop-reason error, and structured tests receive the configured object.
**Token effect**: Zero child-model tokens. Only the scripted final result is added to the parent test history.
Indirectly, through `dsh-tool-subagent`, which renders this test provider's configured reply or stop-reason error into the parent test history.
## Known Limitations and Deferred Work