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

Merge origin/master into worktree/agent-execution-context-rfc

Browse Source
This commit is contained in:
Yichen Jiang
2026-07-18 21:20:30 +08:00
parent a42c28cdc9 417248eed8
commit 0e4785cdb7
105 changed files with 3306 additions and 554 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
docs/architecture.md
View File

@@ -84,11 +84,12 @@ forever:
'assistant/chunk'
agent/step-result
'assistant/message' (transformed content or empty success anchor after step-result rejection)
each tool call:
'tool/call'
tools/pre-execute -> monotonic guards -> tools/execute -> tools/post-execute -> tools/result
'tool/result'
append post-tool context and steering
schedule tool calls by ctx.tools.executionMode:
exclusive -> one-call barrier
parallel -> rolling pool, <= maxParallelToolCalls in flight; reclassify before start
each start -> 'tool/call' -> ordered tools/pre-execute -> concurrent tools/execute
each model-order result -> ordered tools/post-execute -> 'tool/result'
append accepted tool-batch context after all recorded results, then steering
'step/end'
agent/turn-continuation
agent/turn-stop (terminal policy)
@@ -99,7 +100,7 @@ forever:
Each step assembles ordered prompt sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn. `dsh-system-prompt` owns the harness identity and default persona, which an agent scope may shadow. The loop supplies `model` and `cwd` ([prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)).
Post-tool context lands after all tool results so tool-call/result adjacency stays stable. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved.
Context accepted during tool execution—including async `agent.inject()` notices and post-tool `additionalContexts`—waits for settlement, then follows every recorded result. Successful batches preserve call/result adjacency; interrupted batches drain that context before turn closure. Steering drains between steps; ordinary leftover steering becomes queued input. Terminal `agent/turn-stop` runs after continuation and steering folding, stays authoritative through turn close and flush, and discards later steering while preserving queued prompts.
### Failure Boundaries