DeepSeek/deepseek-harness
1
0
Fork 0
mirror of https://github.com/deepseek-ai/deepseek-harness synced 2026-08-15 21:04:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'codex/canonical-tool-output' into codex/code-mode-typed-results

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-21 19:28:23 +08:00
parent 650a9cd82c 5b36be339d
commit 1ff0332ea0
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/architecture.md
View File

@@ -98,7 +98,7 @@ forever:
exclusive -> one-call barrier
parallel -> rolling pool, <= maxParallelToolCalls in flight; reclassify before start
each start -> 'tool/call' -> ordered tools/pre-execute -> concurrent tools/execute
body value -> validate/snapshot -> Native/meta projection
body -> validate/snapshot -> Native/meta
each model-order result -> ordered tools/post-execute -> projected 'tool/result'
append accepted tool-batch context after all recorded results, then steering
agent/post-step
@@ -112,7 +112,7 @@ 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](../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)).
Tool success separates an execution-local canonical JSON value from Native projections; post-policy replaces one projection or blocks, and the loop persists only projections ([contract](../.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.md)). Tool-time context—including async `agent.inject()` notices and post-tool `additionalContexts`—settles after results. Steering drains; before signal closure, `agent/post-step` observes durable output, results, context, and steering. Leftovers queue. Terminal `agent/turn-stop` runs after continuation and steering folding, remains authoritative through close/flush, and discards later steering while preserving queued prompts.
Canonical tool JSON stays execution-local; post-policy replaces value or presentation, or blocks; the loop persists projections ([contract](../.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.md)). Tool-time context—including async `agent.inject()` notices and post-tool `additionalContexts`—settles after results. Steering drains; before signal closure, `agent/post-step` observes durable output, results, context, and steering. Leftovers queue. Terminal `agent/turn-stop` runs after continuation and steering folding, remains authoritative through close/flush, and discards later steering while preserving queued prompts.
Pruning precedes summaries; overflow retries require durable progress. Bounded transient retries compose on `agent/request-error`; cancellation wins ([compaction](../.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md), [retry](../.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md)).