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

Merge remote-tracking branch 'origin/master' into codex/cli-one-shot-demo

Browse Source 
# Conflicts:
#	AGENTS.md
#	docs/architecture.md
#	docs/capability-seams.md
#	docs/cookbook/extension-cookbook.i18n.yaml
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	knip.json
#	packages/README.md
#	packages/support/loader-smoke/README.md
#	packages/support/loader-smoke/src/index.ts
#	vitest.snapshot.config.ts
This commit is contained in:
Tianyi Cui
2026-07-19 13:11:50 +08:00
parent 8d35092e26 114ceee293
commit 53c729e00b
851 changed files with 46937 additions and 13076 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
packages/examples/cli-demo/README.md
View File

@@ -8,12 +8,14 @@ The package mounts no console logger, readline UI, user-interaction service, or
| Key | Default | Routed to |
|---|---|---|
| `provider` | required | the pre-created `main` agent's provider route |
| `model` | required | the pre-created `main` agent's model |
| `persona` | — | the deployment persona in `dsh-system-prompt` |
| `toolOrder` | lexicographic | explicit model-facing tool order in `dsh-system-prompt` |
| `tools` | `{ mode: 'native' }` | tool-registry presentation config through `dsh-agent-spine-demo` |
| `skills` | owner defaults | skill registry, local provider, and model-facing skill tool |
| `persistenceRoot` | `./.sessions` | JSONL session root |
| `workspaceContext` | required | workspace-instruction byte budget, or `false` to disable loading |
Each process creates a new session whose workspace cwd is the launch directory. The app has no resume setting.
@@ -51,7 +53,7 @@ The headless-agent leaf supplies local bash, filesystem, skill, subagent, workfl
### One-shot task turn
**What the model sees**: The positional task becomes one user message. Through `dsh-agent-spine-demo`, the `main` agent also receives the configured persona, skill catalog, visible tool schemas, and retained tool results needed for later steps in the same turn.
**What the model sees**: The positional task becomes one user message. Through `dsh-agent-spine-demo`, the `main` agent also receives configured workspace instructions and persona, the skill catalog, visible tool schemas, and retained tool results needed for later steps in the same turn.
**Token effect**: The task, prompt sections, tool schemas, assistant output, and tool results consume tokens on each model step. JSON event streaming and final rendering add no model tokens; delegated child work has its own model usage and is not included in the parent result's `usage` total.