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

feat(agent-loop): config-driven session resume via RESUME_SESSION_ID

Browse Source 
A config agent with `resumeSessionId` set continues a persisted session
instead of starting a fresh `${id}-session-<uuid>`. The id is sourced from
an env var in cordis.yml, so the coding-agent demo can resume a prior
conversation without code changes. The resume is deferred until the
`sessionPersistence` backend loads (via ctx.inject) and is contained: a
missing/unreadable id logs a warning and starts no agent. Adds a real-API
resume e2e proving cross-process continuity through the JSONL backend.
This commit is contained in:
Tianyi Cui
2026-06-16 22:28:01 +08:00
parent 8511b9639c
commit 0000cdb2c2
6 changed files with 212 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
examples/coding-agent/README.md
View File

@@ -22,6 +22,16 @@ Type a coding task. The agent's only tools are `bash` (+ `bash_output` / `bash_k
…
```
### Resuming a prior session
Each run starts a fresh session by default (its event log lands under `./.sessions/`). To **continue** a previous conversation, set `RESUME_SESSION_ID` to that session's id — the `main` agent then rehydrates the persisted log instead of starting fresh, so the model sees the earlier turns as history:
```sh
RESUME_SESSION_ID=<prior-session-id> pnpm run demo:coding
```
The id is wired through `cordis.yml` (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`); unset, the agent starts a new session. A missing/unreadable id is non-fatal — it logs a warning and starts no `main` agent.
## What each plugin demonstrates
| Entry | Demonstrates |
@@ -36,5 +46,6 @@ Type a coding task. The agent's only tools are `bash` (+ `bash_output` / `bash_k
- `tests/full-loop.e2e.ts` — the canary: real model runs `echo e2e-ok` through the real bash tool; asserts `tool/call`/`tool/result` session events and the final answer.
- `tests/coding-task.e2e.ts` — the swebench-style smoke: a temp dir holds `add.js` (with `a - b` where `a + b` belongs) and a failing `add.test.js`; the agent must fix the bug and verify. The test re-runs `node add.test.js` ITSELF and inspects the files — agent claims are not trusted.
- `tests/resume.e2e.ts` — durable continuity across processes: run 1 tells the real model a secret code and persists the turn to a temp JSONL root, then the whole context is disposed; run 2 is a fresh context over the same root that RESUMES the session id and asks the model to recall the code. The recall can only come from the rehydrated log.
Both self-skip without `DEEPSEEK_API_KEY`.