mirror of
https://github.com/deepseek-ai/deepseek-harness.git
synced 2026-09-11 04:00:38 +00:00
docs(code-runtime-python): register the truncation exception to open merging; clean a case comment
The review's warning: the READMEs (outer and inner wire sections, en + zh) and the fd-3 protocol note still claimed the next log frame always merges into an open entry, while truncateLogs commits the already-billed prefix as its own entry before the marker. The one exception (truncation) is now stated in both READMEs and the owning note, paired and re-recorded. The prefix-commit case's parenthetical describing the pre-fix implementation is removed per the comment-does-not-record-review-history rule.
This commit is contained in:
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/code-runtime/code-runtime-python/README.md
|
||||
README.md: eaba8999c03429473acbfc968ebd0dcd6aae1080
|
||||
README.zh.md: f71eb0b76fbeeece79e747befb1dd090dfd7bb58
|
||||
README.md: 2e22a5122f891b8317e13ee395ce222805b01b29
|
||||
README.zh.md: 0f8773bc8e8292cfc3f0b09395d46ff75b17392c
|
||||
|
||||
@@ -33,7 +33,7 @@ The package's default export is the `PythonCodeRuntime` plugin. Its public surfa
|
||||
|
||||
### The wire
|
||||
|
||||
Frames travel on the child's fd 3 as JSON-lines — one object per line — so stdout/stderr stay clear for the program's own output. Child → host: `boot-ack`, `call`, `log`, `done`. Host → child: `boot` (first frame, carrying every cap and the namespace declarations), `run` (after `boot-ack`, carrying only the program body), and one `reply` per `call`. A forged frame can carry both `value` and `error` on `done`, so a consumer must check `error` first and ignore `value` when it is set. A `log` frame's `open` flag marks an unterminated line committed by an explicit flush: the host appends the next log frame to the same entry, so `print('a', end='', flush=True); print('b')` reads back as one `'ab'` entry rather than a fake newline (the split-billing arithmetic lives in the fd-3 protocol Agent Note's wire-contract section).
|
||||
Frames travel on the child's fd 3 as JSON-lines — one object per line — so stdout/stderr stay clear for the program's own output. Child → host: `boot-ack`, `call`, `log`, `done`. Host → child: `boot` (first frame, carrying every cap and the namespace declarations), `run` (after `boot-ack`, carrying only the program body), and one `reply` per `call`. A forged frame can carry both `value` and `error` on `done`, so a consumer must check `error` first and ignore `value` when it is set. A `log` frame's `open` flag marks an unterminated line committed by an explicit flush: the host appends the next log frame to the same entry, so `print('a', end='', flush=True); print('b')` reads back as one `'ab'` entry rather than a fake newline (the split-billing arithmetic lives in the fd-3 protocol Agent Note's wire-contract section). The one exception to merging is truncation: when a later over-budget frame trips the ledger, the already-billed prefix is committed as its own entry and the truncation marker follows it (the marker stays last, with no re-charge).
|
||||
|
||||
### What can go wrong
|
||||
|
||||
@@ -55,7 +55,7 @@ One direction of trust: the host treats every inbound frame as hostile (model co
|
||||
|
||||
### Wire contract
|
||||
|
||||
The frames are `boot` / `run` (host → child) and `boot-ack` / `call` / `log` / `done` plus one `reply` per call (child → host). The `log` frame's `truncated` flag marks the frame that IS the child ledger's truncation marker, so the host stops capturing at the same point the child did instead of inferring it from its own budget. The `log` frame's `open` flag marks an unterminated line committed by an explicit flush: the host merges the next log frame into the same entry, so `print('a', end='', flush=True); print('b')` reads back as one `'ab'` entry rather than a fake newline (the split-billing arithmetic lives in the fd-3 protocol Agent Note's wire-contract section). `done.error.kind` is one of `exception`, `invalid-output`, `output-limit`; wall/CPU budgets, aborts, and substrate death are observed host-side, not carried as frames.
|
||||
The frames are `boot` / `run` (host → child) and `boot-ack` / `call` / `log` / `done` plus one `reply` per call (child → host). The `log` frame's `truncated` flag marks the frame that IS the child ledger's truncation marker, so the host stops capturing at the same point the child did instead of inferring it from its own budget. The `log` frame's `open` flag marks an unterminated line committed by an explicit flush: the host merges the next log frame into the same entry, so `print('a', end='', flush=True); print('b')` reads back as one `'ab'` entry rather than a fake newline (the split-billing arithmetic lives in the fd-3 protocol Agent Note's wire-contract section). The one exception to merging is truncation: the already-billed prefix is committed as its own entry and the truncation marker follows it (marker last, no re-charge). `done.error.kind` is one of `exception`, `invalid-output`, `output-limit`; wall/CPU budgets, aborts, and substrate death are observed host-side, not carried as frames.
|
||||
|
||||
### Lossless JSON crossing
|
||||
|
||||
|
||||
@@ -55,7 +55,7 @@ kind: "package-reference"
|
||||
|
||||
### wire 契约
|
||||
|
||||
帧为 `boot`/`run`(宿主 → 子进程)与 `boot-ack`/`call`/`log`/`done` 加每个 call 一个 `reply`(子进程 → 宿主)。`log` 帧的 `truncated` 标志标记的就是子进程账本自己的截断标记帧,因此宿主在与子进程相同的点停止捕获,而不是从自己的预算推断。`log` 帧的 `open` 标志标记由显式 flush 提交的未结束行:宿主把下一个 log 帧合并进同一条目,因此 `print('a', end='', flush=True); print('b')` 读回为一条 `'ab'` 条目而不是假换行(拆分计费算术在 fd-3 协议 Agent Note 的 wire-contract 段)。`done.error.kind` 为 `exception`、`invalid-output`、`output-limit` 之一;墙钟/CPU 预算、中止与基底死亡在宿主侧观察,不以帧形式携带。
|
||||
帧为 `boot`/`run`(宿主 → 子进程)与 `boot-ack`/`call`/`log`/`done` 加每个 call 一个 `reply`(子进程 → 宿主)。`log` 帧的 `truncated` 标志标记的就是子进程账本自己的截断标记帧,因此宿主在与子进程相同的点停止捕获,而不是从自己的预算推断。`log` 帧的 `open` 标志标记由显式 flush 提交的未结束行:宿主把下一个 log 帧合并进同一条目,因此 `print('a', end='', flush=True); print('b')` 读回为一条 `'ab'` 条目而不是假换行(拆分计费算术在 fd-3 协议 Agent Note 的 wire-contract 段)。合并的唯一例外是截断:当后续超预算帧触发账本时,已计费的前缀作为独立条目先提交,截断 marker 跟在后面(marker 保持末位,无重复计费)。`done.error.kind` 为 `exception`、`invalid-output`、`output-limit` 之一;墙钟/CPU 预算、中止与基底死亡在宿主侧观察,不以帧形式携带。
|
||||
|
||||
### 无损 JSON 跨越
|
||||
|
||||
|
||||
@@ -1901,8 +1901,7 @@ describe('PythonCodeRuntime — programs and bindings', () => {
|
||||
it('commits a flushed open prefix before the truncation marker', async () => {
|
||||
// A flushed unterminated line is billed and committed; when a later
|
||||
// over-budget write truncates, the committed prefix must appear BEFORE the
|
||||
// marker — the ledger charged for it, so it cannot vanish. (The bug: all
|
||||
// truncation arms pushed only the marker, dropping the held prefix.)
|
||||
// marker — the ledger charged for it, so it cannot vanish.
|
||||
const { runtime } = await setup({ maxLogBytes: 64 })
|
||||
const result = await runtime.run({
|
||||
program: [
|
||||
|
||||
Reference in New Issue
Block a user