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

fix(tools): bound the shaped-append side channel; total error containment; recorded spill snapshot

Browse Source 
Responding to ds-review-bot round 2 on #661:

- logWork is bounded: past maxParallelSubCalls pending shaped-append tasks
  the ordered commit lane holds (Promise.race drains one), so a slow spill
  backend backpressures the run instead of accumulating unbounded pending
  I/O and retained results. Tasks self-remove on settlement; run
  settlement still drains every task inside the open turn. New spill test
  drives three oversized reads against a hung backend at cap 1 and proves
  the third dispatch cannot start until a save drains.
- shapeDispatchLog's catch uses errorMessage() (total), so a thrown value
  with a throwing toString cannot escape the containment and lose the
  settle event.
- CodeDispatchLog.content documented as the RENDERED result projection
  (native tool/result vocabulary), not what the program received — the
  program gets the structured value; doc pair + type-equiv re-synced.
- New RECORDED tui-agent snapshot scenario code-mode-dispatch-spill: the
  real Loader-visible composition (worker runtime + spill-local + policy)
  drives an oversized bash sub-call end-to-end; replay proves the durable
  dispatch copy is bounded to preview + locator while the program value
  stays whole (the outer result carries just the line count).

Agent Note updated (both languages).
This commit is contained in:
Tianyi Cui
2026-07-26 18:29:09 +08:00
parent 442a3dd884
commit c3c10820ba
14 changed files with 384 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/tui-agent/tests/snapshots/code-mode-dispatch-spill/terminal.expected.txt
+65
View File
@@ -0,0 +1,65 @@
terminal 100x36 buffer=normal length=36 base=0 viewport=0
lifecycle started=1 stopped=0 progress=inactive
title "Using ONE run_code program: call — DSH TUI snapshot"
cursor hidden column=1 viewportRow=26 bufferRow=26
buffer
0| " DEEPSEEK HARNESS"
style 1-8 fg=bright-blue bold
style 10-16 bold
1| " Using ONE run_code program: call"
style 1-32 fg=bright-black
2| " deepseek-v4-flash • main-session"
style 1-34 dim
3| <blank>
4| "▌ "
style 0-0 fg=bright-blue
5| "▌ You "
style 0-0 fg=bright-blue
style 2-4 fg=bright-blue bold
6| "▌ Using ONE run_code program: call the bash tool exactly once with the command seq 1 200 | awk "
style 0-0 fg=bright-blue
style 79-99 fg=cyan
7| "▌ '{printf \"line %04d: the quick brown fox jumps over the lazy dog\\n\", $1}', then return ONLY the "
style 0-0 fg=bright-blue
style 2-74 fg=cyan
8| "▌ number of lines in its output. Reply with just that number and stop. "
style 0-0 fg=bright-blue
9| "▌ "
style 0-0 fg=bright-blue
10| <blank>
11| " Reasoning "
style 1-9 fg=bright-black italic
12| " The user wants me to write a single run_code program that calls bash exactly once with a specific "
style 1-99 fg=bright-black italic
13| " command, then returns only the number of lines in its output. "
style 1-61 fg=bright-black italic
14| <blank>
15| "▌ "
style 0-0 fg=green
16| "▌ ✓ Count lines in seq/awk output "
style 0-0 fg=green
style 2-2 fg=green bold
style 3-32 bold
17| "▌ 200 "
style 0-0 fg=green
18| "▌ "
style 0-0 fg=green
19| <blank>
20| " Reasoning "
style 1-9 fg=bright-black italic
21| " The result is 200 lines. The user wants me to reply with just that number and stop. "
style 1-83 fg=bright-black italic
22| <blank>
23| " Assistant "
style 1-9 fg=bright-magenta bold
24| " 200 "
25| "────────────────────────────────────────────────────────────────────────────────────────────────────"
style 0-99 dim
26| " "
style 1-1 inverse
27| "────────────────────────────────────────────────────────────────────────────────────────────────────"
style 0-99 dim
28| "deepseek-v4-flash /workspace/project ↑123 ↓208 cache 99% 3% c"
style 0-93 dim
style 96-99 dim
29-35| <blank>