open/voyage
1
0
Fork 0
Code Issues Releases 1 Activity

docs(agent-return-channel): record what akashic's full-scale numerator closes, and what it does not

Browse source 
akashic-intelligence recovered its four S25 agents' on-disk final text against
the full 3730-line / 277 KB plan (commit e281a9d): 4/4 produced correct output,
delivery alone failed. That closes the size-dependent-work question the caveat
left open. It does not close the returning arm above 66 lines -- all four of
their cells were named -- so that stays stated as inferred, not observed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018w5KWrbxzmki5wdXULT8nU
This commit is contained in:
Kjell Tore Guttormsen 2026-08-18 16:45:45 +02:00
commit f9ebf08cba
1 changed files with 24 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

24
docs/agent-return-channel-defect.md
View file

@ -153,6 +153,30 @@ measured in either arm. Nothing here rules out a *separate*, size-dependent
failure at akashic's scale — it only establishes that the failure they observed
reproduces at 66 lines, where size cannot be the cause.
**External measurement closes half of that (2026-08-17).** `akashic-intelligence`
recovered its own S25 transcripts from
`~/.claude/projects/<slug>/<session>/subagents/` and read the last assistant
text block out of each. Denominator: 4 of 4 agents, all **named**, all against
the full 3730-line / 277 KB plan. Three produced valid JSON review output
(17, 8 and 13 findings); the fourth was their PONG control and produced
`PONG`. Their commit `e281a9d`.
What that closes: **the work is performed at 3730 lines.** No size-dependent
failure of the agent's *reasoning or output* exists at that scale — the named
arm produces correct final text at 66 lines and at 3730 lines alike, and only
delivery fails, identically at both. The 38 recovered findings were re-used
instead of re-run.
What it does **not** close: their four cells were all named, so the *returning*
(unnamed) arm still has no measurement above 66 lines. That a plain subagent
returns a 21 KB result at that scale is inferred, not observed. Stated as
inferred.
Their PONG control also carries the same lesson as cell 1 above, in a third
repo: S25 reported that agent as having "gone idle without sending PONG". It
sent PONG. Absence of *delivery* was read as absence of *work* — the same
face-4 error, three times in one evening.
## Where the defect lives
**Outside this repository.** Nothing in `agents/plan-critic.md` or