lkn
/
ollie-9p
Archived
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

server: update mode mappings for spec; drop removed session files 

spec is 0666; offset/statewait/systemprompt/models/ctxsz/usage are
0444 explicitly. Remove mode cases for state, backend, model, agent,
cwd, params, cwdwait, usagewait, ctxszwait. Update README.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Levi Neely 2026-04-24 07:42:58 +02:00
parent f1a60264e2
commit b432ba987c
2 changed files with 14 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
README.md
View File

@ -44,25 +44,24 @@ ollie/
Interactive session directories (multi-turn, idle<=>running): Interactive session directories (multi-turn, idle<=>running):
<session-id>/ rm -r to kill; mv to rename <session-id>/ rm -r to kill; mv to rename
agent r/w: active agent name spec r/w: KV snapshot of config and current state; write partial KV to mutate
backend r/w: active backend name read fields: state, backend, model, agent, cwd, usage, ctxsz, offset,
maxTokens, temperature, frequencyPenalty, presencePenalty
writable fields: backend, model, agent, cwd, maxTokens, temperature,
frequencyPenalty, presencePenalty
(state, usage, ctxsz, offset are read-only; silently ignored on write)
chat read: cumulative conversation history chat read: cumulative conversation history
ctl write: stop | <command> ctl write: stop | <command>
ctxsz read: estimated context size vs context window
ctxszwait read: blocks until ctxsz changes; returns new value
cwd r/w: working directory for tool execution
cwdwait read: blocks until cwd changes; returns new value
fifo.in write: queue a prompt for later execution fifo.in write: queue a prompt for later execution
fifo.out read: pop the next queued prompt fifo.out read: pop the next queued prompt
model r/w: active model name offset read: byte offset in chat immediately after the last user prompt
models read: available models from the backend
params r/w: generation parameters (maxTokens, temperature, etc.)
prompt write: submit a prompt to the agent prompt write: submit a prompt to the agent
state read: current agent state (idle, thinking, calling: <tool>) statewait read: blocks until state changes; returns new state
statewait read: blocks until state changes; returns new value
systemprompt read: fully rendered system prompt for this session
usage read: token counts (input, output, requests; [estimated] if not reported by backend) usage read: token counts (input, output, requests; [estimated] if not reported by backend)
usagewait read: blocks until usage changes; returns new value ctxsz read: estimated context size vs context window
models read: available models from the backend
systemprompt read: fully rendered system prompt for this session
tail exec: exec tail -f chat
Batch job directories (one-and-done: running => done | failed): Batch job directories (one-and-done: running => done | failed):
<job-id>/ rm -r to cancel and remove <job-id>/ rm -r to cancel and remove

4
server.go
View File

@ -1362,9 +1362,9 @@ func (s *Server) makeStat(path string) plan9.Dir {
switch base { switch base {
case "ctl", "prompt", "fifo.in": case "ctl", "prompt", "fifo.in":
mode = 0200 mode = 0200
case "chat", "state", "usage", "ctxsz", "models", "fifo.out": case "chat", "usage", "ctxsz", "models", "fifo.out", "offset", "statewait", "systemprompt":
mode = 0444 mode = 0444
case "backend", "agent", "model", "cwd": case "spec":
mode = 0666 mode = 0666
case "tail": case "tail":
mode = 0555 mode = 0555