Ilker ManapandClaude Opus 5 eaf3382a6d Give an operator a way to turn conversation storage on ...

SetThreadRetention existed and nothing called it, so the feature was
unreachable: a project could never opt in and every request carrying a thread
was refused.

A command rather than a configuration key, because it is a decision about data
rather than about deployment. Someone has to choose to keep what a team types,
and choosing it should look like an act rather than like a default nobody
read.

--retain-hours is required. Without a number the command would create exactly
the thing the design avoids: a conversation store with no expiry, holding
everything a team ever typed because nobody chose one.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-09-18 11:54:31 +02:00

..

agent.go

Fix an agent that could neither explain itself nor stop

2026-09-16 08:03:21 +02:00

bench.go

Align the bench table, which a tabwriter cannot

2026-09-16 09:59:55 +02:00

cert.go

Add a private CA and mutual TLS for the agent stream

2026-09-16 07:28:56 +02:00

ctl.go

Refuse a node with no room, and take back only what llmgw put there

2026-09-18 09:51:05 +02:00

ctlweights.go

Refuse a node with no room, and take back only what llmgw put there

2026-09-18 09:51:05 +02:00

dispatcherref_test.go

Carry the delete capability through the indirection that hid it

2026-09-18 09:56:36 +02:00

enginecheck_test.go

Ship binaries with releases, and ask engines whether our flags still exist

2026-09-16 16:44:29 +02:00

enginecheck.go

Check llmgw's engine flags against real vLLM and llama.cpp

2026-09-16 16:52:11 +02:00

keys.go

Give an operator a way to turn conversation storage on

2026-09-18 11:54:31 +02:00

model.go

Work out whether a model fits the cluster, and how to split it

2026-09-17 07:46:53 +02:00

modelplan.go

Make the planned entry use an engine that can serve the precision

2026-09-17 07:48:20 +02:00

root.go

Let people sign up, be approved, and issue their own keys

2026-09-16 09:32:35 +02:00

server.go

Carry the delete capability through the indirection that hid it

2026-09-18 09:56:36 +02:00

simengine.go

Onboard a node with a script, and find two examples that never worked

2026-09-16 12:28:36 +02:00

status_test.go

Make the planned entry use an engine that can serve the precision

2026-09-17 07:48:20 +02:00

status.go

Know where the weights are, without owning the storage

2026-09-17 08:21:16 +02:00

threads.go

Give an operator a way to turn conversation storage on

2026-09-18 11:54:31 +02:00

toolcheck_test.go

Stop tool-check blaming the engine for what the model did

2026-09-18 08:31:09 +02:00

toolcheck.go

Stop tool-check blaming the engine for what the model did

2026-09-18 08:31:09 +02:00

users.go

Serve the cluster dashboard over the web, without serving pprof with it

2026-09-16 10:46:45 +02:00