59e23a8030
Bound Assistant fallback startup latency
2026-06-07 04:33:37 +01:00
eda53f0b1a
Suppress compacted Assistant artifact text
2026-06-07 04:09:45 +01:00
b04a7f5938
Show skipped Assistant tools in transcript
2026-06-07 03:59:52 +01:00
132b466f39
Anchor Assistant final answers after tools
2026-06-07 01:09:51 +01:00
c25629ddf0
Keep provider reasoning out of visible answers
2026-06-07 01:01:41 +01:00
42f4a7028d
Surface Assistant idle progress on SSE streams
2026-06-07 00:06:34 +01:00
335c37b01a
Preserve explicit Assistant tool intent
2026-06-06 23:48:15 +01:00
ad8373eec6
Show Assistant provider route start events
2026-06-06 23:30:12 +01:00
e44b11f4d0
Improve Assistant tool activity rows
2026-06-06 21:58:17 +01:00
3c74fe2ca0
Start Assistant runtime in mock mode
2026-06-06 21:39:39 +01:00
d674d11ae8
Add Assistant mock tool stream fixture
2026-06-06 21:21:03 +01:00
e4ac092876
Add Assistant stream idle progress
2026-06-06 19:59:34 +01:00
44e8a1b2bd
Add Assistant turn undo and redo
2026-06-06 19:42:27 +01:00
5503e15d23
Add Assistant session rename
...
Add persisted session rename support across the chat store, API contract, and Assistant session picker.
2026-06-06 18:32:21 +01:00
d7c5e9c4f9
Implement Assistant session forking
2026-06-06 17:10:09 +01:00
2291924cb6
Show Assistant provider retry progress
2026-06-06 15:55:59 +01:00
49c23d6bed
Search Assistant session history
2026-06-06 09:14:06 +01:00
0ad040bdf0
Resolve Assistant plain-text resource context
...
Attach backend-resolved current_resource context for live Assistant read prompts.
2026-06-06 07:13:05 +01:00
0d8b90ce00
Suppress stale Assistant workflow status
2026-06-06 06:15:20 +01:00
3d5e4b7345
Strip Assistant decorative status symbols
2026-06-06 06:00:53 +01:00
d5d8999734
Preserve Assistant restored tool evidence
2026-06-06 05:44:02 +01:00
b55f50a482
Stream Anthropic tool argument progress
2026-06-06 05:20:42 +01:00
93344d61b3
Stream Assistant tool argument progress
2026-06-06 05:13:09 +01:00
f70c0214db
Align Assistant tool context and progress visibility
2026-06-06 04:02:07 +01:00
a7854bf341
Bound Assistant stream chunk stalls
2026-06-06 03:41:05 +01:00
ce4dc88ab7
Show Assistant model reasoning activity
2026-06-06 03:34:08 +01:00
ab99112ad2
Show Assistant tool starts while streaming
2026-06-06 03:12:25 +01:00
7c583c0547
Answer Assistant inventory counts locally
2026-06-06 01:47:05 +01:00
1f4477c27c
Show live Assistant tool progress
2026-06-06 01:12:01 +01:00
e1a9b69862
Bound provider stream startup waits
2026-06-06 00:34:45 +01:00
26bdfe27df
Add same-model OpenRouter chat fallback
2026-06-06 00:26:02 +01:00
73b0635c21
Improve Assistant inventory and activity flow
2026-06-06 00:17:44 +01:00
2ab0a60e99
Speed up Assistant stream startup
2026-06-05 22:54:44 +01:00
0d2f2a3cc8
Anchor Assistant stream and OpenRouter default
2026-06-05 22:02:47 +01:00
5ef50f712d
Expose Assistant fallback model route
2026-06-05 21:29:41 +01:00
17c4c1c172
Scope Assistant fast inventory turns
2026-06-05 21:17:16 +01:00
3d8a926acc
Keep Assistant tool-call leaks out of chat output
2026-06-05 20:29:24 +01:00
7067a51680
Make Assistant provider fallback resilient
2026-06-05 20:15:55 +01:00
c2dd431052
Prefer chat-suitable Assistant model routes
2026-06-05 19:36:16 +01:00
a648afaff0
Avoid duplicate Assistant stream errors
2026-06-05 19:29:07 +01:00
774d49e2a4
Fix Assistant current-resource tool routing
2026-06-05 19:10:46 +01:00
dae5daf6ac
Fix Assistant provider route validation
2026-06-05 18:48:57 +01:00
9c06cda3ea
Bound Assistant stream provider startup
2026-06-05 18:14:14 +01:00
5ea51b4b25
Harden Assistant stream output and OpenRouter token budget
2026-06-05 16:30:07 +01:00
064cd4bc80
Hide Assistant reasoning from message history
2026-06-05 15:43:06 +01:00
05d00a65a6
Hide raw Assistant tool-call output
2026-06-05 14:05:38 +01:00
c5bee4a785
Surface Assistant provider readiness
2026-06-05 12:50:02 +01:00
6ba21c7a2b
Clean up Assistant provider error messages
2026-06-05 12:25:56 +01:00
479ac6db2c
Stream Assistant cold sessions directly
2026-06-05 11:54:01 +01:00
2b24c375e0
Abstain instead of fabricating discovery when commands can't run
...
When a deep scan was attempted for a workload (container/VM) but produced no
command output — e.g. the host agent rejects exec — the AI analyzer was still
asked to identify the service from metadata alone. It confabulated confident,
false identities: an ESPHome LXC and an influxdb-telegraf LXC were both
"identified" as Pi-hole at 0.95 confidence, with invented facts carrying
fabricated command sources (source: "pihole -v" for a command that never ran)
and a docker exec CLI for an LXC.
When a command scan was attempted for a command-dependent resource type but
yielded nothing, abstain: skip the analyzer entirely and return a not-determined
result (no service, no facts, zero confidence) with guidance to enable Pulse
Commands. Host agents are unaffected (identified from their own metadata), and
deployments without command scanning keep the metadata-only path. Abstaining
also avoids a wasted model call.
Verified live: re-running discovery on the esphome LXC now returns an empty,
zero-confidence result with the correct container CLI instead of fabricated
Pi-hole facts. Adds a regression test.
2026-06-05 09:57:57 +01:00
rcourtman