Commit Graph

29 Commits

Author SHA1 Message Date
Ayaan Zaidi 3179692f0e fix(messages): apply response usage to followups 2026-06-24 07:12:33 -07:00
Peter Lindsey 6add1cc969 feat(messages): config-level default for the persistent /usage footer
Adds `messages.responseUsage` (precedence session -> channel -> config default
-> off) so the persistent /usage footer can default-on, with three distinct
states: explicit on (tokens/full), explicit off (persisted), and unset (inherit
the configured default).

Unifies effective-value resolution behind a single channel-aware resolver
`resolveEffectiveResponseUsage` used by reply rendering, the no-arg /usage
toggle, the ACP control, and the gateway session-row builder; the row builder's
`effectiveResponseUsage` is carried through sessions.changed events, chat
snapshots, and the UI row so live consumers never go stale. `/usage reset`
(aliases inherit/clear/default) clears the override to inherit; only explicit
off persists; a full session reset preserves the preference. ACP "Usage detail"
gains an "inherit" option for unset sessions. Docs/help/completions updated; "on"
documented as a legacy alias; config-doc baseline regenerated.
2026-06-24 07:12:33 -07:00
Vincent Koc 0a2ca1f7ac refactor(auto-reply): remove unused thinking exports 2026-06-22 20:43:04 +08:00
Vincent Koc 2b75806197 feat: forward-port fast talks auto mode (#85104) 2026-06-22 09:37:09 +08:00
Peter Steinberger 0e7b5c3429 feat(anthropic): support Claude Fable 5 adaptive thinking (#91882)
* feat(anthropic): support Claude Fable 5

* test(anthropic): tighten Fable stream fixtures

* fix(anthropic): preserve Vertex input types

* test(anthropic): use provider-ready Vertex effort

* fix(anthropic): support Fable deployment aliases

* fix(anthropic): discard incomplete Fable output

* feat(anthropic): support Fable on Bedrock

* fix(anthropic): preserve Fable reasoning contracts

* refactor(anthropic): unify canonical Claude model policy

* fix(anthropic): satisfy extension thinking types

* test(anthropic): complete canonical alias fixture

* fix(bedrock): scope thinking case declarations
2026-06-10 08:08:35 -07:00
Peter Steinberger 826cdd884c docs: document auto reply command contracts 2026-06-04 02:01:00 -04:00
Peter Steinberger 00d8d7ead0 refactor: extract normalization core package
Extract shared normalization/coercion helpers into private @openclaw/normalization-core workspace package while preserving existing plugin SDK helper subpaths.\n\nAlso keeps direct normalization-core imports internal, wires UI/build/loader resolution, and replaces the slow PR network CodeQL lane with a fast added-line boundary scan while retaining full CodeQL for scheduled/manual runs.\n\nVerification: local moved tests, plugin SDK boundary tests, extension loader tests, agents-support shard, UI build/test, build artifacts, lint, workflow guards, autoreview, and GitHub CI passed on PR head 963d893715.
2026-05-31 01:33:00 +01:00
rendrag-git e153eceea5 fix(vllm): wire configured thinking params
Move vLLM Qwen thinking control onto configured model compat metadata and carry it through catalog/model-selection/runtime thinking contexts.

Also migrate legacy provider/default request params in doctor and keep Pi/runtime model rows buildable with explicit reasoning defaults.

Thanks @rendrag-git.

Co-authored-by: rendrag-git <253747599+rendrag-git@users.noreply.github.com>
2026-05-27 13:32:18 +01:00
VACInc b8e2f648a7 chat: clear thinking and fast defaults 2026-05-09 06:51:20 -04:00
Peter Steinberger e816235c2d refactor: narrow dead reexports 2026-05-01 08:18:52 +01:00
Peter Steinberger 93d5cd1015 fix: honor configured xhigh thinking compat (#74273)
* fix: honor configured xhigh thinking compat

* test: update agent command model selection mock
2026-04-29 11:35:03 +01:00
Peter Steinberger bcfa781a1b fix: remap thinking levels on model switch 2026-04-21 18:53:49 +01:00
Peter Steinberger f1805ab54d fix: centralize provider thinking profiles 2026-04-21 09:13:35 +01:00
Peter Steinberger 6ce17db11a fix: gate max thinking by model support 2026-04-21 07:02:43 +01:00
Peter Steinberger e4adb0b0e3 fix: hide adaptive think option for GPT models 2026-04-21 06:19:29 +01:00
Peter Steinberger 7e28caa637 refactor: share fast mode normalization 2026-04-21 00:54:08 +01:00
Peter Steinberger 8ba5865383 chore: remove unused helpers 2026-04-18 20:53:35 +01:00
Tak Hoffman 7c09ba70ef fix(trace command): Improve trace raw diagnostics and trace command UX (#66089)
* improve trace raw diagnostics and command acks

* address trace review feedback

* avoid sync transcript reads in raw trace

* preserve raw cli output for trace

* gate trace emission at reply time

* reflect raw trace mode in status surfaces
2026-04-13 14:26:57 -05:00
Tak Hoffman c37e49f275 Add /trace toggle and fix Active Memory diagnostics 2026-04-12 13:20:22 -05:00
Peter Steinberger cebfa70277 refactor: dedupe auto-reply lowercase helpers 2026-04-07 17:50:37 +01:00
Peter Steinberger 3a2e347dc7 refactor: dedupe auto-reply lowercase parsers 2026-04-07 12:18:22 +01:00
Peter Steinberger fca80d2ee2 refactor(thinking): move provider thinking fallback out of core 2026-04-04 07:00:47 +01:00
Shakker 8d5c11d31b refactor: trim thinking helper import graph 2026-04-04 01:07:28 +09:00
Peter Steinberger b8069c2bd1 refactor: trim provider model compat seams 2026-03-28 00:17:28 +00:00
Peter Steinberger 13316a9118 refactor: reuse shared model prefix helper in thinking 2026-03-28 00:00:08 +00:00
Peter Steinberger 2a06097184 test: update codex test fixtures to gpt-5.4 2026-03-23 02:14:00 -07:00
Peter Steinberger a0d3dc94d0 perf: reduce unit test hot path overhead 2026-03-18 18:19:40 +00:00
Peter Steinberger fe4368cbca fix: align thinking defaults and plugin sdk exports 2026-03-17 03:16:39 +00:00
Vincent Koc 30c31d4efd UI: keep thinking helpers browser-safe 2026-03-16 01:49:41 -07:00