59ea107d09
refactor(agents): delete dead model-selection surface and consolidate compaction targets ( #122474 )
...
* refactor(agents): delete dead model-selection surface, consolidate compaction target assembly
Removes production surface with zero live callers: buildConfiguredAllowlistKeys
(orphaned since fallback allowlist filtering was split out), the
retryTransientProviderRuntimeMiss resolveModelAsync option (its gateway startup
prewarming caller was replaced by prepared runtime snapshots), the ignored
useAsyncModelResolution plumbing (kept only as a deprecated no-op field on the
plugin-SDK-shipped prepareSimpleCompletionModelForAgent), and dead facade
re-exports (inferUniqueProviderFromCatalog, ThinkLevel, ModelRefStatus).
Consolidates resolveEmbeddedCompactionTarget's five hand-built result sites into
one assembleTarget helper owning the auth-profile-drop-on-provider-change rule;
resolution precedence is unchanged and now pinned by new table-driven cases
(unique-provider inference, ambiguous literal, profile-suffix preservation).
Net -93 production LOC, -106 test LOC.
* chore(sdk): regenerate plugin SDK API baseline after facade export removals
2026-08-11 23:37:15 -07:00
e74be5d41d
refactor: eliminate final wrapper-shadowing hazards ( #122157 )
...
* refactor: disambiguate wrapper-shadowed exports
* test: align renamed session and facade boundaries
* test: cover renamed runtime mock exports
* refactor: align remaining wrapper owner call sites
* test: align overlap-rebased runtime mocks
* refactor: preserve public SDK names after overlap rebase
* chore: regenerate wrapper shadowing baselines
* test: align cron model selection mocks
2026-08-11 13:34:24 -07:00
36fbd869ed
refactor(agents): eliminate export name collisions ( #121768 )
...
* refactor(auth): consolidate profile helper owners
* refactor(agents): consolidate subagent registry reads
* refactor(agents): disambiguate runtime placement helpers
* refactor(agents): disambiguate helper exports
* chore(scripts): burn export collision debt
* test(agents): follow moved subagent read owner
2026-08-10 22:24:33 -07:00
6c63c57fe2
perf(sessions): reuse plugin metadata during listing ( #117707 )
2026-08-01 17:22:49 -07:00
f94a790df5
refactor(agents): unify model selection policy ownership ( #117098 )
2026-07-31 16:42:09 -07:00
390f46d042
fix(agents): preserve fallback route provenance ( #114360 )
...
Co-authored-by: 1052326311 <65798732+1052326311@users.noreply.github.com >
2026-07-27 02:20:56 -04:00
cdb8d32bcc
refactor(agents): consolidate model normalization ( #112772 )
...
* refactor(agents): consolidate model normalization
* docs(agents): clarify normalization boundary
2026-07-22 19:19:41 -04:00
c4911a2c77
improve(ui): simplify coding agent session headers ( #112354 )
...
* improve: simplify coding session catalog headers
* improve: simplify coding session catalog headers
2026-07-21 15:27:49 -06:00
09a64f7ab0
feat(models): make per-agent allowlists explicit ( #110888 )
2026-07-18 21:42:05 +01:00
1b1cebfe42
fix(openai): align auth availability with effective routes ( #104685 )
...
* feat(openai): add provider-owned route facts
* fix(openai): harden provider route facts
* test(codex): update rebased auth fixtures
* chore: leave release notes to release workflow
* fix(openai): align route auth with current contracts
* test(openai): align route and shard expectations
* test(openai): satisfy route fixture contracts
* fix(openai): preserve direct profile forwarding
* test(models): complete route auth mocks
* test(codex): type compaction factory mock
* fix(openai): preserve provider-native model ids
* test(agents): align route auth fixtures
* style(agents): format route integrations
* test(plugin-sdk): pin current surface counts
2026-07-11 15:26:48 -07:00
59e95fe3fd
feat: support GPT-5.6 Ultra across OpenClaw and Codex runtimes ( #98021 )
...
* feat: support GPT-5.6 Ultra across agent runtimes
Co-authored-by: J Cai <anyech@gmail.com >
* fix: keep harness projections discovery-free
* fix(codex): mirror V2 native subagent tasks
* chore: refresh plugin SDK surface budgets
* test: expose Ultra wire effort proof
* test(cron): avoid hoisted mock initialization race
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com >
2026-07-10 15:23:24 +01:00
87aae9f11d
perf: skip manifest normalization in status summary ( #87831 )
2026-06-28 15:52:44 -07:00
e8895f0a99
docs: document model selection helpers
2026-06-04 09:51:42 -04:00
ff22b1e9e6
fix: apply ACP spawn model defaults
2026-05-31 15:07:33 +01:00
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
7ee5fe011b
refactor(agents): share model manifest context
2026-05-17 02:24:07 +01:00
20704ffab7
fix: reuse manifest metadata in model selection
2026-05-17 01:55:16 +01:00
2b04cedfb1
Fix subagent default model precedence ( #81783 )
...
* fix subagent default model precedence
* docs changelog for subagent default fix
2026-05-14 05:19:41 -05:00
377d7a0b4c
fix(telegram): simplify thinking defaults
2026-05-11 18:04:53 +05:30
f7a14e678b
fix: keep model visibility policy internal
2026-05-10 00:50:10 -04:00
2d78c72e5e
refactor: centralize model visibility policy
2026-05-10 00:50:10 -04:00
7f5728b4b2
fix: align wildcard model allowlist selection
2026-05-10 00:50:10 -04:00
2e495b07f3
Preserve provider wildcard allowlist intent
2026-05-10 00:50:10 -04:00
ebd776298f
Add provider wildcard model visibility
2026-05-10 00:50:10 -04:00
263469f696
fix(cli): canonicalize infer model refs safely ( #78940 )
...
* fix(cli): canonicalize infer model refs safely
* docs: add changelog entry for infer model ref canonicalization
---------
Co-authored-by: Mason Huang <masonxhuang@tencent.com >
2026-05-08 17:43:22 +08:00
6be5422fd6
fix(gateway): avoid plugin model resolution in session lists
2026-05-06 13:03:54 +05:30
a0e0bf5848
fix(status): ignore malformed persisted model fields
2026-05-03 12:28:04 -07:00
96886381a3
fix(status): tolerate malformed session model refs
2026-05-03 10:44:55 -07:00
323030594e
fix(agents): resolve model aliases in sessions_spawn ( #59681 )
...
* fix(agents): resolve model aliases in sessions_spawn
normalizeModelSelection() only trims the input — it never resolves
aliases through the model alias index. When a user passes an alias
like 'opus' to sessions_spawn, the child session gets patched with
the raw string, which the gateway cannot match to any provider.
Add resolveModelThroughAliases() to check bare strings against the
configured alias map before returning from
resolveSubagentSpawnModelSelection().
Fixes #57532
Refs #50736
* refactor: address review feedback on alias resolution
- Accept pre-built ModelAliasIndex instead of rebuilding per call
- Narrow helper signature to (string, ModelAliasIndex) → string
- Remove unreachable ?? raw fallback
Co-Authored-By: greptile-apps[bot]
* fix(agents): resolve sessions_spawn model aliases
---------
Co-authored-by: HowdyDooToYou <HowdyDooToYou@users.noreply.github.com >
Co-authored-by: vincentkoc <25068+vincentkoc@users.noreply.github.com >
2026-04-27 15:44:56 -07:00
a08a2e381f
fix: resolve bare fallback model providers
2026-04-24 18:16:25 +01:00
e61eba11e6
fix: avoid plugin normalization in status model refs
2026-04-23 04:43:25 +01:00
6ce17db11a
fix: gate max thinking by model support
2026-04-21 07:02:43 +01:00
310d2db312
refactor: share model selection helpers
2026-04-18 22:41:40 +01:00
d13869aab9
fix(models): resolve openrouter compat aliases ( #68579 )
...
* fix(models): resolve openrouter compat aliases
* fix(models): cover openrouter free interactive alias
* fix(models): mirror openrouter compat aliases in runtime resolver
* fix(models): align openrouter free allowlist aliases
2026-04-18 08:24:34 -07:00
117ae85bf5
perf(agents): isolate thinking default helper
2026-04-13 18:39:38 +01:00
d7fcd23091
fix(runtime): split cli provider and abort seams
2026-04-11 21:16:50 +01:00
74e7b8d47b
fix(cycles): bulk extract leaf type surfaces
2026-04-11 13:26:50 +01:00
7308e72fac
fix(cycles): continue seam extraction
2026-04-11 10:43:22 +01:00
a8bb0ab255
refactor: remove redundant model selection conversions
2026-04-10 22:00:02 +01:00
4977c4ab82
fix(control-ui): preserve configured model metadata in picker ( #61382 )
...
Merged via squash.
Prepared head SHA: c738f6f14683214007+Mule-ME@users.noreply.github.com >
Co-authored-by: mukhtharcm <56378562+mukhtharcm@users.noreply.github.com >
Reviewed-by: @mukhtharcm
2026-04-09 16:28:43 +05:30
65ea8c60f3
refactor: dedupe agent trimmed readers
2026-04-08 00:09:41 +01:00
d56fe040b4
refactor: dedupe agent lowercase helpers
2026-04-07 17:50:37 +01:00
9e61209780
refactor: dedupe agent lowercase helpers
2026-04-07 17:50:37 +01:00
8e4eaec394
refactor: dedupe agent lowercase helpers
2026-04-07 13:01:23 +01:00
6bd6f4d27c
refactor: dedupe shared lowercase helpers
2026-04-07 11:18:18 +01:00
86f15687b5
Agents: extract narrow model normalization seam
2026-04-07 12:05:27 +08:00
4436ca23ca
perf(agents): lazy cli backend setup lookup
2026-04-07 03:49:40 +01:00
0ffceca50a
test: align agent auth and model expectations
2026-04-06 17:02:10 +01:00
1fb44f0aad
fix: separate selected session model resolution
2026-04-06 16:07:50 +01:00
c39f061003
Revert "refactor(cli): remove bundled cli text providers"
...
This reverts commit 05d351c430
2026-04-06 13:40:41 +01:00
Peter Steinberger