xingsy97 2c39cd0953 fix(agents): rephrase session reset prompt to avoid Azure content filter (#43403) ...

* fix(agents): rephrase session reset prompt to avoid Azure content filter

Azure OpenAI's content filter flags the phrase 'Execute your Session
Startup sequence now' as potentially harmful, causing /new and /reset
to return 400 for all Azure-hosted deployments.

Replace 'Execute ... now' with 'Run your Session Startup sequence' in
session-reset-prompt.ts and post-compaction-context.ts. The semantics
are identical but the softer phrasing avoids the false-positive.

Closes #42769

* ci: retrigger checks (windows shard timeout)

* fix: add changelog for Azure startup prompt fix (#43403) (thanks @xingsy97)

---------

Co-authored-by: Ayaan Zaidi <hi@obviy.us>

2026-03-13 15:07:03 +05:30

..

reply

fix(agents): rephrase session reset prompt to avoid Azure content filter (#43403)

2026-03-13 15:07:03 +05:30

test-helpers

…

chunk.test.ts

…

chunk.ts

…

command-auth.owner-default.test.ts

…

command-auth.ts

…

command-control.test.ts

…

command-detection.ts

…

commands-args.test.ts

…

commands-args.ts

…

commands-registry.data.ts

feat: add fast mode toggle for OpenAI models

2026-03-12 23:31:31 +00:00

commands-registry.test.ts

feat: add fast mode toggle for OpenAI models

2026-03-12 23:31:31 +00:00

commands-registry.ts

…

commands-registry.types.ts

…

dispatch.test.ts

…

dispatch.ts

…

envelope.test.ts

…

envelope.ts

…

fallback-state.test.ts

…

fallback-state.ts

…

group-activation.ts

…

heartbeat-reply-payload.ts

…

heartbeat.test.ts

…

heartbeat.ts

…

inbound-debounce.ts

…

inbound.test.ts

…

media-note.test.ts

…

media-note.ts

…

media-understanding.test-fixtures.ts

…

model-runtime.ts

…

model.test.ts

…

model.ts

…

reply.block-streaming.test.ts

…

reply.directive.directive-behavior.applies-inline-reasoning-mixed-messages-acks-immediately.test.ts

…

reply.directive.directive-behavior.defaults-think-low-reasoning-capable-models-no.test.ts

…

reply.directive.directive-behavior.e2e-harness.ts

feat: add fast mode toggle for OpenAI models

2026-03-12 23:31:31 +00:00

reply.directive.directive-behavior.e2e-mocks.ts

…

reply.directive.directive-behavior.model-directive-test-utils.ts

…

reply.directive.directive-behavior.prefers-alias-matches-fuzzy-selection-is-ambiguous.test.ts

…

reply.directive.directive-behavior.shows-current-verbose-level-verbose-has-no.test.ts

feat: add fast mode toggle for OpenAI models

2026-03-12 23:31:31 +00:00

reply.directive.parse.test.ts

feat: add fast mode toggle for OpenAI models

2026-03-12 23:31:31 +00:00

reply.heartbeat-typing.test.ts

…

reply.media-note.test.ts

…

reply.raw-body.test.ts

…

reply.test-harness.ts

…

reply.triggers.group-intro-prompts.cases.ts

…

reply.triggers.trigger-handling.filters-usage-summary-current-model-provider.cases.ts

…

reply.triggers.trigger-handling.stages-inbound-media-into-sandbox-workspace.test.ts

…

reply.triggers.trigger-handling.targets-active-session-native-stop.e2e.test.ts

…

reply.triggers.trigger-handling.test-harness.ts

fix(agents): rephrase session reset prompt to avoid Azure content filter (#43403)

2026-03-13 15:07:03 +05:30

reply.ts

…

send-policy.ts

…

skill-commands.test.ts

…

skill-commands.ts

…

stage-sandbox-media.test-harness.ts

…

status.test.ts

feat: add fast mode toggle for OpenAI models

2026-03-12 23:31:31 +00:00

status.ts

feat: add fast mode toggle for OpenAI models

2026-03-12 23:31:31 +00:00

templating.ts

Telegram: exec approvals for OpenCode/Codex (#37233)

2026-03-09 23:04:35 -04:00

thinking.test.ts

feat(ui): dashboard-v2 views refactor (slice 3/3 of dashboard-v2) (#41503)

2026-03-12 12:46:19 -05:00

thinking.ts

feat: add fast mode toggle for OpenAI models

2026-03-12 23:31:31 +00:00

tokens.test.ts

…

tokens.ts

…

tool-meta.test.ts

…

tool-meta.ts

…

types.ts

feat: show status reaction during context compaction (#35474)

2026-03-12 21:06:15 -07:00