Teknium 69c999f8a7 fix(agent): keep the tripping correction and explain the restart-bound exit ...

When the redirect cap trips, the correction that cancelled the final attempt is
still sitting in _pending_redirect; finalize_turn's clear_interrupt() would drop
it silently. Drain it into the steer slot so it rides result["pending_steer"] and
becomes the next user turn on every surface that already honours that key.

Both new exit reasons get a turn-completion explanation so the user sees why the
turn stopped instead of an empty reply.

2026-09-09 09:51:31 -07:00

..

lsp

fix: keep Kanban worker scope out of descendant processes

2026-09-07 07:10:28 -07:00

monitoring

fix: cron and local DMs reach an open Desktop Bot Chat

2026-09-07 16:48:29 -07:00

pet

…

proxy_sources

…

secret_sources

…

transports

fix(openai): drop prompt_cache_options from Astra requests — not an SDK kwarg, 30m is the server default

2026-09-07 21:43:54 +05:30

verify

refactor(verify): one honest return type for the compose live-state probe (str | None)

2026-09-06 20:50:02 +05:30

__init__.py

…

account_usage.py

…

acp_openai_bridge.py

…

activity_tracking.py

…

agent_init.py

fix(compressor): thread custom_providers into context-length resolution

2026-09-08 02:27:01 +05:30

agent_runtime_helpers.py

fix(agent): a persisted /steer row survives the next prompt's alternation repair; typed for history

2026-09-09 12:21:28 +05:30

AGENTS.md

fix(agent): the pre-API-call /steer drain also stops smearing the persisted tool row

2026-09-09 12:21:28 +05:30

anthropic_adapter.py

…

anthropic_credentials.py

fix: prefer owned Anthropic grants and bind auxiliary refresh to request credentials

2026-09-07 08:07:26 -07:00

anthropic_endpoints.py

fix(anthropic): DeepSeek thinking replay contract for third-party proxies

2026-09-06 05:37:03 -07:00

anthropic_message_convert.py

fix(anthropic): DeepSeek thinking replay contract for third-party proxies

2026-09-06 05:37:03 -07:00

api_error_summary.py

…

api_request_hooks.py

…

async_utils.py

…

aux_accounting.py

…

auxiliary_client.py

fix(openai): drop prompt_cache_options from Astra requests — not an SDK kwarg, 30m is the server default

2026-09-07 21:43:54 +05:30

auxiliary_health.py

refactor: isolate custom health identity and trim redundant alias tests

2026-09-07 07:06:58 -07:00

auxiliary_wire.py

fix: sanitize resolved auxiliary chat requests before dispatch

2026-09-07 06:02:22 -07:00

azure_identity_adapter.py

…

backend_identity.py

fix(agent): preserve route URL path identity

2026-09-07 07:06:58 -07:00

background_review.py

fix(review): keep /refine under the background_review origin; attendedness is its own flag

2026-09-09 12:19:13 +05:30

battery.py

…

bedrock_adapter.py

…

billing_links.py

…

billing_usage.py

…

billing_view.py

…

bounded_response.py

…

browser_provider.py

…

browser_registry.py

…

chat_completion_helpers_relay.py

…

chat_completion_helpers.py

fix(agent): close the interrupted tool tail on the overflow terminal

2026-09-09 17:45:12 +05:30

chat_completion_nonstream.py

fix: wait sixty seconds before provider silence notices

2026-09-07 05:24:15 -07:00

chat_completion_stream_monitor.py

fix: wait sixty seconds before provider silence notices

2026-09-07 05:24:15 -07:00

client_lifecycle.py

fix: distinguish callable Anthropic bearer sources from OAuth text

2026-09-07 06:07:16 -07:00

codex_headers.py

…

codex_responses_adapter.py

fix(openai): drop prompt_cache_options from Astra requests — not an SDK kwarg, 30m is the server default

2026-09-07 21:43:54 +05:30

codex_runtime.py

fix(codex): keep transport echoes out of durable user history

2026-09-07 08:09:57 -07:00

coding_context.py

perf(prefix-cache): pin session-start workspace snapshot across compaction rebuilds

2026-09-06 22:45:31 +05:30

command_token_source.py

fix: keep command-auth model discovery lazy across config and setup

2026-09-07 21:22:49 -07:00

compaction_display.py

…

compression_facade.py

…

context_breakdown.py

fix(display): retain provider provenance for persisted fallback readings

2026-09-07 08:13:01 -07:00

context_compressor_summary.py

style: trim summary dispatch trailing whitespace

2026-09-07 05:59:08 -07:00

context_compressor.py

fix(compression): preserve batch clarify answers in summarize pass

2026-09-09 09:21:55 -07:00

context_engine.py

…

context_references.py

refactor(context): fold simplify findings into oversized-file fallback

2026-09-05 16:44:23 +05:30

conversation_compression.py

fix(agent): a persisted /steer row survives the next prompt's alternation repair; typed for history

2026-09-09 12:21:28 +05:30

conversation_loop.py

fix(agent): bound redirect/rebuilt restart refunds so a runaway turn can't hold the session lease

2026-09-09 09:51:31 -07:00

copilot_acp_client.py

…

credential_persistence.py

…

credential_pool_admin.py

feat: choose pooled credential priority from the CLI

2026-09-07 08:06:48 -07:00

credential_pool.py

feat: refresh one pooled OAuth grant from the CLI

2026-09-07 08:06:48 -07:00

credential_sources.py

…

credits_tracker.py

…

curator_backup.py

…

curator.py

fix: remove dedicated user-facing output cap controls

2026-09-07 06:15:43 -07:00

deadline.py

fix(process): stop late forks escaping deadline tree cleanup

2026-09-07 08:19:32 -07:00

delegation_context.py

fix: keep Kanban worker scope out of descendant processes

2026-09-07 07:10:28 -07:00

display.py

…

empty_response_guard.py

…

error_classifier.py

fix: trim opencode-go 422 salvage to the invariant set

2026-09-09 03:52:47 -07:00

error_surface.py

…

errors.py

…

estop.py

…

fallback_cooldown.py

fix: describe remaining retry eligibility without promising recovery

2026-09-07 07:08:25 -07:00

fast_mode.py

…

file_safety.py

…

gemini_native_adapter.py

…

gemini_schema.py

fix: preserve native Gemini union constraints

2026-09-07 21:10:50 -07:00

i18n.py

…

image_gen_provider.py

…

image_gen_registry.py

…

image_routing.py

fix: failed probe credentials cannot fall through to configured auth

2026-09-07 08:08:04 -07:00

image_token_cost.py

feat(compression): per-image token cost learned from the provider's own usage (#70328, supersedes #70463)

2026-09-06 14:19:42 -07:00

inline_tool_executors.py

fix(agent): forward the new_text alias in the memory inline executor

2026-09-07 06:05:13 -07:00

insights.py

…

interrupt_compat.py

…

interrupt_control.py

fix(agent): a /steer row is human input for every user-turn predicate

2026-09-09 13:08:25 +05:30

iteration_budget.py

fix: keep budget checkpoints out of cancelled tool results

2026-09-07 08:28:43 -07:00

jiter_preload.py

…

kanban_stop.py

…

lazy_forward.py

…

learn_prompt.py

…

learning_graph_render.py

…

learning_graph.py

…

learning_mutations.py

…

lmstudio_reasoning.py

…

manual_compression_feedback.py

…

markdown_tables.py

…

memory_manager.py

fix: mirror successful memory alias writes to providers

2026-09-07 06:05:13 -07:00

memory_provider.py

…

message_content.py

…

message_metadata.py

…

message_sanitization.py

…

micro_compaction.py

…

moa_loop.py

fix: remove dedicated user-facing output cap controls

2026-09-07 06:15:43 -07:00

moa_trace.py

…

model_metadata.py

feat(models): preserve live-verified Astra 900K opt-in from #103132

2026-09-07 21:43:54 +05:30

models_dev.py

test(openai): close Astra baseline review gaps

2026-09-07 21:43:54 +05:30

moonshot_schema.py

…

native_compaction.py

fix(compression): defer local preflight after native checkpoint

2026-09-06 09:09:00 -07:00

nous_rate_guard.py

…

nous_wire.py

feat(nous): anthropic_wire=auto decides a session's wire from its first response

2026-09-06 09:11:04 -07:00

onboarding.py

…

oneshot.py

…

opencode_affinity.py

…

outbound_webhooks.py

…

periodic_scheduler.py

refactor(agent): one _requeue for the three heappush sites; timing test asserts ordering, not a 0.3 s bound

2026-09-09 12:17:57 +05:30

plan_prompt.py

…

plugin_llm.py

…

plugin_stream_hooks.py

…

portal_tags.py

…

process_bootstrap.py

…

prompt_builder.py

fix(agent): a persisted /steer row survives the next prompt's alternation repair; typed for history

2026-09-09 12:21:28 +05:30

prompt_cache_boundary.py

…

prompt_cache_scope.py

…

prompt_caching.py

…

provider_base.py

…

provider_media.py

…

provider_projection.py

…

provider_registry.py

…

rate_limit_credits.py

…

rate_limit_tracker.py

…

reactions.py

…

reasoning_effort.py

refactor(openai): one is_astra_model predicate; gate Astra at the untrusted Codex inputs

2026-09-07 21:43:54 +05:30

reasoning_params.py

…

reasoning_summaries.py

fix: structured reasoning no longer breaks chat consumers

2026-09-07 08:24:54 -07:00

reasoning_timeouts.py

…

redact.py

…

relay_llm.py

…

relay_runtime.py

…

relay_tools.py

…

repetition_guard.py

…

replay_cleanup.py

…

retry_utils.py

…

review_engine.py

fix: make review workers recognizable in live subagent viewers

2026-09-08 04:38:47 -07:00

review_idle_queue.py

…

runtime_cwd.py

…

search_policy.py

…

secret_scope.py

test: exercise output-cap removal across native and child surfaces

2026-09-07 06:15:43 -07:00

session_activity.py

refactor(gateway): iteration-progress formatter lives in agent/session_activity, tests trimmed to the invariant bar

2026-09-06 05:35:12 -07:00

session_persistence.py

refactor(agent): one durable-row rule for the flush and the sidecar stamp; trim tests

2026-09-09 10:32:01 +05:30

shell_hooks.py

fix: keep Kanban worker scope out of descendant processes

2026-09-07 07:10:28 -07:00

side_question.py

…

skill_bundles.py

…

skill_commands.py

…

skill_preprocessing.py

fix: keep Kanban worker scope out of descendant processes

2026-09-07 07:10:28 -07:00

skill_utils.py

…

ssl_guard.py

…

ssl_verify.py

…

status_output.py

…

stream_delivery.py

…

stream_diag.py

…

stream_single_writer.py

…

subagent_lifecycle.py

…

subdirectory_hints.py

…

subscription_view.py

…

surface_switch.py

simplify(agent): surface switch — reuse flatten_message_text / agent_tool_names / one runtime-boundary split

2026-09-09 10:31:26 +05:30

system_prompt.py

simplify(agent): surface switch — reuse flatten_message_text / agent_tool_names / one runtime-boundary split

2026-09-09 10:31:26 +05:30

terminal_env_provider.py

…

terminal_env_registry.py

…

think_scrubber.py

…

thinking_timeout_guidance.py

…

thread_scoped_output.py

…

title_generator.py

…

tool_dispatch_helpers.py

…

tool_executor.py

fix(agent): stop the run-budget wrap-up notice from mutating a persisted tool row

2026-09-09 17:04:30 +05:30

tool_guardrails.py

…

tool_result_classification.py

…

trace_upload.py

refactor(state): fold the speculative-open retry into acquire's loop; keep real inode-swap tests

2026-09-06 22:56:51 +05:30

trajectory.py

…

transcript_repair.py

…

transcription_provider.py

…

transcription_registry.py

…

tts_provider.py

…

tts_registry.py

…

turn_api_call.py

…

turn_api_error.py

…

turn_api_request.py

…

turn_context_compaction.py

refactor(compression): every compaction gate asks real usage first; rough estimates only decide whether to wait

2026-09-06 13:21:17 -07:00

turn_context.py

fix(loop): the turn-boundary export skips preflight-timeout envelopes and stops re-anchoring the persist index

2026-09-09 12:55:43 +05:30

turn_empty_response.py

…

turn_explainers.py

fix(agent): keep the tripping correction and explain the restart-bound exit

2026-09-09 09:51:31 -07:00

turn_facade_lease.py

fix(agent): isolate periodic scheduler callbacks from blocking siblings (#102574)

2026-09-09 12:17:57 +05:30

turn_facade.py

…

turn_final_response.py

…

turn_finalizer.py

fix(display): distinguish estimated context from provider usage

2026-09-07 08:13:01 -07:00

turn_iteration_prep.py

fix(agent): keep the tripping correction and explain the restart-bound exit

2026-09-09 09:51:31 -07:00

turn_liveness.py

fix(agent): isolate periodic scheduler callbacks from blocking siblings (#102574)

2026-09-09 12:17:57 +05:30

turn_loop_errors.py

…

turn_overflow.py

…

turn_preflight_gate.py

refactor(compression): every compaction gate asks real usage first; rough estimates only decide whether to wait

2026-09-06 13:21:17 -07:00

turn_preflight.py

refactor(compression): every compaction gate asks real usage first; rough estimates only decide whether to wait

2026-09-06 13:21:17 -07:00

turn_recovery.py

fix(agent): normalize zero-cooldown semantics, dedupe test driver

2026-09-06 21:37:47 +05:30

turn_request_assembly.py

fix: remove dedicated user-facing output cap controls

2026-09-07 06:15:43 -07:00

turn_response_check.py

…

turn_response_intake.py

…

turn_retry_state.py

…

turn_stop_gates.py

…

turn_summary.py

…

turn_tool_round.py

…

turn_tool_validation.py

…

turn_truncation.py

fix(agent): close the interrupted tool tail on the overflow terminal

2026-09-09 17:45:12 +05:30

turn_usage.py

feat(compression): per-image token cost learned from the provider's own usage (#70328, supersedes #70463)

2026-09-06 14:19:42 -07:00

usage_anchor.py

feat(compression): usage anchor survives DB reloads and process restarts (salvage #99585)

2026-09-06 13:21:17 -07:00

usage_pricing.py

feat(openai): add GPT-6 Astra baseline support

2026-09-07 21:43:54 +05:30

verification_evidence.py

fix: verification evidence ledger is inert while verify_on_stop is off

2026-09-09 02:35:41 -07:00

verification_stop.py

…

verify_hooks.py

…

vertex_adapter.py

…

video_gen_provider.py

…

video_gen_registry.py

…

vision_message_prep.py

…

web_search_provider.py

…

web_search_registry.py

…