Strixa AI
TopicsSearchPricing
Sign inStart tracking

Signal Detail

Loading signal detail

Reading this signal card's judgment, risks, and evidence.

Strixa AI
TopicsSearchPricing
Sign inStart tracking
Back to Signal Feed
CodeTracked since May 21, 2026

Gateway uses startup AppConfig snapshot, causing config.yaml changes to be ignored during runs

In bytedance/deer-flow v2.0-m1-rc1, changes to `config.yaml` (notably `max_tokens`) do not reliably apply while the gateway is running. The gateway initializes `request.app.state.config` once at startup, passes that object through run context and runtime/agent factories, and therefore executes subsequent runs against old settings until the process is restarted.

AppConfigconfig.yamlgatewayrequest.app.state.config

Signal Intelligence

Confidence Level95%
Worth Continued TrackingFinal score 84% with 1 evidence item.
Primary Impact Areas
AppConfigconfig.yamlgateway

What Happened

  • In bytedance/deer-flow v2.0-m1-rc1, changes to `config.yaml` (notably `max_tokens`) do not reliably apply while the gateway is running. The gateway initializes `request.app.state.config` once at startup, passes that object through run context and runtime/agent factories, and therefore executes subsequent runs against old settings until the process is restarted.
  • In bytedance/deer-flow v2.0-m1-rc1, changes to `config.yaml` (notably `max_tokens`) do not reliably apply while the gateway is running. The gateway initializes `request.app.state.config` once at startup, passes that object through run context and runtime/agent factories, and therefore executes subsequent runs against old settings until the process is restarted.
  • 1 evidence item attached for review.

What is Different

Before

Scattered source updates, isolated context, and manual follow-up across multiple feeds.

Now

The issue identifies a concrete behavior bug: the run path in the gateway binds to a startup `AppConfig` object instead of a freshly reloaded config, so updates to file-backed configuration are not consistently propagated to `RunContext`, runtime initialization, and downstream runtime components.

Why Track This

Why It Matters

Operators using the local Docker stack can change config files expecting immediate effect, but many runs continue with old startup values (for example an 8192 token cap) until a gateway restart, which makes behavior inconsistent between consecutive runs and can cause unexpected truncation-driven retries and extra cost. The technical root is that `app.state.config` is set once at startup and then threaded through `get_config`, worker runtime context, and lead-agent creation, bypassing reload checks in `get_app_config()` on active request/run paths. This is especially important for users relying on dynamic tuning of model output limits or runtime backends during long Ultra workflows, and it should be watched for whether the product moves to true hot-reload semantics or introduces an explicit, clearly surfaced restart-required boundary for affected fields.

Impact

Operators using the local Docker stack can change config files expecting immediate effect, but many runs continue with old startup values (for example an 8192 token cap) until a gateway restart, which makes behavior inconsistent between consecutive runs and can cause unexpected truncation-driven retries and extra cost. The technical root is that `app.state.config` is set once at startup and then threaded through `get_config`, worker runtime context, and lead-agent creation, bypassing reload checks in `get_app_config()` on active request/run paths. This is especially important for users relying on dynamic tuning of model output limits or runtime backends during long Ultra workflows, and it should be watched for whether the product moves to true hot-reload semantics or introduces an explicit, clearly surfaced restart-required boundary for affected fields.

What To Watch Next

  • Watch whether AppConfig becomes a repeated pattern.
  • Track follow-up changes around AI Agents.
  • Compare future signals against this evidence trail.
  • Re-check risk flags: runtime_starts_with_stale_app_config, runtime_components_not_rebound_after_config_change.
Open Topic TimelineOpen Technical EventOpen Original Sourceruntime_starts_with_stale_app_config / runtime_components_not_rebound_after_config_change / silent_runtime_behavior_divergence / restart_boundary_not_explicit_to_users

Supporting Evidence

GITHUB ISSUEHigh Trust

bytedance/deer-flow Issue #3107: [Stability][v2.0-m1-rc1] Release-blocking issues found in Ultra/user workflow testing

Issue #3107 documents a reproducible stale-config path in the local Docker workflow where runtime components and run-time model limits remain bound to gateway startup state.