Validate session IDs before resume and persist Claude stderr#57
Open
Richuthegreat14 wants to merge 4 commits into
Open
Validate session IDs before resume and persist Claude stderr#57Richuthegreat14 wants to merge 4 commits into
Richuthegreat14 wants to merge 4 commits into
Conversation
Key changes: - Windows: set HOME from USERPROFILE, unset CLAUDECODE for nested sessions, explicit binary path to avoid PATHEXT issues - Agent timeout default changed to 0 (unlimited) with safe clearTimeout guards - Surface agent errors to users for easier diagnostics - Downgrade memory-ingest missing-key logs; skip OAuth file check when using keychain - Upgrade better-sqlite3 to v12, revert Gemini model to 2.0-flash - Expand esbuild platform binaries for cross-platform builds Co-Authored-By: Claude Opus 4.7 (1M context) <<EMAIL>>
Co-Authored-By: Oz <oz-agent@warp.dev>
- add UUID validation guard so invalid session IDs do not get passed as --resume - fall back to fresh session when session ID format is invalid - persist full Claude subprocess stderr to logs/claude-subprocess-stderr.log for debugging - keep structured stderr warnings in existing logger output Co-Authored-By: Oz <oz-agent@warp.dev>
Threadbury
pushed a commit
to Threadbury/claudeclaw
that referenced
this pull request
Jun 14, 2026
…duled tasks (earlyaidopters#57) The mission_task and scheduled_task execution paths were calling runAgent with `model` parameter as undefined, causing the SDK to fall through to its default model regardless of agent.yaml `model:` field. Interactive Telegram path (bot.ts:519) was honoring the yaml correctly via agentDefaultModel, but background tasks were not. Verified via temporary diagnostic log: post-fix, research/Scooby's runAgent receives 'claude-opus-4-7' and viral receives 'claude-sonnet-4-6' matching their yaml configs. Pre-fix, both received undefined. Impact: every model registry update (e.g. yesterday's Scooby->Opus 4.7 and Viral->Sonnet 4.6 bumps) was silently a no-op for any background task. Affects only mission_tasks + scheduled_tasks — interactive paths were always correct. Three-line change: - Import agentDefaultModel from config.js - Pass it as positional arg 5 (model) at line 95 (scheduled tasks) - Pass it as positional arg 5 (model) at line 169 (mission tasks) Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Threadbury
pushed a commit
to Threadbury/claudeclaw
that referenced
this pull request
Jun 14, 2026
…ToAgent (#67) ## Bug `src/orchestrator.ts:209` calls `runAgent()` with `undefined` for the `model` parameter inside `delegateToAgent`. When a sync delegation (`@research: ...` from the chat parser) fires, the SDK falls through to its default model regardless of the `model:` field declared in the target specialist's `agent.yaml`. Same theme as earlyaidopters#57 (`fix(scheduler): pass agentDefaultModel to runAgent for mission + scheduled tasks`), but the orchestrator path is a separate callsite that earlyaidopters#57 did not touch. ## Impact For any user with non-default `model:` values across agents (e.g. main on `claude-opus-4-7`, specialists on `claude-sonnet-4-6`), sync delegations from the orchestrator have been silently running on the SDK default. The interactive DM path to each specialist's own bot already honoured the override (it goes through `bot.ts` which passes `agentDefaultModel`), but every `@<id>:` delegation from the orchestrator landed on the wrong model. Empirically: in a deploy where specialists were configured as `claude-sonnet-4-6` while main remained on Opus default, a delegate roundtrip took ~68s pre-fix vs ~10s post-fix — consistent with the Sonnet vs Opus latency ratio, confirming the target's model was being ignored. ## Why `agentConfig.model`, not `agentDefaultModel` `delegateToAgent` runs **in-process** inside the orchestrator (main). The module-level `agentDefaultModel` exported from `config.ts` is set once per process at startup, from the *caller* agent's `agent.yaml`. Inside main's process that's main's model (typically `undefined` since main doesn't have an agent.yaml in the default layout), NOT the target's. The target's config is already loaded on the line above the runAgent call (`const agentConfig = loadAgentConfig(agentId)` at line 174), so `agentConfig.model` is the correct source. Inline comment in the diff documents the distinction so a future contributor doesn't "simplify" it to `agentDefaultModel` and silently break delegations. ## Fix One field in `src/orchestrator.ts`: pass `agentConfig.model` as the positional `model` arg (instead of `undefined`) to the `runAgent()` call inside `delegateToAgent`. No new imports (`loadAgentConfig` is already imported and used a few lines above). No behaviour change for users with no `model:` field set in their agents — `agentConfig.model` is `string | undefined`, so the fallthrough to SDK default still applies. Test changes not required; existing tests don't exercise this parameter. ## Relation to prior work - earlyaidopters#57 (merged) fixed the same theme in `src/scheduler.ts` for `runAgent` call sites that run inside the *target* process (where `agentDefaultModel` is correctly the target's). The orchestrator callsite needs `agentConfig.model` instead because it runs in-process from a different agent. - Conceptually adjacent to earlyaidopters#47 — model overrides should be honoured consistently across surfaces.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
esume to the Claude subprocess
Validation
Artifacts
Co-Authored-By: Oz oz-agent@warp.dev