Conversation
Rename the core AI provider interface and all related types, classes, factory functions, and directory from clients/ to providers/. Rename map: - IAssistantClient → IAgentProvider - ClaudeClient → ClaudeProvider - CodexClient → CodexProvider - getAssistantClient → getAgentProvider - AssistantRequestOptions → AgentRequestOptions - IWorkflowAssistantClient → IWorkflowAgentProvider - AssistantClientFactory → AgentProviderFactory - WorkflowAssistantOptions → WorkflowAgentOptions - packages/core/src/clients/ → packages/core/src/providers/ NOT renamed (user-facing/DB-stored): assistant config key, DEFAULT_AI_ASSISTANT env var, ai_assistant_type DB column. No behavioral changes — purely naming.
…nd docs - AssistantDefaults → ProviderDefaults, ClaudeAssistantDefaults → ClaudeProviderDefaults - Logger domains: client.claude → provider.claude, client.codex → provider.codex - Fix stale JSDoc, error messages, and references in architecture docs, CHANGELOG, testing rules
- ProviderDefaults → CodexProviderDefaults (symmetric with ClaudeProviderDefaults) - Fix stale "AI client" comments in orchestrator-agent.ts and orchestrator.test.ts - Remove dead createMockAgentProvider in test/mocks/streaming.ts (zero importers, wrong method names) - Fix irregular whitespace in .claude/rules/workflows.md
…t-to-iagentprovider refactor: rename IAssistantClient to IAgentProvider
docs: consolidate Claude guidance into CLAUDE.md
…oleam00#1137) * refactor: extract providers from @archon/core into @archon/providers Move Claude and Codex provider implementations, factory, and SDK dependencies into a new @archon/providers package. This establishes a clean boundary: providers own SDK translation, core owns business logic. Key changes: - New @archon/providers package with zero-dep contract layer (types.ts) - @archon/workflows imports from @archon/providers/types — no mirror types - dag-executor delegates option building to providers via nodeConfig - IAgentProvider gains getCapabilities() for provider-agnostic warnings - @archon/core no longer depends on SDK packages directly - UnknownProviderError standardizes error shape across all surfaces Zero user-facing changes — same providers, same config, same behavior. * refactor: remove config type duplication and backward-compat re-exports Address review findings: - Move ClaudeProviderDefaults and CodexProviderDefaults to the @archon/providers/types contract layer as the single source of truth. @archon/core/config/config-types.ts now imports from there. - Remove provider re-exports from @archon/core (index.ts and types/). Consumers should import from @archon/providers directly. - Update @archon/server to depend on @archon/providers for MessageChunk. * refactor: move structured output validation into providers Each provider now normalizes its own structured output semantics: - Claude already yields structuredOutput from the SDK's native field - Codex now parses inline agent_message text as JSON when outputFormat is set, populating structuredOutput on the result chunk This eliminates the last provider === 'codex' branch from dag-executor, making it fully provider-agnostic. The dag-executor checks structuredOutput uniformly regardless of provider. Also removes the ClaudeCodexProviderDefaults deprecated alias — all consumers now use ClaudeProviderDefaults directly. * fix: address PR review — restore warnings, fix loop options, cleanup Critical fixes: - Restore MCP missing env vars user-facing warning (was silently dropped) - Restore Haiku + MCP tool search warning - Fix buildLoopNodeOptions to pass workflow-level nodeConfig (effort, thinking, betas, sandbox were silently lost for loop nodes) - Add TODO(coleam00#1135) comments documenting env-leak gate gap Cleanup: - Remove backward-compat type aliases from deps.ts (keep WorkflowTokenUsage) - Remove 26 unnecessary eslint-disable comments from test files - Trim internal helpers from providers barrel (withFirstMessageTimeout, getProcessUid, loadMcpConfig, buildSDKHooksFromYAML) - Add @archon/providers dep to CLI package.json - Fix 8 stale documentation paths pointing to deleted core/src/providers/ - Add E2E smoke test workflows for both Claude and Codex providers * fix: forward provider system warnings to users in dag-executor The dag-executor only forwarded system chunks starting with "MCP server connection failed:" — all other provider warnings (missing env vars, Haiku+MCP, structured output issues) were logged but never reached the user. Now forwards all system chunks starting with⚠️ (the prefix providers use for user-actionable warnings). * fix: add providers package to Dockerfile and fix CI module resolution - Add packages/providers/ to all three Dockerfile stages (deps, production package.json copy, production source copy) - Replace wildcard export map (./*) with explicit subpath entries to fix module resolution in CI (bun workspace linking) * chore: update bun.lock for providers package exports
…1160) * fix: make env-integration test cross-platform (Windows CI) Check for Windows env var equivalents (Path instead of PATH, USERPROFILE instead of HOME) in scenario 3 assertions. Closes coleam00#1128 * fix: Windows PATH/HOME casing in provider subprocess env test Same cross-platform fix for ClaudeProvider test — spread objects lose Windows case-insensitive behavior (Path vs PATH, USERPROFILE vs HOME).
…ies (coleam00#1162) * refactor: decompose provider sendQuery() into explicit helper boundaries (coleam00#1139) sendQuery() in both Claude and Codex providers was a monolith mixing SDK option building, nodeConfig translation, stream normalization, and error classification. This makes it hard to safely extend for Phase 2 provider extensibility. Decompose both providers into focused internal helpers: Claude: - buildBaseClaudeOptions: SDK option construction - buildToolCaptureHooks: PostToolUse/PostToolUseFailure hook setup - applyNodeConfig: workflow nodeConfig → SDK translation + structured warnings - streamClaudeMessages: raw SDK event → MessageChunk normalization - classifyAndEnrichError: error classification with retry decisions Codex: - buildTurnOptions: per-turn option construction (output schema, abort) - streamCodexEvents: raw SDK event → MessageChunk normalization - classifyAndEnrichCodexError: error classification with retry decisions Also introduces ProviderWarning { code, message } replacing raw string warnings for machine-readable provider translation warnings. Adds 43 focused unit tests covering the extracted helpers directly. Fixes coleam00#1139 * fix: export ToolResultEntry type used in public buildBaseClaudeOptions API * fix: unexport internal helpers to prevent API surface leakage, fix retry state bug Review findings: 1. Internal helpers were exported and reachable through package.json subpath exports (./claude/provider, ./codex/provider), widening the public API. All new helpers are now file-local — the only public exports remain ClaudeProvider, CodexProvider, loadMcpConfig, buildSDKHooksFromYAML, withFirstMessageTimeout, getProcessUid. 2. Codex streamState (lastTodoListSignature) was shared across retry attempts, causing todo-list dedup to suppress output on retry. Now creates fresh state per attempt. Removed direct helper test imports — existing sendQuery e2e tests (51 Claude + 42 Codex) cover all behavior paths. * fix: address review findings — abort handling, retry bugs, error swallowing Fixes from CodeRabbit + multi-agent review: 1. classifyAndEnrichError preserves first-event timeout diagnostic instead of collapsing it into generic "Query aborted" (the timeout aborts the controller, but the original error carries the coleam00#1067 breadcrumb) 2. nodeConfigWarnings emitted once before retry loop, not per attempt 3. buildSubprocessEnv() called once before retry loop (was re-logging auth mode and rebuilding { ...process.env } per attempt) 4. Abort signal listener registered once with forwarding to current controller (was accumulating per-retry listeners) 5. PostToolUse hook wrapped in try/catch (JSON.stringify can throw on circular refs — was asymmetric with PostToolUseFailure which had it) 6. Codex streamCodexEvents throws on abort instead of silent break (callers were getting truncated stream with no result/error) 7. Both providers store enrichedError (not raw error) for retry exhaustion — preserves stderr context in final throw 8. Log is_error result events at error level in Claude stream normalizer * test: add black-box behavioral tests for sendQuery decomposition fixes Restore test coverage for the specific fixes from the decomposition review, exercised through sendQuery (black-box) since helpers are file-local: Claude (6 tests): - Timeout error preserved (not collapsed into "Query aborted") - nodeConfig warnings emitted once even when retries occur - Abort signal cancels across retries via single forwarding listener - Enriched error (with stderr) thrown at retry exhaustion - PostToolUse hook handles circular reference without crashing - is_error result events logged at error level Codex (3 tests): - Abort signal throws instead of silently truncating stream - Enriched error thrown at retry exhaustion - Todo-list dedup state resets between retry attempts
- e2e-all-nodes: exercises bash, prompt, script (bun), structured output, model override (haiku), effort control, and $nodeId.output refs - e2e-mixed-providers: tests Claude + Codex in the same workflow with cross-provider output references - echo-args.js: simple script node test helper
…leam00#1135) Remove the entire env-leak scanning/consent infrastructure: scanner, allow_env_keys DB column usage, allow_target_repo_keys config, PATCH consent route, --allow-env-keys CLI flag, and UI consent toggle. The env-leak gate was the wrong primitive. Target repo .env protection is already structural: - stripCwdEnv() at boot removes Bun-auto-loaded CWD .env keys - Archon loads its own env sources afterward (~/.archon/.env) - process.env is clean before any subprocess spawns - Managed env injection (config.yaml env: + DB vars) is unchanged No scanning, no consent, no blocking. Any repo can be registered and used. Subprocesses receive the already-clean process.env.
* chore(homebrew): update formula to v0.3.6 * feat: open PRs as ready by default + pr-maintenance draft promotion (#1) * Fix pr-maintenance cron: prepend user bins to PATH When cron invoked the script every 15 min, PATH was the minimal /usr/bin:/bin. archon (installed at ~/.bun/bin/archon) was not findable, so every "launching archon" step died with: /mnt/ext-fast/archon/scripts/pr-maintenance-cron.sh: line 59: archon: command not found As a result PRs that needed conflict resolution stopped being processed — they just accumulated as DIRTY or UNKNOWN. Prepend $HOME/.bun/bin, $HOME/.local/bin, and /usr/local/bin to PATH at the top of the script. Works from cron and from an interactive shell unchanged. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat: open PRs as ready by default + pr-maintenance draft promotion Archon workflows previously created PRs with --draft, which meant even a CI-green PR would sit idle until a human marked it ready. Combined with the Phase 1 merge filter in pr-maintenance-cron.sh (which skips drafts), a green draft could linger indefinitely. This change removes --draft from all three unconditional gh pr create invocations so PRs open ready-for-review by default: - .archon/workflows/defaults/archon-fix-github-issue.yaml - .archon/workflows/defaults/archon-piv-loop.yaml - .archon/workflows/defaults/archon-ralph-dag.yaml Also includes the already-in-tree pr-maintenance-cron.sh additions that complement this: - Phase 0: promote any CLEAN draft PRs to ready (belt-and-suspenders for PRs that still open as drafts from other sources). - Surface gh pr merge stderr to the cron log so real failures (perms, branch protection, etc.) are diagnosable instead of silently swallowed. Together these eliminate "green draft sitting idle" as a failure mode. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * scripts: remove pr-maintenance-cron (moved to interstellarai.net) This script was never archon-specific — it was a cron wrapper that invokes archon workflows. It's been moved to alexsiri7/interstellarai.net:ops/cron/pr-maintenance-cron.sh where the rest of the pipeline cron scripts live, in PR coleam00#12 there. The old copy here also sourced a now-dead gt/mayor lib path, so removing it also clears a latent bug. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Rasmus Widing <rasmus.widing@gmail.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* chore(homebrew): update formula to v0.3.6 * feat: open PRs as ready by default + pr-maintenance draft promotion (#1) * Fix pr-maintenance cron: prepend user bins to PATH When cron invoked the script every 15 min, PATH was the minimal /usr/bin:/bin. archon (installed at ~/.bun/bin/archon) was not findable, so every "launching archon" step died with: /mnt/ext-fast/archon/scripts/pr-maintenance-cron.sh: line 59: archon: command not found As a result PRs that needed conflict resolution stopped being processed — they just accumulated as DIRTY or UNKNOWN. Prepend $HOME/.bun/bin, $HOME/.local/bin, and /usr/local/bin to PATH at the top of the script. Works from cron and from an interactive shell unchanged. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat: open PRs as ready by default + pr-maintenance draft promotion Archon workflows previously created PRs with --draft, which meant even a CI-green PR would sit idle until a human marked it ready. Combined with the Phase 1 merge filter in pr-maintenance-cron.sh (which skips drafts), a green draft could linger indefinitely. This change removes --draft from all three unconditional gh pr create invocations so PRs open ready-for-review by default: - .archon/workflows/defaults/archon-fix-github-issue.yaml - .archon/workflows/defaults/archon-piv-loop.yaml - .archon/workflows/defaults/archon-ralph-dag.yaml Also includes the already-in-tree pr-maintenance-cron.sh additions that complement this: - Phase 0: promote any CLEAN draft PRs to ready (belt-and-suspenders for PRs that still open as drafts from other sources). - Surface gh pr merge stderr to the cron log so real failures (perms, branch protection, etc.) are diagnosable instead of silently swallowed. Together these eliminate "green draft sitting idle" as a failure mode. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * workflows: downshift routine nodes to haiku, keep opus for heavy reasoning (#3) Applied a systematic model audit to the 15 default workflows. Moved routine nodes (create-pr, fix-failures, loop counters, status reports) from Sonnet/Opus to Haiku 4.5. Kept Opus for: - The 5 security-audit analysis agents (injection, auth, privacy, config-deps, logic) + synthesize - archon-adversarial-dev's core GAN loop - All `implement` / `implement-tasks` nodes in feature-dev, idea-to-pr, plan-to-pr, ralph-dag, fix-github-issue Upgraded archon-adversarial-dev's `plan` to Opus (spec-writing from scratch in an adversarial context needs depth Sonnet doesn't provide). Expected impact: ~35-40% cost reduction on the routine nodes that dominate cron-driven archon runs, without sacrificing quality on the heavy-reasoning paths. * workflows: add custom workflows + auto-merge phases Adds three custom archon workflows that were living untracked in the working tree (pr-maintenance, security-audit, test-audit). Applies the same haiku/sonnet downshifts from #3 to their routine nodes (create-pr, fix-failures, fix-security, coverage-gap-agent, flaky-test-agent). Also commits the Phase 11 prepare-merge + Phase 12 watch-and-merge auto-merge additions to archon-fix-github-issue.yaml (watch-and-merge uses haiku — polling loop, not reasoning) and the Phase 9 auto-merge step in archon-idea-to-pr.yaml. Gitignores *.jks — keystore files must never be committed. * deps: add @openai/codex-sdk For using Codex as a provider in archon workflows alongside Claude. Also bumps internal workspace versions 0.3.5 → 0.3.6 (bun regenerated on install). --------- Co-authored-by: Rasmus Widing <rasmus.widing@gmail.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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
2 participants
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.
Reconciles the fork so
mainbecomes the single canonical branch.Brings onto main:
Doesn't touch any upstream remote. After this lands, the fork's default branch will be switched from
devtomain.