fix: replace ct filter with opencode run --format json (direct-exec)#502
Closed
MichielDean wants to merge 6 commits into
Closed
fix: replace ct filter with opencode run --format json (direct-exec)#502MichielDean wants to merge 6 commits into
MichielDean wants to merge 6 commits into
Conversation
added 4 commits
May 9, 2026 22:27
The previous ct filter implementation used a direct-exec approach (opencode run --format json) which doesn't work because opencode run requires an existing session ID and doesn't produce output on stdout. The new implementation spawns opencode in a tmux session, mirroring how cataractae work: 1. Create temp workdir with CONTEXT.md + AGENTS.md + agent identity 2. Spawn opencode run in tmux with --dangerously-skip-permissions --agent filter 3. Use pipe-pane to capture PTY output to a log file 4. Wait for session exit (poll with 10min timeout) 5. Read log, strip ANSI, extract agent response 6. Clean up tmux session and temp files Key changes: - filter.go: Replaced callFilterAgent with filterAgentTmux/filterAgentResume - filter_agent.go: New file with tmux-based spawning logic - preset.go: Removed FormatArgs (was --format json, doesn't work with opencode) - dashboard_web.go: Updated filterResume to use invokeFilterNew - filter_test.go: Kept structural tests, callFilterAgent now returns error Also unset OPENCODE_SERVER_* env vars in tmux sessions to prevent 'session not found' errors (same fix as cataractae). Replaces the incomplete FormatArgs fix (PR #500) with a proper architectural solution.
…lter The PTY log approach for extracting agent responses was fundamentally broken — pipe-pane captures raw terminal output mixed with TUI chrome, and the heuristic extraction (cleanANSI + isTUICrome) consistently truncated responses or captured TUI artifacts. Solution: instruct the filter agent to write its response to RESPONSE.md in the workdir. After the tmux session exits, read the file directly. No ANSI stripping, no extraction heuristics, no truncated paragraphs. Changes: - filterAgentsMD() now instructs the agent to write RESPONSE.md - filterAgentTmux() reads RESPONSE.md instead of PTY log - filterAgentResume() uses tmux display-message to find workdir, then reads RESPONSE.md instead of polling PTY log for size changes - Removed cleanANSI(), extractFilterResponse(), isTUICrome() functions - Removed pipe-pane log setup and PTY parsing logic - Added tmuxSessionWorkdir() helper for --resume path - Added dropVec0Objects() to prevent 'no such module: vec0' errors - Updated fakeagent to write RESPONSE.md when --agent filter is present - Updated tests: removed deprecated callFilterAgent tests, updated FormatArgs test for empty (removed) format args, simplified integration tests
The root cause of all previous failures was OPENCODE_SERVER_* env vars causing 'Session not found' errors. Unsetting those vars allows opencode run to work correctly as a direct subprocess. opencode run --format json produces NDJSON output with: - type:'text' events containing the agent's response - sessionID for --resume support This is dramatically simpler and more reliable than the tmux approach: - No PTY log parsing, no ANSI stripping - No RESPONSE.md file redirect with timing issues - No tmux session management - Direct JSON parsing of stdout, just like the original design intended The tmux approach was a workaround for 'Session not found' errors that turned out to be caused by OPENCODE_SERVER_* vars leaking into the tmux session. Now that we know the root cause, the direct-exec approach works correctly. Changes: - filter_agent.go: complete rewrite from tmux to direct-exec - filterAgentRun() runs opencode as subprocess, parses NDJSON - filterAgentRunResume() uses -s flag for session continuation - buildFilterRunCommand() constructs args and env - Env vars OPENCODE_SERVER_*, OPENCODE_PID, OPENCODE are unset - --format json flag captures output programmatically - Removed tmux, pipe-pane, RESPONSE.md, cleanANSI, extractFilterResponse - Removed isSessionAlive, shellQuote, homeDir, minimalTmuxEnv - filter.go: updated invokeFilterNew/Resume to use new functions - callFilterAgent deprecated stub now references filterAgentRun - filter_test.go: updated for new architecture - Replaced tmux-based tests with direct-exec tests - Added unsetEnvPrefix, buildFilterRunCommand tests - Removed ResponseFileName test (no longer applicable) - fakeagent: added --agent filter detection for test mode
…attern - Remove stale --file flag reference (flag was removed) - Replace tmux wrapper pattern with direct ct droplet add --filter - Note that ct filter now uses opencode run --format json
MichielDean
changed the title
added 2 commits
May 10, 2026 21:59
The upgrade test used a stale config with workflow_path instead of aqueduct and no aqueducts section. Since the config validator requires both aqueducts and repo-level aqueduct refs, the castellarius service failed to start with this config. Updated the stale config to include valid current-schema fields (aqueducts + aqueduct refs) while keeping the stale unknown keys (old_binary_path, legacy_agent_timeout) that YAML parser should silently ignore. Also added trailing newlines to Go source files.
Owner
Author
MichielDean
added a commit
that referenced
this pull request
May 22, 2026
## Summary The installer upgrade test used a stale config with `workflow_path` (deprecated key) instead of `aqueduct` and was missing the `aqueducts:` section. Since the config validator requires both `aqueducts:` and repo-level `aqueduct:` refs, the castellarius service failed to start with this config. This fixes the **installer-tests** CI failure on PR #502 (and main). ## Changes - Updated the stale config in the upgrade test scenario to include valid current-schema fields (`aqueducts:` section + `aqueduct:` refs on repos) - Preserved the stale unknown keys (`old_binary_path`, `legacy_agent_timeout`) that the YAML parser silently ignores — this is the actual upgrade scenario being tested - Removed `workflow_path` (no longer a valid key) and replaced with `aqueduct: default` ## Testing - All unit tests pass locally - The installer-tests CI should now pass since the upgrade scenario uses a valid config Fixes the failing installer-tests check on #502. --------- Co-authored-by: Lobsterdog Contributors <noreply@lobsterdog.dev>
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
Replaces the broken
ct filterdirect-exec approach with a working implementation usingopencode run --format json.Root cause:
opencode runrequiresOPENCODE_SERVER_*env vars to be unset. When these vars are set (which they are in the running lobsterdog session), opencode connects to an existing server and fails with "Session not found." UnsettingOPENCODE_SERVER_USERNAME,OPENCODE_SERVER_PASSWORD,OPENCODE_PID, andOPENCODEallows opencode to start a fresh session.Solution:
opencode run --format json --dangerously-skip-permissionswith those env vars unset produces clean NDJSON output withtype:"text"events andsessionIDfor--resumesupport. No tmux, no PTY parsing, no file redirect — just a subprocess with stdout capture.Key changes:
filter_agent.go: Complete rewrite from tmux to direct-execfilterAgentRun()runs opencode as subprocess, parses NDJSON from stdoutfilterAgentRunResume()uses-sflag for session continuationbuildFilterRunCommand()constructs args and env, unsets OPENCODE_SERVER_*--format jsonflag captures output programmaticallyfilter.go: Updated invokeFilterNew/Resume to use new functionsfilter_test.go: Updated for new architecture, replaced tmux tests with direct-exec testsinternal/provider/preset_test.go: Updated FormatArgs test (opencode preset no longer has FormatArgs)internal/testutil/fakeagent: Added--agent filterdetection for test modeSKILL.md: Removed stale--fileflag reference, updated tmux wrapper to direct commandreferences/commands.md: Removed tmux wrapper patternTesting
unset OPENCODE_SERVER_* OPENCODE_PID OPENCODE && opencode run --format json --dangerously-skip-permissions --model ollama/glm-5.1:cloud 'Say OK'produces correct NDJSON output--resumewith session ID works correctlyct filterwith the new code produces correct JSON/text output