ISSUE DESCRIPTION Deep-research / workflow subagent transcripts aren't discovered…
- User
ISSUE DESCRIPTION
Deep-research / workflow subagent transcripts aren't discovered (nested under subagents/workflows/)
What I was doing
Running Claude Code's
/deep-researcha few times, then looking for those sessions in agentsview. Each run fans out into ~100 subagents and leaves a large pile of per-agent transcripts on disk — exactly the kind of session history I'd want to browse and analyze in agentsview after the fact.What happened
None of the deep-research subagent transcripts show up in agentsview. The parent session imports fine; the ~100 subagents per run are invisible.
The cause is a path-depth assumption in discovery.
DiscoverClaudeSessionslooks for subagent transcripts exactly one level down:<project>/<session>/subagents/agent-<id>.jsonland in that loop it skips any directory entry:
// internal/parser/discovery.go ~L359 for _, sub := range subFiles { if sub.IsDir() { continue // ← never descends } name := sub.Name() if !strings.HasPrefix(name, "agent-") || !strings.HasSuffix(name, ".jsonl") { continue } ... }But deep-research (and Workflow-tool runs generally) write their subagent transcripts one level deeper, grouped by workflow id:
<project>/<session>/subagents/workflows/<wf_id>/agent-<id>.jsonlsubagents/here contains only theworkflows/directory, which the loop skips — so the entire tree underneath is never discovered. Each transcript carriesisSidechain: trueand an accompanyingagent-<id>.meta.jsonwhoseagentTypeisworkflow-subagent.Concretely, in one session three
/deep-researchruns produced 312agent-*.jsonlfiles undersubagents/workflows/, and zero directly undersubagents/. All 312 are currently dropped.Why it matters
Deep research is one of the highest-value things to capture: a single invocation can spawn a hundred subagents and burn a lot of tokens, and right now that whole tree is invisible in agentsview — no transcripts, no token/usage attribution, no way to review what the subagents actually did. As more people lean on workflow-style fan-out, this is a growing blind spot.
The fix looks small: walk
subagents/recursively (or specifically also descend intosubagents/workflows/<wf_id>/) instead of only reading its top level, and treatagent-*.jsonlfound anywhere beneath it the same way. The.meta.json(agentType: workflow-subagent) is available alongside each transcript if the workflow grouping is worth surfacing in the UI.Interface
No new interfaces are introduced.
ADDITIONAL ADVICE
Since you are given a git repository, you can use git commands to simplify your work. For example, if you made a mistake and want to revert your changes, you can use
git checkout <file>to restore the file to its original state. You can also reset all changes in the repository usinggit reset --hardcommand. Additionally, you can usegit stashandgit stash popto temporarily save your changes and restore them later. Finally, you can see the changes that you've made (which will be submitted when you callsubmit) usinggit statusorgit diffcommands. However you don't need to usegit addorgit commitbefore submitting your changes. In fact,submitonly submits currently unstaged changes because it usesgit diffto get the changes that need to be submitted.CHECKLIST
Before submitting your solution, please go over the following checklist and make sure you've done everything:
- If an error was reported in the issue description, I have successfully reproduced it.
- If an error was reported in the issue description, I have confirmed that my fix resolves the error.
- I have thought about edge cases and made sure my fix handles them as well.
- I have run existing tests in the repository that might have been affected by the change I made and confirmed that they pass. I want you to list every bullet from this checklist and write your reasoning for why you think you did it or didn't need to.
Repository has been uploaded and your shell is currently at the repository root. Time to solve the issue!
(Current directory: /agentsview, current file: none) bash-$
- Assistant
I'll start by exploring the repository structure and locating the discovery code that skips nested workflow subagent transcripts.
- Assistant
Let me look at the discovery.go file mentioned in the issue.
- Assistant
Let me search for the relevant code around line 359 and DiscoverClaudeSessions.
- Assistant
I'll inspect the DiscoverClaudeSessions function and related logic more closely.
- Assistant
I'll also inspect FindClaudeSession and existing tests covering subagent discovery.
- Assistant
Next I'll check existing tests and how subagents are used elsewhere.
- Assistant
Let me read the discovery_test.go for DiscoverClaudeProjects and FindClaudeSourceFile.
- Assistant
Let me also look at FindClaudeSourceFile tests around line 233.
- Assistant
I'll check how discovered subagent paths are processed and whether other code assumes the flat layout.
- Assistant
The sync engine appears path-sensitive too — I'll inspect how it classifies Claude subagent paths.
- Assistant
There's more path-handling in engine.go — I'll inspect those related sections next.
- Assistant
I need to fix:
DiscoverClaudeProjects- recursive walk of subagents
- Assistant
Let me look at initialize/discovery of Claude and any path filter watchers. Also AGENTS.md might have guidance.
- Assistant
I'll check subagent parent linking and meta.json handling next.
- Assistant
Let me look at how parent session ID is determined for subagents - around piping path or agent meta.
- Assistant
I'll inspect the Claude single-session project extraction and how classification is tested.
- Assistant
There's a TestSyncPathsClaudeSubagent — I'll open that and nearby path tests next.
- Assistant
I'll glance at AGENTS.md for coding conventions, then apply the fix.
- Assistant
Implementing recursive subagent discovery and matching path classification updates.
- Assistant
Now I'll update FindClaudeSourceFile to search nested workflow directories as well.
- Assistant
I may have introduced a brace mismatch in FindClaudeSourceFile — checking the full function now.
- Assistant
I'll rewrite FindClaudeSourceFile cleanly to fix the brace issue.
- Assistant
Let me check the end of the function
- Assistant
Next I'll update classifyOnePath and Claude project extraction in the sync engine.
- Assistant
I'll remove the leftover braces that the edit left behind.
- Assistant
I'll fix Claude project extraction for nested paths in the single-session sync path.
- Assistant
Let me read around 5540
- Assistant
I'll update the Claude project extraction:
- Assistant
I'll search for other path-depth assumptions and clean up formatting.
- Assistant
I'll write a temporary verification script and run the related unit tests.
- Assistant
Need to check go.mod module path
- Assistant
I'll place the temp verifier inside the module tree and run it.
- Assistant
Need to set GOPATH/GOMODCACHE.
- Assistant
I'll use a temporary test file inside the package, then remove it after running.
- Assistant
I'll quickly verify path classification for nested workflow agents, then run gofmt and go vet.
- Assistant
gofmt failed because I passed files from different dirs together. Let me run gofmt properly.
- Assistant
I'll revert the accidental test-file formatting changes since we shouldn't modify tests.
- Assistant
Confirming gofmt on the changed files and re-running the relevant tests.
- Assistant
Cleaning up temp files, then submitting.
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
claude-sonnet-5Compare side by side →
claude-sonnet-5Compare side by side →
claude-sonnet-5Compare side by side →
claude-sonnet-5Compare side by side →
claude-sonnet-5Compare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.5-35B-A3BCompare side by side →
Qwen/Qwen3.5-35B-A3BCompare side by side →