Questions tagged agents
The plan/generate/heal/upgrade/review roles and the proposals they write.
15 questions
Audit wants proof the agents cannot write to our repo — what do I actually show them?
Internal audit has heard the words "AI writes our tests" and wants a control, not a paragraph. Saying that agents only write proposals is exactly the kind of claim they will ask…
asked by Zeynep Arslan64 ·Local model loops on agent generate, calling the same tool until it hits max turns
It calls feature_list, reads the result, calls feature_list again with the same arguments, and keeps going until the turn budget stops it. No proposal. It is not confused about…
asked by Paulo Mendes97 ·sdods doctor lists six credential rows for agents — which one do I actually need?
New to this. sdods doctor gives me a tidy screen and then a token section that lists what looks like six different ways to pay for the same thing. ANTHROPIC_API_KEY, a claude CLI…
asked by Paulo Mendes97 ·proposals accept --branch fails with Could not switch to branch and no reason why
That is the whole message. Nothing applied, which I am glad about, but git's own reason is nowhere — not on stdout, not with --json. Am I supposed to guess?
asked by Devon Marsh183 ·sdods agent heal ends with Agent job ... failed: unknown and I cannot find a log
Nothing under proposals/. sdods agent jobs lists the job with the same empty error. Adding --events prints the turns up to about turn eleven and then just stops, mid tool call,…
asked by Devon Marsh183 ·My mcp.servers block is ignored when the agent runs with the openai adapter
Project yaml has the usual: With --adapter claude the planner browses the app and the plan is full of real page names. With --adapter openai against our internal endpoint, the…
asked by Thom Vasseur5,470 ·Same locator healed five times and I still have no page-object proposal
The docs say three identical successful heals of the same locator produce a page-object patch proposal. Ours has healed five times across four nightly runs, same description,…
asked by Koen Vermeulen309 ·The reference says 37 tools, the MCP guide says 33 to 35 — which number is right?
Writing an internal page about what our agents can reach and I cannot make the docs agree with themselves. The MCP tools reference is titled as the 37 tools. The MCP guide says…
asked by Koen Vermeulen309 ·Local model writes out the tool call as text instead of actually calling it
Running the generator on my own machine because the source cannot leave it: It does not call anything. It writes a paragraph about what it is going to do, then a line that looks…
asked by Tanvi Bhatt126 ·What does sdods record convert actually write, and where do I review it before it lands?
I have four recordings under projects/demo-shop/recorded/ and I have been told to convert them rather than hand-write the features. Before I point it at anything that matters:…
asked by Sergio Alcaraz415 ·Accepting a proposal I rejected yesterday fails with Proposal ... was rejected
Rejected this one in a hurry, then realised two of the three files were fine. The directory is still there with all the files in it. Is there an un-reject, or do I re-run the…
asked by Sergio Alcaraz415 ·The healer proposed a CSS locator when there is a perfectly good label — reject it?
Scenario broke, ran the healer, got a proposal. The patch swaps a page-object locator for a class chain: The input has a visible label reading "Promo code". So there is an…
asked by Anouk de Vries238 ·Does sdods agent generate --dry-run call the model at all?
Before I point this at a paid key I would like to see what it is going to send. Does --dry-run do a cheap call, or no call?
asked by Bruno Teixeira694 ·What should I actually look at in a proposal before running sdods proposals accept?
First week of using the generator role. sdods proposals show <id> gives me a diff and a manifest and I am reading it the way I read any PR, which I suspect is the wrong instinct…
asked by Bea Lindqvist4,318 ·Can an SDODS agent commit the feature it wrote, or does a person always have to accept?
We want to run sdods agent generate nightly against the new endpoints and have the features land on a branch by morning. Right now every run leaves something in proposals/ that…
asked by Chandra Pillai873 ·