@engineeros/connector 1.59.4 → 1.59.5

package/README.md

@@ -348,7 +348,7 @@ ENGINEEROS_AGENT_MODELS="model-a,model-b" npx @engineeros/connector start --work
 
 ### One model per session, stepping up after failures, and the image probe
 
-Writing tests and repairing them, and hunting and fixing case files, run on **one model per session**: a repair or a correction resumes the session that wrote, on the same model, so the prompt cache is not thrown away. When repairs do not work (two failed repairs of Automate tests, or case files that still cannot run after the correction turn), one more attempt runs as the `escalated` class: one effort step above the choice it follows (or the choice EngineerOS sent for it), in a **fresh session** that is given the whole task and what went wrong. Its tokens are reported as their own part (`task: "escalated"`).
+Writing tests and repairing them, and hunting and fixing case files, run on **one model per session**: a repair or a correction resumes the session that wrote, on the same model, so the prompt cache is not thrown away. When two repairs of Automate tests do not work, one more attempt runs as the `escalated` class: one effort step above the choice it follows (or the choice EngineerOS sent for it), in a **fresh session** that is given the whole task and what went wrong. Its tokens are reported as their own part (`task: "escalated"`).
 
 Reading production signals (`monitoring`) runs on the engine default unless EngineerOS chose, never on the reviewer's model.
 
@@ -552,13 +552,13 @@ npx --yes @engineeros/connector@latest tools setup playwright --workspace .
 On Linux, missing Chromium system libraries require administrator access. At a terminal, setup asks for your password; otherwise it prints the exact installation command to run. Download or launch failures are reported and can be retried with the command above. Installing the npm connector package alone does not download a browser; the connected workspace setup does.
 
 - **Catalogue runs** execute the recorded cases. A failure is run twice more from a fresh start: failing all three times it is reproduced, otherwise flaky.
-- **Hunts** run one agent turn in `.engineeros/bug-hunt/<session>/`. The agent writes each scenario as a case file in `cases/` and probes a draft with `node .engineeros/bug-hunt/<session>/probe.mjs <case file>`, which runs it through the same runner. Case files that cannot be read get one correction turn. The connector registers the cases with EngineerOS, which refuses duplicates, then runs each one.
-- **Review**: newly reproduced failures go to one reviewer turn in a fresh session. Its verdicts decide what becomes a bug.
+- **Hunts** keep cases and probe evidence under `.engineeros/bug-hunt/<session>/`. A first whole-application web hunt maps and tests progressively: verified screens are grouped in batches of up to four (or flushed after five seconds), described with evidence-backed test paths, and assigned to separate agents under `areas/area-N/`. One worker remains with the crawler; the others describe, explore, prove and review each area within their slot. With one worker, exploration follows traversal. Focused hunts and environments that reset between checks retain their existing order. Each area has 90 seconds to explore and stops after three probes hit the same access or locator blocker without new page evidence. The hunt time box includes discovery and authoring; written cases still finish proof and review. All agents share one case-format correction, and the failed originals remain in `case-attempts/`.
+- **Review**: newly reproduced failures go to an independent reviewer in a fresh session. Whole-application hunts publish reviewed results area by area while discovery continues. Each failure still needs three fresh runs and review; each case is reviewed once.
 - **What pages do on their own**: every run listens, without sending anything, for console and page errors, failed and 5xx or 404 requests, loading that never finishes, broken images and links and mixed content, scans each page once for serious accessibility violations (axe-core) and samples Web Vitals. A signal never changes a case's result. A cause that shows again on a clean re-run is sent to EngineerOS, which files it as a bug; nothing but text (messages, URLs without query values, selectors, numbers) leaves the machine. A production check only listens.
-- **Routes and API calls**: a map also reads `robots.txt`, `sitemap.xml`, the application's own bundles and public source maps (and, in a checkout, its source) for routes, then presses navigation buttons and tabs with every write aborted. It records the application's own XHR and fetch calls as a map of endpoints, reduced to their shape; no response value is kept.
+- **Routes and API calls**: a map reads HTML links, inline route declarations, `robots.txt`, `sitemap.xml`, the application's own bundles and public source maps (and, in a checkout, its source). Static network discovery has a 30-second budget, with at most four bundle requests concurrently and 24 scripts per pass. Candidates alternate with browser links for verification; routes that redirect to login remain access blockers and the gateway is counted once per role. The map then presses navigation buttons and tabs with every write aborted, moving on after three controls reveal no new named content or route. Possible journeys are hypotheses, not product requirements; raw model descriptions stay under `map/`. It records the application's own XHR and fetch calls as a map of endpoints, reduced to their shape; no response value is kept.
 - **Rules of engagement** are enforced by the runner. Only the environment's hosts and the allowed hosts may be opened or written to. A step that a forbidden-action rule names (a quoted element name or a path) is refused.
 - **Stopping**: EngineerOS can stop a session at any time. Stop ends the agent's turn and still runs and reviews what it wrote; stop without review skips the review; abort ends everything at once.
-- **One at a time**: a hunt starts only while the coding agent is idle, and one session runs on a connector at a time. The session folder is removed when it ends.
+- **One at a time**: a hunt starts only while the coding agent is idle, and one session runs on a connector at a time. The session folder stays on the host for review and recovery.
 - **Versions**: when the environment's version path is set (a path such as `/version`, or `header:X-App-Version`), the connector reads it at the start of each session and reports it. EngineerOS then compares each page with the previous version.
 - **Command line**: a case's `run` step runs a program without a shell, in this folder, with the environment's variables and any input the case gives. Only programs the hunter allows may run.
 - **Locale, time zone and network**: `set locale` and `set time zone` shape the browser sessions a case starts after them. `set network` makes the current session `offline`, `online` or `slow` (Chromium throttling).