Store per-campaign startup parameters

[Copilot]

Each campaign now persists its startup configuration at the beginning of execution, written to harnesses/<harness>/campaigns/<campaign_id>/startup_params.json.

Stored parameters

• num_cpus — cores allocated to the campaign (from Docker machine)
• duration_secs — configured fuzz duration
• engines / sanitizers — project config (fuzzers and sanitizers enabled)
• commit_hash — commit hash of the target binary being fuzzed

Implementation

infra/types — new CampaignStartupParams struct (serde JSON-serializable)

fuzzor/src/env — EnvironmentParams gains commit_hash: String; Environment trait gains get_num_cpus()

Schedulers (RoundRobin, CoverageBased, OneShot) — store commit hash from CampaignSchedulerInput (populated from build.revision().commit_hash() in handle_new_build) and include it in each EnvironmentParams

Campaign — commit_hash and duration fields added; run() writes startup_params.json immediately after the environment starts

DockerEnv — implements get_num_cpus() as machine.cores.len()

Example output:

{
  "num_cpus": 8,
  "duration_secs": 57600,
  "engines": ["LibFuzzer", "AflPlusPlus"],
  "sanitizers": ["Address", "Undefined", "CmpLog"],
  "commit_hash": "a3f9c12d8e4b7061f5c2d9a8e3b1047f6d2c5a90"
}

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Store per-campaign startup parameters</issue_title>
<issue_description>For each campaign we should store (in addition to the coverage summary and stats we already store) the startup parameters, such as:

• Number of CPUs
• Duration
• Config (fuzzers, sanitizers, ...)
• Commit hash of the target binary</issue_description>

<agent_instructions>make no mistakes</agent_instructions>

Comments on the Issue (you are @copilot in this section)

• Fixes Store per-campaign startup parameters #85

---

💬 Send tasks to Copilot coding agent from Slack and Teams to turn conversations into code. Copilot posts an update in your thread when it's finished.