mirror of
https://github.com/Kilo-Org/kilocode.git
synced 2026-11-01 04:38:31 +08:00
* fix(ci): pass --auto to the docs-sync kilo runs and keep full stderr logs Headless kilo run auto-rejects every permission ask it receives, and the GitHub runner has no user config granting bash — so without --auto the docs-sync bot's triage, edit and verify-fix calls were silently crippled whenever the agent reached for a non-allowlisted shell command (CI run 30306629290: 9 rejections, all 11 edit batches failed, exit 0). - Pass --auto immediately after "run" at all three call sites (triage.mjs, edit.mjs, docs-sync.yml Fix verify failures step) - runKilo now always writes the child's full stderr to docs-sync-out/kilo-stderr-<label>.log, on success as well as failure — the blindness that hid the defect - selftest asserts --auto non-vacuously (region-scoped source match + a stub invocation that records argv) and proves the stderr log is written on both the failure and the summary-writing success path * fix(cli): exit nonzero when a headless run auto-rejects or its session errors Non-interactive kilo run reported success for runs that accomplished nothing — a caller cannot distinguish success from a dead run, which is why the docs-sync bot had to stop trusting exit codes entirely. - Plain headless run (neither --auto nor --dangerously-skip-permissions) in which the CLI auto-rejected at least one permission ask now exits non-zero, even when the session still reaches idle afterwards, with the diagnostic: run ended with an auto-rejected permission; pass --auto for autonomous use. Deliberate contract change: any auto-rejected ask means the run was crippled, not successful. - A mid-stream session error now writes its diagnostic to stderr before emitting the json error event, so the cause is visible under --format json as well (the emit-first shape skipped the stderr write). - The old exit-0 contract lock-in test is replaced: its llm.fail fixture never published a consumable session.error, so it locked in a false premise. New tests cover both scenarios in both output formats; happy-path and --format json runs still exit 0 unchanged. * fix(ci): redact secret env values from persisted kilo stderr logs The full-stderr capture added for observability lands in uploaded CI artifacts, which are raw files (GitHub masks secrets in log streams only) on a public repo, and the runner env holds a long-lived KILO_API_KEY. Redact exact values of KEY|TOKEN|SECRET-named env vars (len >= 8) once at capture, so both the console tail and the artifact file are safe. Adds the changeset for the headless exit-code contract change. * fix(ci): redact secrets from persisted kilo stdout and harden redaction The docs-sync workflow uploads docs-sync-out/ as a public 14-day artifact, and kilo stdout was persisted raw there in two more places: triage-raw-*.txt and the edit-log.txt tee. Redact at capture in runKilo for stdout as already done for stderr, and pipe the verify-fix step's kilo stdout through a new line-wise redact-stream.mjs filter before tee. Also harden redactEnvSecrets: widen the name pattern to KEY|TOKEN|SECRET|CREDENTIAL|PASSWORD|ORG_ID|_PAT (KILO_ORG_ID is a repo secret), replace longer values first so a short secret that prefixes a longer one cannot leak the remainder, and document the exact-substring limitation. Selftest gains cases 2e (prefix ordering), 2f (stdout capture), 2g (stream filter) and a non-vacuous exact-line assertion in 2d. * fix(cli): correct the headless-exit changeset's json-format claim The auto-reject path adds a new error event to the --format json stream; only the existing event shapes are unchanged. Also state that the exit-1 rule covers a plain non-interactive --attach run that auto-rejects an ask. * fix(ci): document --auto security trade-off and deferred hardening Update comments in triage.mjs and edit.mjs to accurately describe the security implications of --auto (unrestricted bash for an agent steered by external PR content) and note that a scoped permission.bash map via KILO_CONFIG_CONTENT is the intended hardening, deferred until required shell patterns are stable. * fix(ci): raise docs-sync budgets so the backlog can actually drain --auto fixes the batches the bot attempted; it does not fix the ones it never started. In run 30306629290 (254 PRs collected, 51 docs-worthy), the wall-clock budgets deferred 54 PRs untriaged and 31 unedited without an attempt — 45 of the 60 pending rows on the rolling PR. Triage got 8 of 11 chunks in 35 min; edit got 4 of 11 batches in 50 min. Both are ceilings, not costs. A caught-up run needs ~2 chunks and ~1 batch and finishes in ~25 min, so raising them spends nothing on a normal day and drains the backlog on a bad one. 90/120 covers 20 chunks and 14 batches — 500 triaged and 70 edited PRs against a ~5 docs-worthy/day inflow — inside a 240-minute job timeout. Also strip ANSI CSI sequences in tailText, the shared path both triage and edit route their pending causes through. kilo renders its TUI to stderr, so every "Why" cell on the rolling PR currently reads "^[[0m→ ^[[0mRead packages/..." instead of the diagnostic. The persisted docs-sync-out/kilo-stderr-*.log stays raw as the debugging record. selftest case 2h asserts the pending reason is escape-free and still carries the diagnostic text; case 2i asserts each budget fits at least two units and the job timeout outlasts both, so a future edit cannot silently restore a budget too small to run anything. Both shown failing on the unmodified code first. * fix(ci): keep the docs-sync rebuild authoritative in the fix step The "Fix verify failures" step runs under `set -o pipefail` and the default `bash -e`. Once the CLI half of this PR ships, `kilo run` exits 1 on a mid-stream session error, which aborts the block before the rebuild runs: verify2.log is never written and `Re-verify status` reports VERIFIED=false even when the docs build fine. A transient provider error would flip every rolling docs PR to "Verification: failing". The agent's exit code was never the signal for this step — the rebuild is. Guard the pipeline with `|| echo ::warning::` so a nonzero kilo run is surfaced but the rebuild still decides the outcome. Extends selftest case 2b (which already parses this step) rather than adding a case: the guard must appear between the pipeline's tee and the rebuild, so a comment elsewhere in the block cannot satisfy it. Shown failing with the guard removed. --------- Co-authored-by: kiloconnect[bot] <240665456+kiloconnect[bot]@users.noreply.github.com>
167 lines
7.0 KiB
TypeScript
167 lines
7.0 KiB
TypeScript
// Subprocess integration tests for `opencode run` (non-interactive mode).
|
|
// These exercise the real CLI binary against a TestLLMServer running in the
|
|
// same process. See `test/lib/cli-process.ts` for the harness — each test uses
|
|
// `opencode.run(message, opts?)` to spawn `bun src/index.ts run ...` with
|
|
// `KILO_CONFIG_CONTENT` providing the test provider config inline.
|
|
import { describe, expect } from "bun:test"
|
|
import { Effect } from "effect"
|
|
import { cliIt } from "../../lib/cli-process"
|
|
|
|
describe("opencode run (non-interactive subprocess)", () => {
|
|
// kilocode_change start
|
|
// Keep full CLI subprocesses serial within this file; the test runner already
|
|
// executes files in parallel, and nested concurrency exhausts Windows CI.
|
|
// Happy path: prompt completes, output reaches stdout, process exits 0.
|
|
// If this fails, all the others likely will too — debug here first.
|
|
cliIt.live(
|
|
"exits 0 and writes the response to stdout on a successful prompt",
|
|
({ llm, opencode }) =>
|
|
Effect.gen(function* () {
|
|
yield* llm.text("hello from the test llm")
|
|
const result = yield* opencode.run("say hi")
|
|
opencode.expectExit(result, 0)
|
|
expect(result.stdout).toContain("hello from the test llm")
|
|
}),
|
|
60_000,
|
|
)
|
|
// kilocode_change end
|
|
|
|
// kilocode_change start
|
|
// Regression for #27371: an unknown model used to hang the process forever
|
|
// waiting on a session.status === idle event that never arrived. The fix
|
|
// makes the SDK call surface an error promptly so the process exits 1.
|
|
// A harness timeout produces synthetic exit code -1, so the exact assertion
|
|
// distinguishes the intended failure from a signal-killed process.
|
|
cliIt.live(
|
|
"exits nonzero promptly when the model is unknown (regression for #27371)",
|
|
({ opencode }) =>
|
|
Effect.gen(function* () {
|
|
const result = yield* opencode.run("say hi", {
|
|
model: "test/nonexistent-model",
|
|
timeoutMs: 30_000,
|
|
})
|
|
opencode.expectExit(result, 1)
|
|
}),
|
|
60_000,
|
|
)
|
|
// kilocode_change end
|
|
|
|
// kilocode_change start
|
|
// Was: "mid-stream LLM error still exits 0 today (contract lock-in)" using
|
|
// llm.fail(...). That fixture never published a session.error the CLI
|
|
// consumed (stream failure recovered as incomplete; idle with error unset),
|
|
// so the lock-in was locking in a false premise. Contract change: a run
|
|
// whose session actually errored mid-stream must exit non-zero with a
|
|
// stderr diagnostic naming the cause — callers (docs-sync) cannot otherwise
|
|
// distinguish success from a dead run and had to stop trusting exit codes.
|
|
cliIt.live(
|
|
"mid-stream session error exits nonzero with a stderr diagnostic",
|
|
({ llm, opencode }) =>
|
|
Effect.gen(function* () {
|
|
yield* llm.error(400, { error: { message: "upstream provider exploded mid-stream" } })
|
|
const result = yield* opencode.run("trigger midstream error", { timeoutMs: 30_000 })
|
|
opencode.expectExit(result, 1)
|
|
expect(result.stderr).toContain("upstream provider exploded mid-stream")
|
|
}),
|
|
60_000,
|
|
)
|
|
|
|
cliIt.live(
|
|
"mid-stream session error exits nonzero with stderr diagnostic under --format json",
|
|
({ llm, opencode }) =>
|
|
Effect.gen(function* () {
|
|
yield* llm.error(400, { error: { message: "upstream provider exploded mid-stream" } })
|
|
const result = yield* opencode.run("trigger midstream error", {
|
|
format: "json",
|
|
timeoutMs: 30_000,
|
|
})
|
|
opencode.expectExit(result, 1)
|
|
expect(result.stderr).toContain("upstream provider exploded mid-stream")
|
|
const events = opencode.parseJsonEvents(result.stdout)
|
|
expect(events.some((event) => event.type === "error")).toBe(true)
|
|
}),
|
|
60_000,
|
|
)
|
|
|
|
// Plain headless run (no --auto): CLI auto-rejects bash asks under the
|
|
// harness's isolated config. Any auto-reject ⇒ non-zero, even if idle.
|
|
cliIt.live(
|
|
"auto-rejected permission in plain headless run exits nonzero",
|
|
({ llm, opencode }) =>
|
|
Effect.gen(function* () {
|
|
yield* llm.tool("bash", { command: "sed -n 1,5p README.md" })
|
|
const result = yield* opencode.run("run sed on readme", { timeoutMs: 45_000 })
|
|
opencode.expectExit(result, 1)
|
|
expect(result.stderr).toContain("permission requested: bash")
|
|
expect(result.stderr).toContain("auto-rejecting")
|
|
expect(result.stderr).toContain(
|
|
"run ended with an auto-rejected permission; pass --auto for autonomous use",
|
|
)
|
|
}),
|
|
60_000,
|
|
)
|
|
|
|
cliIt.live(
|
|
"auto-rejected permission exits nonzero with stderr diagnostic under --format json",
|
|
({ llm, opencode }) =>
|
|
Effect.gen(function* () {
|
|
yield* llm.tool("bash", { command: "sed -n 1,5p README.md" })
|
|
const result = yield* opencode.run("run sed on readme", {
|
|
format: "json",
|
|
timeoutMs: 45_000,
|
|
})
|
|
opencode.expectExit(result, 1)
|
|
expect(result.stderr).toContain(
|
|
"run ended with an auto-rejected permission; pass --auto for autonomous use",
|
|
)
|
|
const events = opencode.parseJsonEvents(result.stdout)
|
|
expect(events.some((event) => event.type === "error")).toBe(true)
|
|
}),
|
|
60_000,
|
|
)
|
|
// kilocode_change end
|
|
|
|
// kilocode_change start
|
|
// --format json puts one JSON object per line on stdout for each emitted
|
|
// event. Consumers (CI scripts, tooling) parse this stream. Asserts the
|
|
// shape so a future event-emit change has to update this expectation.
|
|
cliIt.live(
|
|
"--format json emits parseable line-delimited JSON to stdout",
|
|
({ llm, opencode }) =>
|
|
Effect.gen(function* () {
|
|
yield* llm.text("structured output")
|
|
const result = yield* opencode.run("say hi", { format: "json", extraArgs: ["--auto"] })
|
|
opencode.expectExit(result, 0)
|
|
expect(result.stdout).not.toContain("auto-rejected permission")
|
|
|
|
const events = opencode.parseJsonEvents(result.stdout)
|
|
expect(events.length).toBeGreaterThan(0)
|
|
for (const evt of events) {
|
|
expect(typeof evt.type).toBe("string")
|
|
expect(typeof evt.sessionID).toBe("string")
|
|
}
|
|
expect(events.filter((event) => event.type === "step_start")).toHaveLength(1)
|
|
expect(events.filter((event) => event.type === "text")).toHaveLength(1)
|
|
expect(events.filter((event) => event.type === "step_finish")).toHaveLength(1)
|
|
}),
|
|
60_000,
|
|
)
|
|
|
|
cliIt.live(
|
|
"--format json emits each completed tool once",
|
|
({ llm, opencode }) =>
|
|
Effect.gen(function* () {
|
|
yield* llm.tool("glob", { pattern: "package.json" })
|
|
yield* llm.text("tool complete")
|
|
const result = yield* opencode.run("find package.json", { format: "json", extraArgs: ["--auto"] })
|
|
opencode.expectExit(result, 0)
|
|
|
|
const events = opencode.parseJsonEvents(result.stdout)
|
|
expect(events.filter((event) => event.type === "tool_use")).toHaveLength(1)
|
|
expect(events.filter((event) => event.type === "text")).toHaveLength(1)
|
|
}),
|
|
60_000,
|
|
)
|
|
// kilocode_change end
|
|
})
|