CB-617: pass auto-compact window to leads
This commit is contained in:
Dai Ha
@@ -209,13 +209,13 @@ herdrSocket: ~/.config/herdr/herdr.sock
|
||||
# e.g. `env DISPLAY=:10.0 idea {dir}`. Best-effort: a failure is logged, never
|
||||
# fails the spawn. Omit to open the member's module by hand. There is no close
|
||||
# half yet — an opened module stays open until the operator closes it.
|
||||
# autoCompactWindow → opt-in, default off. A bounded token window that forces a spawned member to
|
||||
# compact its context instead of running on the backend's own default and dying
|
||||
# mid-turn (losing its fleet_reply — the whole point of the turn — with it).
|
||||
# autoCompactWindow → opt-in, default off. A bounded token window that forces a launched Claude Code
|
||||
# lead or member to compact its context instead of running on the backend's own
|
||||
# default. A member that runs out of context can die mid-turn and lose its fleet_reply.
|
||||
# Validated at config load to [100000, 1000000] — the band Claude Code's own
|
||||
# --autocompact flag accepts.
|
||||
# CROSS-BACKEND SEMANTICS DIFFER: on claude-code this is a launch-time
|
||||
# `--autocompact <tokens>` flag — the member compacts AT this window. opencode
|
||||
# `--autocompact <tokens>` flag — the Claude Code session compacts AT this window. opencode
|
||||
# has no equivalent flag (it only forces `compaction.auto: true`, unconditionally,
|
||||
# already), so this is instead applied as the model's `limit.context` in the
|
||||
# generated opencode.json — the member compacts WITHIN this window, not exactly
|
||||
@@ -415,7 +415,7 @@ profiles:
|
||||
# ideMcpUrl: http://127.0.0.1:29170/index-mcp/streamable-http # opt-in (CB-634): IDE code intelligence, pinned to the worktree
|
||||
# ideProjectDir: fleetd # CB-634: module dir the IDE opens + the overlay pins (this repo's pom is in fleetd/)
|
||||
# ideOpenCommand: env DISPLAY=:10.0 idea {dir} # CB-634 auto-open: opens {dir} in the IDE at spawn; omit to open by hand
|
||||
# autoCompactWindow: 250000 # opt-in: bound member context; claude-code compacts AT this, opencode within it (model limit.context)
|
||||
# autoCompactWindow: 250000 # opt-in: bound Claude Code lead/member context; claude-code compacts AT this, opencode within it (model limit.context)
|
||||
gx11: # a second backend, so `placement: weighted` has a choice
|
||||
baseUrl: http://gx01.gw:8000 # self-hosted; ccs handles the model + token
|
||||
placement: tab
|
||||
|
||||
@@ -462,8 +462,8 @@ public record FleetConfig(
|
||||
* profile that does not opt in. Read live off the current config, so it is
|
||||
* HOT: a change takes effect on the next exhaustion classification / spawn,
|
||||
* no restart needed.
|
||||
* @param autoCompactWindow opt-in per-profile token window that forces a spawned member to
|
||||
* auto-compact its context at (Claude Code) or within (opencode) a bound the
|
||||
* @param autoCompactWindow opt-in per-profile token window that forces a launched Claude Code
|
||||
* session to auto-compact its context at, or an opencode session within, a bound the
|
||||
* operator chooses, instead of the backend's own default. {@code null} (the
|
||||
* default) leaves today's behaviour exactly — opencode already forces
|
||||
* {@code compaction.auto: true} unconditionally (CB-523) but has no absolute
|
||||
@@ -1875,6 +1875,7 @@ public record FleetConfig(
|
||||
rejectDuplicateMemberSlots(yaml);
|
||||
rejectNegativeMaxLoad(yaml);
|
||||
rejectAutoCompactWindowOutOfRange(yaml);
|
||||
rejectConflictingAutoCompactWindows(yaml);
|
||||
rejectMalformedProfilePatterns(yaml);
|
||||
rejectUnknownKind(yaml);
|
||||
rejectUnknownAuthMode(yaml);
|
||||
@@ -2225,6 +2226,46 @@ public record FleetConfig(
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Reject a Claude Code profile when its auto-compaction flag and environment setting disagree.
|
||||
*
|
||||
* <p>Claude Code gives {@code CLAUDE_CODE_AUTO_COMPACT_WINDOW} priority over
|
||||
* {@code --autocompact}. A disagreement would therefore make the configured flag misleading.
|
||||
* Equal values remain valid because either input produces the same session window.
|
||||
*/
|
||||
static void rejectConflictingAutoCompactWindows(String yaml) {
|
||||
Map<?, ?> raw;
|
||||
try {
|
||||
raw = YAML.readValue(yaml, Map.class);
|
||||
} catch (IOException | IllegalArgumentException e) {
|
||||
return;
|
||||
}
|
||||
if (raw == null || !(raw.get("profiles") instanceof Map<?, ?> profiles)) {
|
||||
return;
|
||||
}
|
||||
List<String> bad = new ArrayList<>();
|
||||
for (Map.Entry<?, ?> entry : profiles.entrySet()) {
|
||||
if (!(entry.getValue() instanceof Map<?, ?> profile)
|
||||
|| !(profile.get("autoCompactWindow") instanceof Number window)
|
||||
|| !(profile.get("env") instanceof Map<?, ?> env)
|
||||
|| !env.containsKey("CLAUDE_CODE_AUTO_COMPACT_WINDOW")) {
|
||||
continue;
|
||||
}
|
||||
Object kind = profile.get("kind");
|
||||
boolean claudeCode = kind == null || String.valueOf(kind).isBlank()
|
||||
|| Profile.KIND_CLAUDE_CODE.equalsIgnoreCase(String.valueOf(kind));
|
||||
if (claudeCode && !String.valueOf(window).equals(String.valueOf(env.get("CLAUDE_CODE_AUTO_COMPACT_WINDOW")))) {
|
||||
bad.add(String.valueOf(entry.getKey()));
|
||||
}
|
||||
}
|
||||
bad.sort(String::compareTo);
|
||||
if (!bad.isEmpty()) {
|
||||
throw new IllegalStateException("refusing to start: Claude Code profile(s) ["
|
||||
+ String.join(", ", bad) + "] set disagreeing autoCompactWindow and env."
|
||||
+ "CLAUDE_CODE_AUTO_COMPACT_WINDOW; remove one key or set equal values.");
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Reject a profile whose {@code errorPattern} (fleetd #201 Unit 5) or {@code exhaustedPattern}
|
||||
* (CB-578 stage A) is not a valid Java regex, naming the profile, the key, and the parser's own
|
||||
|
||||
@@ -0,0 +1,31 @@
|
||||
package dev.ltms.fleet.launch;
|
||||
|
||||
import dev.ltms.fleet.config.FleetConfig;
|
||||
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
|
||||
/** Arguments shared by every fleetd path that starts Claude Code. */
|
||||
public final class ClaudeCodeArguments {
|
||||
|
||||
private ClaudeCodeArguments() {
|
||||
}
|
||||
|
||||
/**
|
||||
* Append the configured Claude Code auto-compaction window when the profile opts in.
|
||||
*
|
||||
* <p>The environment variable {@code CLAUDE_CODE_AUTO_COMPACT_WINDOW} takes precedence over
|
||||
* this flag and saved settings. {@link FleetConfig#load(java.nio.file.Path)} rejects a Claude
|
||||
* profile when this flag's value disagrees with that environment entry, so a launched session
|
||||
* cannot silently use a different window.
|
||||
*/
|
||||
public static List<String> withAutoCompactWindow(List<String> argv, FleetConfig.Profile profile) {
|
||||
if (profile.autoCompactWindow() == null) {
|
||||
return argv;
|
||||
}
|
||||
List<String> withAutoCompact = new ArrayList<>(argv);
|
||||
withAutoCompact.add("--autocompact");
|
||||
withAutoCompact.add(String.valueOf(profile.autoCompactWindow()));
|
||||
return withAutoCompact;
|
||||
}
|
||||
}
|
||||
@@ -8,6 +8,7 @@ import dev.ltms.fleet.herdr.PendingCloseMarker;
|
||||
import dev.ltms.fleet.herdr.Tab;
|
||||
import dev.ltms.fleet.herdr.Workspace;
|
||||
import dev.ltms.fleet.herdr.WorkspaceControl;
|
||||
import dev.ltms.fleet.launch.ClaudeCodeArguments;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
@@ -358,7 +359,8 @@ public final class LeadLauncher {
|
||||
}
|
||||
|
||||
/**
|
||||
* The lead's argv: the profile's own command, the model pin, and the bridge MCP mount.
|
||||
* The lead's argv: the profile's own command, the model and auto-compaction pins, and the bridge
|
||||
* MCP mount.
|
||||
*
|
||||
* <p>No {@code --append-system-prompt}. That flag carries the worker reply charter, and a lead
|
||||
* is not a worker — it reads its orchestration rules from the project's {@code CLAUDE.md} like
|
||||
@@ -380,7 +382,7 @@ public final class LeadLauncher {
|
||||
argv.add("--model");
|
||||
argv.add(profile.model());
|
||||
}
|
||||
return argv;
|
||||
return profile.isOpenCode() ? argv : ClaudeCodeArguments.withAutoCompactWindow(argv, profile);
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@@ -8,6 +8,7 @@ import dev.ltms.fleet.guard.SubscriptionGuard;
|
||||
import dev.ltms.fleet.herdr.Agent;
|
||||
import dev.ltms.fleet.herdr.AgentControl;
|
||||
import dev.ltms.fleet.herdr.WorkspaceControl;
|
||||
import dev.ltms.fleet.launch.ClaudeCodeArguments;
|
||||
import dev.ltms.fleet.peer.Capability;
|
||||
import dev.ltms.fleet.peer.PeerLauncher;
|
||||
import org.slf4j.Logger;
|
||||
@@ -298,7 +299,7 @@ public final class ClaudeCodeLauncher extends HerdrPeerLauncher {
|
||||
// has neither MCP nor a charter — session flags must be added into a list we own.
|
||||
List<String> argv = mutableArgv(argvWithFleet(cfg, spec));
|
||||
String agentSessionId = applySessionIdentity(argv, spec.sessionName(), spec.resumeSessionId());
|
||||
return new Launch(workerEnv, argvWithAutoCompact(argvWithModel(argv, cfg), cfg), agentSessionId);
|
||||
return new Launch(workerEnv, ClaudeCodeArguments.withAutoCompactWindow(argvWithModel(argv, cfg), cfg), agentSessionId);
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -908,30 +909,6 @@ public final class ClaudeCodeLauncher extends HerdrPeerLauncher {
|
||||
return withModel;
|
||||
}
|
||||
|
||||
/**
|
||||
* Pin a bounded auto-compaction window on the command line via {@code --autocompact <tokens>},
|
||||
* opt-in per profile (CB-634's sibling ticket: a member that runs out of context dies mid-turn
|
||||
* and its {@code fleet_reply} — the whole point of the turn — is lost with it; opencode already
|
||||
* forces {@code compaction.auto: true} unconditionally, CB-523, but Claude Code has no equivalent
|
||||
* and runs at the backend's own default window).
|
||||
*
|
||||
* <p>Mirrors {@link #argvWithModel}: appended after it, so it survives the {@code ccs <profile>}
|
||||
* wrapper the same way {@code --model} does, and outranks env/settings and the operator's own
|
||||
* {@code argv}. Verified: {@code claude 2.1.241 --help} lists {@code --autocompact <auto|tokens>}
|
||||
* (either the literal {@code auto}, or an integer 100k–1M) — {@link FleetConfig#load} rejects a
|
||||
* configured value outside that band before this ever runs, so the flag Claude Code receives here
|
||||
* is always in range.
|
||||
*/
|
||||
private static List<String> argvWithAutoCompact(List<String> argv, FleetConfig.Profile cfg) {
|
||||
if (cfg.autoCompactWindow() == null) {
|
||||
return argv;
|
||||
}
|
||||
List<String> withAutoCompact = mutableArgv(argv);
|
||||
withAutoCompact.add("--autocompact");
|
||||
withAutoCompact.add(String.valueOf(cfg.autoCompactWindow()));
|
||||
return withAutoCompact;
|
||||
}
|
||||
|
||||
// --- Agent-returning convenience spawns (used by callers/tests that want the herdr Agent) ---
|
||||
|
||||
/** Spawn a worker for the default profile in the resolved default cwd. */
|
||||
|
||||
@@ -93,6 +93,40 @@ class FleetConfigTest {
|
||||
"unset means off — today's behaviour, unchanged");
|
||||
}
|
||||
|
||||
@Test
|
||||
void aClaudeProfileWithConflictingAutoCompactFlagAndEnvironmentWindowIsRejected(@TempDir Path dir)
|
||||
throws Exception {
|
||||
Path f = dir.resolve("conflicting-auto-compact-window.yaml");
|
||||
Files.writeString(f, """
|
||||
profiles:
|
||||
claude-profile:
|
||||
autoCompactWindow: 250000
|
||||
env:
|
||||
CLAUDE_CODE_AUTO_COMPACT_WINDOW: "300000"
|
||||
""");
|
||||
|
||||
IllegalStateException e = assertThrows(IllegalStateException.class, () -> FleetConfig.load(f));
|
||||
|
||||
assertTrue(e.getMessage().contains("claude-profile"));
|
||||
assertTrue(e.getMessage().contains("autoCompactWindow"));
|
||||
assertTrue(e.getMessage().contains("CLAUDE_CODE_AUTO_COMPACT_WINDOW"));
|
||||
}
|
||||
|
||||
@Test
|
||||
void aClaudeProfileWithEqualAutoCompactFlagAndEnvironmentWindowLoads(@TempDir Path dir)
|
||||
throws Exception {
|
||||
Path f = dir.resolve("equal-auto-compact-window.yaml");
|
||||
Files.writeString(f, """
|
||||
profiles:
|
||||
claude-profile:
|
||||
autoCompactWindow: 250000
|
||||
env:
|
||||
CLAUDE_CODE_AUTO_COMPACT_WINDOW: "250000"
|
||||
""");
|
||||
|
||||
assertEquals(250_000, FleetConfig.load(f).profiles().get("claude-profile").autoCompactWindow());
|
||||
}
|
||||
|
||||
// ── fleetd #201 Unit 5: errorPattern ────────────────────────────────────────────────────────
|
||||
|
||||
@Test
|
||||
|
||||
@@ -32,13 +32,26 @@ class LeadLauncherTest {
|
||||
Map.of("CLAUDE_CODE_AUTO_COMPACT_WINDOW", "300000"), null, null, true, null);
|
||||
}
|
||||
|
||||
private static FleetConfig.Profile profileWithAutoCompactWindow(String kind) {
|
||||
return new FleetConfig.Profile(
|
||||
"opus", null, "claude-opus-5", null, "FLEETD_WORKER_TOKEN",
|
||||
List.of("ccs", "ltms"), "tab", "fleet", null,
|
||||
"http://127.0.0.1:8765/mcp", null, null,
|
||||
null, null, kind, Map.of(), null, null, true, null, null,
|
||||
null, null, null, 250_000);
|
||||
}
|
||||
|
||||
private static FleetConfig configWith(FleetConfig.Leader lead) {
|
||||
return configWith(lead, opusProfile());
|
||||
}
|
||||
|
||||
private static FleetConfig configWith(FleetConfig.Leader lead, FleetConfig.Profile profile) {
|
||||
Map<String, FleetConfig.Leader> leaders = new LinkedHashMap<>();
|
||||
leaders.put("opus", lead);
|
||||
FleetConfig.Fleet fleet =
|
||||
new FleetConfig.Fleet(leaders, Map.of(), Map.of(), Map.of(), null);
|
||||
return new FleetConfig(
|
||||
null, null, Map.of("opus", opusProfile()), null, null, null, null, null,
|
||||
null, null, Map.of("opus", profile), null, null, null, null, null,
|
||||
null, null, fleet, null, "fixed", null).withDefaults();
|
||||
}
|
||||
|
||||
@@ -330,6 +343,36 @@ class LeadLauncherTest {
|
||||
"--model is appended last so it outranks the ccs wrapper (CB-533)");
|
||||
}
|
||||
|
||||
@Test
|
||||
void aClaudeLeadPassesItsConfiguredAutoCompactWindowToClaudeCode() {
|
||||
FakeHerdr herdr = new FakeHerdr();
|
||||
FleetConfig.Profile profile = profileWithAutoCompactWindow("claude-code");
|
||||
|
||||
launcher(herdr, configWith(lead("opus", "lead: opus", 1), profile)).ensureLeads();
|
||||
|
||||
List<String> args = startedArgs(herdr);
|
||||
assertEquals("250000", args.get(args.indexOf("--autocompact") + 1));
|
||||
}
|
||||
|
||||
@Test
|
||||
void aClaudeLeadWithNoAutoCompactWindowGetsNoAutoCompactFlag() {
|
||||
FakeHerdr herdr = new FakeHerdr();
|
||||
|
||||
launcher(herdr, configWith(lead("opus", "lead: opus", 1))).ensureLeads();
|
||||
|
||||
assertFalse(startedArgs(herdr).contains("--autocompact"));
|
||||
}
|
||||
|
||||
@Test
|
||||
void aNonClaudeLeadDoesNotGetAnAutoCompactFlag() {
|
||||
FakeHerdr herdr = new FakeHerdr();
|
||||
FleetConfig.Profile profile = profileWithAutoCompactWindow("opencode");
|
||||
|
||||
launcher(herdr, configWith(lead("opus", "lead: opus", 1), profile)).ensureLeads();
|
||||
|
||||
assertFalse(startedArgs(herdr).contains("--autocompact"));
|
||||
}
|
||||
|
||||
/** A lead runs on the operator's subscription. Nothing may move it off. */
|
||||
@Test
|
||||
void theLeadEnvCarriesNoAnthropicBinding() {
|
||||
|
||||
Reference in New Issue
Block a user