feat(v2): Ultra mode toggle — proactive delegation for every model/effort - #1209
Conversation
|
✅ Deterministic PR hygiene checks passed. |
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
📝 WalkthroughWalkthroughThe change adds Ultra Mode hint-text configuration across Codex persistence, the ChangesUltra Mode delegation settings
Estimated code review effort: 4 (Complex) | ~60 minutes Possibly related PRs
Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
✅ READY
Review readiness checklist
✅ 4/4 boxes ticked. This pull request is already Ready for Review. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@gui/src/components/subagents-workspace/SubagentDelegationSection.tsx`:
- Around line 127-145: Update SubagentDelegationSection’s Ultra Mode editor to
maintain a local draft of ultraMode.hintText instead of calling onUltraModeSave
from the textarea onChange. Add an explicit Save action or serialized debounced
commit using the draft, pass ultraSaving from Subagents.tsx, and disable the
textarea and preset/save controls while the commit is active; keep the draft
synchronized with management API responses after successful reloads.
In `@gui/src/pages/Subagents.tsx`:
- Around line 31-57: Consolidate the duplicated `/api/v2` fetch logic in
`loadUltraMode` and the mount `useEffect` into one shared loader. Ensure
initial-load failures set `status` to `t("sub.ultraModeLoadFail")`, while
refresh failures invoked by saving propagate to `saveUltraMode` instead of being
swallowed; preserve the existing state updates on successful loads.
In `@src/cli/v2.ts`:
- Around line 131-148: Update the mode-hint argument handling around the verb
=== "mode-hint" branch to preserve the raw supplied text for
setMultiAgentModeHintText. Treat only a missing argument as equivalent to
--clear, reject a present whitespace-only value, and retain leading/trailing
whitespace in nonblank hints so CLI behavior matches the API contract.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: ec5671af-c0fb-4a89-842c-42e92cdabde3
📒 Files selected for processing (14)
gui/src/components/subagents-workspace/SubagentDelegationSection.tsxgui/src/components/subagents-workspace/SubagentsWorkspace.tsxgui/src/i18n/de.tsgui/src/i18n/en.tsgui/src/i18n/ja.tsgui/src/i18n/ko.tsgui/src/i18n/ru.tsgui/src/i18n/zh.tsgui/src/pages/Subagents.tsxgui/src/pages/use-subagent-delegation.tssrc/cli/v2.tssrc/codex/features.tssrc/server/management/agent-settings-routes.tstests/codex-v2-gate.test.ts
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a914681d3d
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
src/codex/features.ts (1)
650-667: 🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick winHandle quoted keys before editing a dedicated table.
A config can contain
"multi_agent_mode_hint_text" = "old value"or'multi_agent_mode_hint_text' = "old value"in[features.multi_agent_v2].editScalarInTableonly matches the bare key, and the multiline guard at Line 661 also only matches the bare form. A set operation then inserts a bare duplicate key instead of replacing the existing key. TOML treats these keys as identical, so Codex can no longer parseconfig.toml.Match and decode bare and quoted keys consistently in the dedicated-table reader, multiline guard, and writer. Add a regression test for updating and clearing a quoted key.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/codex/features.ts` around lines 650 - 667, Update setV2StringField and the dedicated-table helpers to recognize bare, double-quoted, and single-quoted forms of the same key, decoding them consistently for reads, multiline detection, and edits so existing quoted entries are replaced rather than duplicated. Preserve support for unquoted keys and null clearing, and add regression coverage for updating and clearing quoted multi_agent_mode_hint_text entries.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@gui/src/pages/Subagents.tsx`:
- Around line 34-42: Update loadUltraMode to return the parsed UltraModeState
without calling setUltraMode, and have its callers apply the result only when
the request is still current. Add cancellation, request-generation, or
current-apiBase guarding that covers both mount loads and save-triggered
refreshes, ensuring stale /api/v2 responses never overwrite state for a newer
API server.
---
Outside diff comments:
In `@src/codex/features.ts`:
- Around line 650-667: Update setV2StringField and the dedicated-table helpers
to recognize bare, double-quoted, and single-quoted forms of the same key,
decoding them consistently for reads, multiline detection, and edits so existing
quoted entries are replaced rather than duplicated. Preserve support for
unquoted keys and null clearing, and add regression coverage for updating and
clearing quoted multi_agent_mode_hint_text entries.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: f09bb947-49b9-44e0-b92e-b8202a9af59c
⛔ Files ignored due to path filters (1)
docs-site/public/assets/ultra-mode-subagents.pngis excluded by!**/*.png
📒 Files selected for processing (8)
docs-site/src/content/docs/reference/cli/agents.mddocs-site/src/content/docs/reference/configuration/agents.mdgui/src/components/subagents-workspace/SubagentDelegationSection.tsxgui/src/components/subagents-workspace/SubagentsWorkspace.tsxgui/src/pages/Subagents.tsxsrc/cli/v2.tssrc/codex/features.tstests/codex-v2-gate.test.ts
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b85b95cb45
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: fb8a391591
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| const probe = probeCodexSupportsModeHint(); | ||
| if (probe === false) { |
There was a problem hiding this comment.
When a user downgrades Codex or shares a CODEX_HOME containing a hint written by a newer build, the old runtime rejects the existing key and cannot start, but this unconditional probe also makes ocx v2 mode-hint --clear and the dashboard's off action refuse to remove it. The newly added capability gate should apply only to non-null writes; null removal is backward-compatible and must remain available as the recovery path.
AGENTS.md reference: src/AGENTS.md:L10-L10
Useful? React with 👍 / 👎.
| // Multi-line basic string: `"""..."""` with escapes. | ||
| if (token.startsWith('"""')) { | ||
| if (!token.endsWith('"""') || token.length < 6) return null; | ||
| return decodeBasicStringBody(token.slice(3, -3)); |
There was a problem hiding this comment.
For a valid multiline hint using TOML's opening-newline elision or a line-ending backslash continuation, this new branch delegates to the single-line escape decoder: it retains the normally discarded first newline, and a continuation reaches the default escape case and returns null. Consequently getMultiAgentModeHintText can report text different from what Codex uses—or report an active hint as absent—while the writer then refuses to edit that multiline value. Decode the multiline-only newline and continuation rules before returning the hint.
AGENTS.md reference: src/AGENTS.md:L10-L10
Useful? React with 👍 / 👎.
| if (value.trim().length === 0 || value.startsWith("-")) { | ||
| log.error("v2 mode-hint: pass the hint text, or --clear to unset it."); | ||
| return 1; |
There was a problem hiding this comment.
When the intended prose begins with a hyphen, such as ocx v2 mode-hint "- Delegate independent work early", this condition rejects it even though --clear is the only reserved argument and the documented contract otherwise accepts arbitrary nonblank text. This makes a valid hint impossible to set through the CLI; distinguish the exact reserved flag, or support a -- terminator, instead of rejecting every leading hyphen.
AGENTS.md reference: AGENTS.md:L231-L232
Useful? React with 👍 / 👎.
| ultraSaving, | ||
| onUltraModeSave: patch => { void saveUltraMode(patch); }, | ||
| ultraLoadFailed, | ||
| onUltraModeRetry: () => { void loadUltraMode().catch(() => { setOk(false); setUltraLoadFailed(true); setStatus(t("sub.ultraModeLoadFail")); }); }, |
There was a problem hiding this comment.
After the initial /api/v2 request fails, status is set to the Ultra-mode load error and rendered as the page-level red notice; the newly added retry callback only handles rejection, while a successful loadUltraMode() clears ultraLoadFailed but never clears that status. The controls therefore recover while the page continues to claim loading failed until some unrelated save changes the notice. Clear the stale status, and update its tone if needed, when the retry succeeds.
AGENTS.md reference: gui/AGENTS.md:L33-L33
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/codex/features.ts`:
- Around line 832-892: Deduplicate the platform package definitions in
codexNativeBinaryCandidates by extracting one shared array of package name,
target triple, and executable name tuples, including all Windows variants.
Replace the three repeated candidate-building lists in the wrapper-relative,
CODEX_MANAGED_PACKAGE_ROOT, and resolved-command branches with loops over that
shared array, preserving their existing root paths.
- Around line 785-830: Cache the result of probeCodexSupportsModeHint per
resolved runtime.command so repeated setMultiAgentModeHintText requests do not
reread and scan native binaries on the request thread. Reuse the cached boolean
or null result for the same command, while invalidating or distinguishing
entries when the resolved command changes; preserve the existing false rejection
and null fallback behavior.
- Around line 375-396: Update decodeTomlStringToken so multi-line literal and
basic string bodies remove the TOML-required leading newline after stripping
their triple delimiters. Apply the trim directly to the triple-single body and
before calling decodeBasicStringBody for triple-double strings, while preserving
all other decoding and validation behavior.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: a10a9305-5c3a-4d56-bf27-2498bca681b5
📒 Files selected for processing (12)
gui/src/components/subagents-workspace/SubagentDelegationSection.tsxgui/src/components/subagents-workspace/SubagentsWorkspace.tsxgui/src/i18n/de.tsgui/src/i18n/en.tsgui/src/i18n/ja.tsgui/src/i18n/ko.tsgui/src/i18n/ru.tsgui/src/i18n/zh.tsgui/src/pages/Subagents.tsxsrc/cli/help.tssrc/codex/features.tstests/codex-v2-gate.test.ts
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: fb8a391591
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| const table = tomlTableBody(content, "features.multi_agent_v2"); | ||
| if (table !== null) { | ||
| const m = table.match(/^\s*subagent_developer_instructions\s*=\s*/m); | ||
| const keyRe = new RegExp(`^\\s*${escapeRegExp(key)}\\s*=\\s*`, "m"); |
There was a problem hiding this comment.
When a valid dedicated table uses the quoted key form "multi_agent_mode_hint_text" = "old", this bare-key regex reports the hint as absent. A subsequent non-null save reaches editScalarInTable, which also misses the quoted assignment and inserts an equivalent bare key, producing a duplicate TOML key that Codex cannot parse; clearing similarly becomes a no-op. Recognize and decode quoted keys before reading, replacing, or removing this field.
AGENTS.md reference: src/AGENTS.md:L10-L10
Useful? React with 👍 / 👎.
| // saveUltraMode can report them against the save action. | ||
| const loadUltraMode = useCallback(async (signal?: AbortSignal) => { | ||
| const res = await fetch(`${apiBase}/api/v2`, { signal }); | ||
| const data = await readJsonOrThrow<{ enabled?: boolean; multiAgentModeHintText?: string | null }>(res, t("sub.ultraModeLoadFail")); |
There was a problem hiding this comment.
The /api/v2 response also provides multiAgentMode, but this loader ignores it and treats the native feature flag alone as sufficient. In the normal default mode, applyMultiAgentMode preserves upstream V1 pins such as Luna, and after mode v1 followed by ocx v2 on, every catalog entry remains forced to V1; those sessions do not receive this V2-only mode hint even though the dashboard enables the switch and claims every model is covered. Consume the effective surface mode and either require/offer v2 mode or clearly restrict Ultra mode to V2 models.
AGENTS.md reference: gui/AGENTS.md:L10-L10
Useful? React with 👍 / 👎.
| out.push(join(pkgRoot, "node_modules", "@openai", "codex-darwin-arm64", "vendor", "aarch64-apple-darwin", "bin", "codex")); | ||
| out.push(join(pkgRoot, "node_modules", "@openai", "codex-darwin-x64", "vendor", "x86_64-apple-darwin", "bin", "codex")); | ||
| out.push(join(pkgRoot, "node_modules", "@openai", "codex-linux-x64", "vendor", "x86_64-unknown-linux-musl", "bin", "codex")); | ||
| out.push(join(pkgRoot, "node_modules", "@openai", "codex-linux-arm64", "vendor", "aarch64-unknown-linux-musl", "bin", "codex")); |
There was a problem hiding this comment.
On a normal Windows npm installation, the resolved runtime is a codex.cmd or codex.opencodex-real.cmd wrapper. The probe reads that wrapper and sets sawBinary = true, but this wrapper-discovery block adds only Darwin and Linux native packages; the later realpathSync(command) fallback also derives the package root from the .cmd file's directory rather than from the referenced JS package. It therefore finds no native executable, returns false, and rejects every attempt to enable Ultra mode with the misleading instruction to update Codex even when the installed version supports the key. Add the Windows platform-package candidates using the wrapper's actual npm package location, and do not count script wrappers as inspected native binaries.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: fb8a391591
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| const pathDirs = (process.env.PATH ?? "").split(process.platform === "win32" ? ";" : ":"); | ||
| for (const dir of pathDirs) { | ||
| const wrapper = join(dir, process.platform === "win32" ? "codex.opencodex-real.cmd" : "codex.opencodex-real"); |
There was a problem hiding this comment.
When CODEX_CLI_PATH or the persisted runtime selects an older Codex while a newer codex.opencodex-real is also on PATH, this unconditional PATH scan adds the newer installation's native binary to the candidates. The probe returns true as soon as that unrelated binary contains the key, so Ultra mode writes multi_agent_mode_hint_text for the selected older runtime, which then rejects the unknown field and cannot start. Derive candidates exclusively from runtime.command (and its own shim metadata/package root) rather than mixing every PATH installation into the capability result.
AGENTS.md reference: src/AGENTS.md:L10-L10
Useful? React with 👍 / 👎.
| const tableText = `[features.multi_agent_v2]${eol}${key} = ${encoded}${eol}`; | ||
| atomicWriteFile(path, `${content}${suffix}${separator}${tableText}`); |
There was a problem hiding this comment.
When a valid Codex config expresses this object with root dotted keys, such as features.multi_agent_v2.enabled = true, none of the preceding dedicated-table, [features] inline-table, or bare-boolean checks recognize it. Enabling Ultra mode therefore appends [features.multi_agent_v2], redefining the table created by the dotted key and making config.toml invalid, so Codex fails at startup. Detect and edit the dotted-key representation or refuse the mutation without writing.
AGENTS.md reference: src/AGENTS.md:L10-L10
Useful? React with 👍 / 👎.
| /** Canonical Proactive delegation text mirrored from codex-rs (multi_agent_mode_instructions.rs). */ | ||
| export const ULTRA_MODE_PRESET = | ||
| "Proactive multi-agent delegation is active. Any earlier instruction requiring an explicit user request before spawning sub-agents no longer applies. Use sub-agents when parallel work would materially improve speed or quality. This mode remains active until a later multi-agent mode developer message changes it."; |
There was a problem hiding this comment.
This string is labeled as the canonical codex-rs preset, but it differs materially from the repository's existing PROACTIVE_MULTI_AGENT_MODE_TEXT in src/server/responses/collaboration.ts: it omits the instructions not to serialize independent work and to prefer specialist sub-agents with their own tool-capable contexts. Because multi_agent_mode_hint_text replaces the effort-derived message rather than augmenting it, enabling or restoring Ultra mode installs this weaker prompt instead of the native proactive behavior the UI and documentation promise. Keep this preset byte-aligned with the canonical text, ideally from a single shared source.
Useful? React with 👍 / 👎.
Ingwannu
left a comment
Ingwannu
left a comment
There was a problem hiding this comment.
The upstream capability is technically real, but this head is not an integration candidate yet.
- The branch is currently 526 commits behind
dev; the readiness checklist correctly leaves the latest-dev box unchecked. Please rebase and resolve the accumulated config/GUI/test overlap before further review. - Exact-head CI is red (
test 2/4, macOS, gates, and the aggregatecicheck). Do not treat the local focused pass as sufficient until the rebased head is green. - The current
decodeTomlStringTokenimplementation returns the mandatory first newline inside TOML multiline basic/literal strings. TOML trims the newline immediately following the opening triple quote, so reading a validmulti_agent_mode_hint_text = """ Proactive..."""currently adds a spurious leading newline. Fix both triple-quoted forms and keep a regression that matches TOML semantics.
The product naming, default preset text, GUI switch, and whether OCX should expose this unstable upstream override at all require @lidge-jun's explicit product/UI decision. This review is limited to the stale integration and parser/CI blockers; it is not an approval of the UI direction.
fb8a391 to
d0affeb
Compare
|
Note GitHub couldn't provide a complete incremental comparison for this pull request, so CodeRabbit is performing a full review instead. This review may take a little longer. |
Wibias
left a comment
Wibias
left a comment
There was a problem hiding this comment.
Re-review on current head d8987f59c34686bfad27d3eca3b0d0773e1baf7a.
The previous P2 parser blocker is fixed correctly. scanTomlValueEnd now consumes valid 4- and 5-quote closing runs for both multiline basic and literal TOML strings, and the added regressions verify that the surplus one or two quotes remain part of the decoded hint. I did not find a new code blocker in that fix or in the previously reviewed Ultra-mode implementation.
One integration blocker remains before approval:
- The branch is currently 1 commit behind
dev. Currentdevisb8a2e51b81aafec33a4865675d2bb29aa1f9eea1, while this head still has merge basee8db4e0365b12a314d1c08ec2cf81599efe5b2d3. The missing dev commit is #1501 (fix(deepseek): preserve parallel reasoning replay) and appears unrelated to this PR, so the rebase should be low-risk, but the repository readiness contract requires the PR to be on latestdev. - Exact-head React Doctor is green. Cross-platform CI for this head is still running at the time of review. After rebasing, the new head needs its own green CI signal.
- The PR is currently draft and its readiness checklist is reset/unchecked, which matches that integration state.
Please rebase onto current dev, rerun exact-head CI, and request re-review. Assuming that lands cleanly and CI is green, I have no remaining code objection from this review.
|
🧠 Learnings used✅ Action performedReview finished.
|
|
🧠 Learnings used
|
|
Note GitHub couldn't provide a complete incremental comparison for this pull request, so CodeRabbit is performing a full review instead. This review may take a little longer. |
|
🧠 Learnings used
|
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/codex/features.ts`:
- Around line 825-861: Update tomlTableBodyForStringFields to scan from offset 0
using scanTomlValueEnd, accepting [header] matches only when they occur outside
complete TOML values; continue searching past header-shaped lines inside
multiline strings. In editScalarInTable, ensure the missing-target guard runs
when either table body omits the assignment, preventing insertion into unrelated
content. Add a regression test covering a header-shaped line inside an earlier
multiline string before the real table.
- Around line 1184-1192: Update resolveSelectedCommandPath to support bare
Windows commands by checking each suffix from PATHEXT, including candidates such
as codex.cmd and codex.exe, while preserving direct path handling and existing
PATH lookup behavior. Add regression tests covering bare commands that resolve
to .cmd and .exe files, ensuring unsupported mode hints are not persisted when
resolution fails.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 4a1a1b07-3e89-41b9-b287-65f2f792c824
⛔ Files ignored due to path filters (1)
docs-site/public/assets/ultra-mode-subagents.pngis excluded by!**/*.png
📒 Files selected for processing (21)
docs-site/src/content/docs/reference/cli/agents.mddocs-site/src/content/docs/reference/configuration/agents.mdgui/src/components/subagents-workspace/SubagentDelegationSection.tsxgui/src/components/subagents-workspace/SubagentsWorkspace.tsxgui/src/i18n/de.tsgui/src/i18n/en.tsgui/src/i18n/ja.tsgui/src/i18n/ko.tsgui/src/i18n/ru.tsgui/src/i18n/tr.tsgui/src/i18n/zh-TW.tsgui/src/i18n/zh.tsgui/src/pages/Subagents.tsxgui/src/pages/use-subagent-delegation.tsgui/tests/multi-agent-guidance.test.tsxgui/tests/subagents-ultra-mode.test.tsxsrc/cli/help.tssrc/cli/v2.tssrc/codex/features.tssrc/server/management/agent-settings-routes.tstests/codex-v2-gate.test.ts
| /** | ||
| * A table body scanner that skips complete TOML values before recognizing the | ||
| * next header. Unlike the legacy line scanner, bracket-shaped prose inside a | ||
| * multi-line string cannot truncate the table. | ||
| */ | ||
| function tomlTableBodyForStringFields(content: string, header: string): string | null { | ||
| const escaped = escapeRegExp(header); | ||
| const match = new RegExp(`^\\s*\\[${escaped}\\]\\s*(?:#.*)?$`, "m").exec(content); | ||
| if (!match) return null; | ||
| const newline = content.indexOf("\n", match.index + match[0].length); | ||
| if (newline === -1) return ""; | ||
| const bodyStart = newline + 1; | ||
| let lineStart = bodyStart; | ||
| while (lineStart < content.length) { | ||
| let cursor = lineStart; | ||
| while (content[cursor] === " " || content[cursor] === "\t") cursor++; | ||
| if (content[cursor] === "[") return content.slice(bodyStart, lineStart); | ||
| const lineEnd = content.indexOf("\n", cursor); | ||
| const boundedEnd = lineEnd === -1 ? content.length : lineEnd; | ||
| let keyEnd = cursor; | ||
| if (content[keyEnd] === '"' || content[keyEnd] === "'") { | ||
| keyEnd = scanTomlValueEnd(content, keyEnd); | ||
| } else { | ||
| const keyMatch = /^[A-Za-z0-9_.-]+/.exec(content.slice(keyEnd, boundedEnd)); | ||
| if (keyMatch) keyEnd += keyMatch[0].length; | ||
| } | ||
| while (content[keyEnd] === " " || content[keyEnd] === "\t") keyEnd++; | ||
| if (content[keyEnd] === "=" && keyEnd < boundedEnd) { | ||
| const valueEnd = scanTomlValueEnd(content, keyEnd + 1); | ||
| const nextLine = content.indexOf("\n", valueEnd); | ||
| lineStart = nextLine === -1 ? content.length : nextLine + 1; | ||
| } else { | ||
| lineStart = lineEnd === -1 ? content.length : lineEnd + 1; | ||
| } | ||
| } | ||
| return content.slice(bodyStart); | ||
| } |
There was a problem hiding this comment.
🗄️ Data Integrity & Integration | 🟠 Major | 🏗️ Heavy lift
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== both header lookups in features.ts =="
rg -nP --type=ts -C6 'function tomlTableBodyForStringFields|function tomlTableBody\b' src/codex/features.ts
echo
echo "== every caller that depends on the header anchor =="
rg -nP --type=ts -C3 'tomlTableBodyForStringFields\(|tomlTableBody\(' src
echo
echo "== does any existing test place a header-shaped line BEFORE the real table? =="
rg -nP -C6 'unrelated|\[prose\]|\[bracketed\]' tests/codex-v2-gate.test.tsRepository: lidge-jun/opencodex
Length of output: 18134
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== relevant helper implementations =="
sed -n '730,940p' src/codex/features.ts
echo
echo "== exact fixture-related tests and writer paths =="
sed -n '480,605p' tests/codex-v2-gate.test.ts
echo
echo "== structural definitions and call sites =="
rg -n -C3 'function (scanTomlValueEnd|findTomlAssignment|setV2StringField|tomlTableBodyForStringFields|tomlTableBody)\b|tomlTableBodyForStringFields\(|tomlTableBody\(' src/codex/features.tsRepository: lidge-jun/opencodex
Length of output: 28512
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== scanner and assignment semantics =="
sed -n '500,730p' src/codex/features.ts
echo
echo "== writer implementation around editScalarInTable =="
sed -n '650,760p' src/codex/features.ts
echo
echo "== behavioral probe for the proposed fixture =="
node - <<'JS'
const content = `[unrelated]
note = """
[features.multi_agent_v2]
"""
[features.multi_agent_v2]
enabled = true
multi_agent_mode_hint_text = "old"
`;
function escapeRegExp(value) {
return value.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
}
function legacyBody(content, header) {
const lines = content.split("\n");
const escaped = escapeRegExp(header);
const start = lines.findIndex(l => new RegExp(`^\\s*\\[${escaped}\\]\\s*(?:#.*)?$`).test(l));
if (start === -1) return null;
const rest = lines.slice(start + 1);
const end = rest.findIndex(l => /^\s*\[/.test(l));
return rest.slice(0, end === -1 ? rest.length : end).join("\n");
}
function scanTomlValueEnd(text, start) {
let i = start;
while (i < text.length && (text[i] === " " || text[i] === "\t")) i++;
const first = text[i];
const triple = text.slice(i, i + 3);
if (triple === '"""' || triple === "'''") {
const quote = triple;
i += 3;
while (i < text.length) {
if (text.slice(i, i + 3) === quote) {
let run = 3;
while (i + run < text.length && text[i + run] === quote[0]) run++;
i += run;
return i;
}
i++;
}
return text.length;
}
if (first === '"' || first === "'") {
const quote = first;
i++;
while (i < text.length) {
if (text[i] === quote && (quote === "'" || text[i - 1] !== "\\")) return i + 1;
i++;
}
return text.length;
}
let depth = 0;
let inBasic = false;
let inLiteral = false;
while (i < text.length) {
const ch = text[i];
if (ch === '"' && !inLiteral && text[i - 1] !== "\\") inBasic = !inBasic;
else if (ch === "'" && !inBasic) inLiteral = !inLiteral;
else if (!inBasic && !inLiteral && (ch === "[" || ch === "{")) depth++;
else if (!inBasic && !inLiteral && (ch === "]" || ch === "}")) {
if (depth > 0) depth--;
} else if (!inBasic && !inLiteral && depth === 0 && ch === "#") break;
else if (!inBasic && !inLiteral && depth === 0 && ch === "\n") break;
i++;
}
return i;
}
function newBody(content, header) {
const escaped = escapeRegExp(header);
const match = new RegExp(`^\\s*\\[${escaped}\\]\\s*(?:#.*)?$`, "m").exec(content);
if (!match) return null;
const newline = content.indexOf("\n", match.index + match[0].length);
if (newline === -1) return "";
const bodyStart = newline + 1;
let lineStart = bodyStart;
while (lineStart < content.length) {
let cursor = lineStart;
while (content[cursor] === " " || content[cursor] === "\t") cursor++;
if (content[cursor] === "[") return content.slice(bodyStart, lineStart);
const lineEnd = content.indexOf("\n", cursor);
const boundedEnd = lineEnd === -1 ? content.length : lineEnd;
let keyEnd = cursor;
if (content[keyEnd] === '"' || content[keyEnd] === "'") {
keyEnd = scanTomlValueEnd(content, keyEnd);
} else {
const keyMatch = /^[A-Za-z0-9_.-]+/.exec(content.slice(keyEnd, boundedEnd));
if (keyMatch) keyEnd += keyMatch[0].length;
}
while (content[keyEnd] === " " || content[keyEnd] === "\t") keyEnd++;
if (content[keyEnd] === "=" && keyEnd < boundedEnd) {
const valueEnd = scanTomlValueEnd(content, keyEnd + 1);
const nextLine = content.indexOf("\n", valueEnd);
lineStart = nextLine === -1 ? content.length : nextLine + 1;
} else {
lineStart = lineEnd === -1 ? content.length : lineEnd + 1;
}
}
return content.slice(bodyStart);
}
const legacy = legacyBody(content, "features.multi_agent_v2");
const current = newBody(content, "features.multi_agent_v2");
console.log(JSON.stringify({
regexMatchOffset: content.indexOf("[features.multi_agent_v2]"),
realHeaderOffset: content.lastIndexOf("[features.multi_agent_v2]"),
legacy,
current,
legacyHasEnabled: /^\s*enabled\s*=/m.test(legacy ?? ""),
currentHasEnabled: /^\s*enabled\s*=/m.test(current ?? "")
}, null, 2));
JSRepository: lidge-jun/opencodex
Length of output: 13661
🏁 Script executed:
#!/bin/bash
set -euo pipefail
node - <<'JS'
const content = `[unrelated]
note = """
[features.multi_agent_v2]
"""
[features.multi_agent_v2]
enabled = true
multi_agent_mode_hint_text = "old"
`;
function escapeRegExp(value) {
return value.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
}
function scanTomlValueEnd(text, start) {
let i = start;
while (i < text.length && (text[i] === " " || text[i] === "\t")) i++;
const first = text[i];
if (first === '"' && text[i + 1] === '"' && text[i + 2] === '"') {
i += 3;
while (i < text.length) {
if (text[i] === "\\") { i += 2; continue; }
if (text[i] === '"' && text[i + 1] === '"' && text[i + 2] === '"') {
let end = i + 3;
if (text[end] === '"') {
end++;
if (text[end] === '"') end++;
}
return end;
}
i++;
}
return text.length;
}
if (first === '"' || first === "'") {
const quote = first;
i++;
while (i < text.length) {
if (quote === "'" ? text[i] === "'" : text[i] === '"' && text[i - 1] !== "\\") return i + 1;
i++;
}
return text.length;
}
while (i < text.length && !/[\s,}\]#]/.test(text[i])) i++;
return i;
}
function stringAwareBody(content, header) {
const escaped = escapeRegExp(header);
const match = new RegExp(`^\\s*\\[${escaped}\\]\\s*(?:#.*)?$`, "m").exec(content);
if (!match) return null;
const newline = content.indexOf("\n", match.index + match[0].length);
if (newline === -1) return "";
const bodyStart = newline + 1;
let lineStart = bodyStart;
while (lineStart < content.length) {
let cursor = lineStart;
while (content[cursor] === " " || content[cursor] === "\t") cursor++;
if (content[cursor] === "[") return content.slice(bodyStart, lineStart);
const lineEnd = content.indexOf("\n", cursor);
const boundedEnd = lineEnd === -1 ? content.length : lineEnd;
let keyEnd = cursor;
if (content[keyEnd] === '"' || content[keyEnd] === "'") {
keyEnd = scanTomlValueEnd(content, keyEnd);
} else {
const keyMatch = /^[A-Za-z0-9_.-]+/.exec(content.slice(keyEnd, boundedEnd));
if (keyMatch) keyEnd += keyMatch[0].length;
}
while (content[keyEnd] === " " || content[keyEnd] === "\t") keyEnd++;
if (content[keyEnd] === "=" && keyEnd < boundedEnd) {
const valueEnd = scanTomlValueEnd(content, keyEnd + 1);
const nextLine = content.indexOf("\n", valueEnd);
lineStart = nextLine === -1 ? content.length : nextLine + 1;
} else {
lineStart = lineEnd === -1 ? content.length : lineEnd + 1;
}
}
return content.slice(bodyStart);
}
function findAssignment(text, key) {
const match = new RegExp(`^\\s*${escapeRegExp(key)}\\s*=.*$`, "m").exec(text);
return match ? match[0] : null;
}
function editScalarInTable(source, table, key, encoded) {
const lines = source.split(/\r?\n/);
const headerRe = new RegExp(`^\\s*\\[${table.replace(/\./g, "\\.")}\\]\\s*(?:#.*)?$`);
const headerIdx = lines.findIndex(l => headerRe.test(l));
let end = lines.length;
for (let i = headerIdx + 1; i < lines.length; i++) {
if (/^\s*\[/.test(lines[i])) { end = i; break; }
}
for (let i = headerIdx + 1; i < end; i++) {
if (findAssignment(lines[i], key)) {
lines[i] = `${key} = ${encoded}`;
return lines.join("\n");
}
}
lines.splice(headerIdx + 1, 0, `${key} = ${encoded}`);
return lines.join("\n");
}
const body = stringAwareBody(content, "features.multi_agent_v2");
const legacyBody = content.split("\n").slice(
content.split("\n").findIndex(l => /^\s*\[features\.multi_agent_v2\]\s*(?:#.*)?$/.test(l)) + 1
).join("\n").split(/^\s*\[/m)[0];
const edited = editScalarInTable(content, "features.multi_agent_v2", "multi_agent_mode_hint_text", '"new"');
console.log(JSON.stringify({
stringAwareBody: body,
targetReadFromStringAwareBody: findAssignment(body ?? "", "multi_agent_mode_hint_text"),
targetReadFromLegacyBody: findAssignment(legacyBody, "multi_agent_mode_hint_text"),
failClosedGuardWouldFire: !!findAssignment(body ?? "", "multi_agent_mode_hint_text") &&
!findAssignment(legacyBody, "multi_agent_mode_hint_text"),
edited
}, null, 2));
JSRepository: lidge-jun/opencodex
Length of output: 509
🏁 Script executed:
nl -ba src/codex/features.ts | sed -n '670,715p;824,930p'Repository: lidge-jun/opencodex
Length of output: 193
Resolve the header anchor outside multiline values
At src/codex/features.ts:832, the regex can match [features.multi_agent_v2] inside an earlier multiline string. The scanner then starts at the false header and returns only the string terminator, so getV2StringField misses the real field.
The writer also fails closed incorrectly. At src/codex/features.ts:922-925, both bodies omit the target assignment, so the guard does not run. editScalarInTable then inserts the replacement into the unrelated multiline string instead of the real table, which can corrupt the TOML document.
Scan from offset 0 with the same string-aware value scanner and accept a header only outside a complete TOML value. Add a regression test with a header-shaped line before the real table.
🧰 Tools
🪛 ast-grep (0.45.1)
[warning] 831-831: Regular expression constructed from variable input detected. This can lead to Regular Expression Denial of Service (ReDoS) attacks if the variable contains malicious patterns. Use libraries like 'recheck' to validate regex safety or use static patterns.
Context: new RegExp(^\\s*\\[${escaped}\\]\\s*(?:#.*)?$, "m")
Note: [CWE-1333] Inefficient Regular Expression Complexity
(regexp-from-variable)
🪛 OpenGrep (1.26.0)
[ERROR] 832-832: Dynamic command passed to child_process.exec/execSync. Use child_process.execFile or spawn with an argument array instead.
(coderabbit.command-injection.exec-js)
[ERROR] 848-848: Dynamic command passed to child_process.exec/execSync. Use child_process.execFile or spawn with an argument array instead.
(coderabbit.command-injection.exec-js)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@src/codex/features.ts` around lines 825 - 861, Update
tomlTableBodyForStringFields to scan from offset 0 using scanTomlValueEnd,
accepting [header] matches only when they occur outside complete TOML values;
continue searching past header-shaped lines inside multiline strings. In
editScalarInTable, ensure the missing-target guard runs when either table body
omits the assignment, preventing insertion into unrelated content. Add a
regression test covering a header-shaped line inside an earlier multiline string
before the real table.
| /** Resolve only the selected bare command against PATH; never enumerate peers. */ | ||
| function resolveSelectedCommandPath(command: string): string | null { | ||
| if (command.includes("/") || command.includes("\\")) return existsSync(command) ? resolve(command) : null; | ||
| for (const dir of (process.env.PATH ?? "").split(delimiter).filter(Boolean)) { | ||
| const candidate = join(dir, command); | ||
| if (existsSync(candidate)) return candidate; | ||
| } | ||
| return null; | ||
| } |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟠 Major | 🏗️ Heavy lift
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== how runtime.command is produced =="
rg -nP --type=ts -C6 '\bcommand\s*[:=]' src/codex/runtime.ts | head -120
echo
echo "== any PATHEXT / .cmd / .exe awareness in runtime resolution =="
rg -nP --type=ts -C4 'PATHEXT|\.cmd|\.exe|win32' src/codex/runtime.ts src/codex/features.ts
echo
echo "== existing PATH-scan helpers elsewhere in the repo =="
ast-grep run --lang typescript --pattern 'process.env.PATH ?? $_' src | head -40Repository: lidge-jun/opencodex
Length of output: 10027
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== feature gate call chain and candidate construction =="
sed -n '1000,1215p' src/codex/features.ts
echo
echo "== runtime candidate resolution and platform checks =="
sed -n '280,380p' src/codex/runtime.ts
sed -n '520,590p' src/codex/runtime.ts
echo
echo "== tests covering Windows runtime commands and feature probing =="
rg -n -C8 --type=ts 'codexNativeBinaryCandidates|resolveSelectedCommandPath|multi_agent_mode_hint_text|platform.*win32|codex\.cmd|codex\.exe' tests src/codex
echo
echo "== exact call sites for the selected-command resolver =="
rg -n -C10 --type=ts 'resolveSelectedCommandPath|codexNativeBinaryCandidates|probeCodexSupportsModeHint' src/codex/features.tsRepository: lidge-jun/opencodex
Length of output: 50376
🏁 Script executed:
#!/bin/bash
set -euo pipefail
python3 - <<'PY'
from pathlib import Path
features = Path("src/codex/features.ts").read_text()
runtime = Path("src/codex/runtime.ts").read_text()
needles = [
"function resolveSelectedCommandPath",
"function codexNativeBinaryCandidates",
"function probeCodexSupportsModeHint",
"function setMultiAgentModeHintText",
"resolveSelectedCommandPath(",
]
for needle in needles:
print(f"== {needle} in src/codex/features.ts ==")
lines = features.splitlines()
for i, line in enumerate(lines, 1):
if needle in line:
for j in range(max(1, i-8), min(len(lines), i+35)+1):
print(f"{j}: {lines[j-1]}")
print()
print("== pathCandidates/probeVersion in src/codex/runtime.ts ==")
lines = runtime.splitlines()
for needle in ("function pathCandidates", "function probeVersion", "function shimCandidates"):
for i, line in enumerate(lines, 1):
if needle in line:
for j in range(max(1, i-5), min(len(lines), i+45)+1):
print(f"{j}: {lines[j-1]}")
print()
PYRepository: lidge-jun/opencodex
Length of output: 22761
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== runtime resolution order and persisted/environment behavior =="
sed -n '530,575p' src/codex/runtime.ts
sed -n '240,285p' src/codex/runtime.ts
rg -n -C8 --type=ts 'CODEX_CLI_PATH|persisted.*command|resolveAndPersistCodexRuntime|isSpawnableCodexCandidate' src/codex/runtime.ts tests/codex-v2-gate.test.ts
echo
echo "== focused capability-probe tests =="
sed -n '590,680p' tests/codex-v2-gate.test.ts
sed -n '1660,1700p' tests/codex-v2-gate.test.ts
echo
echo "== platform candidate validation =="
rg -n -C12 --type=ts 'function isSpawnableCodexCandidate|isSpawnableCodexCandidate' src/codex/runtime.tsRepository: lidge-jun/opencodex
Length of output: 25506
🏁 Script executed:
#!/bin/bash
set -euo pipefail
python3 - <<'PY'
from pathlib import PurePosixPath
def feature_resolve(command, path, existing):
if "/" in command or "\\" in command:
return command if command in existing else None
for directory in filter(None, path.split(";")):
candidate = f"{directory}/{command}"
if candidate in existing:
return candidate
return None
def runtime_path_candidates(path):
out = []
for directory in filter(None, path.split(";")):
out.extend([f"{directory}/codex.exe", f"{directory}/codex.cmd"])
return list(dict.fromkeys(out))
existing = {r"C:\bin/codex.cmd", r"C:\bin/codex.exe"}
print("feature resolver with bare command:", feature_resolve("codex", r"C:\bin", existing))
print("runtime resolver candidates:", runtime_path_candidates(r"C:\bin"))
print("feature resolver with selected .cmd:", feature_resolve("C:\\bin\\codex.cmd", r"C:\bin", existing))
PYRepository: lidge-jun/opencodex
Length of output: 312
Resolve bare Windows commands with PATHEXT.
When runtime.command is bare codex, resolveSelectedCommandPath checks only PATH\codex. This occurs for CODEX_CLI_PATH, persisted runtime state, or fallback selections; normal Windows PATH discovery already returns codex.exe or codex.cmd. If only codex.cmd or codex.exe exists, the resolver returns null, skips wrapper and binary candidates, and probeCodexSupportsModeHint() returns null. Because only false blocks the write, setMultiAgentModeHintText() can still persist an unsupported key. Scan PATHEXT suffixes and add regression tests for bare commands resolving to .cmd and .exe.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@src/codex/features.ts` around lines 1184 - 1192, Update
resolveSelectedCommandPath to support bare Windows commands by checking each
suffix from PATHEXT, including candidates such as codex.cmd and codex.exe, while
preserving direct path handling and existing PATH lookup behavior. Add
regression tests covering bare commands that resolve to .cmd and .exe files,
ensuring unsupported mode hints are not persisted when resolution fails.
Source: Linters/SAST tools
…el/effort Expose codex-rs features.multi_agent_v2.multi_agent_mode_hint_text through the OCX config editor, /api/v2, the ocx v2 CLI, and the Subagents GUI. The upstream field overrides the effort-derived multi-agent policy (ultra -> Proactive, else ExplicitRequestOnly) with custom <multi_agent_mode> text, so any model and any reasoning effort can run the Proactive delegation prompt. - features.ts: generalize the v2 string-field reader/writer and add get/setMultiAgentModeHintText (dedicated table, inline table, bare-boolean upgrade, CRLF/EOL preservation). - agent-settings-routes.ts: GET /api/v2 reports multiAgentModeHintText; PUT accepts string|null and rejects empty/whitespace strings (a present empty override would suppress even the ultra-derived Proactive message). - cli/v2.ts: ocx v2 mode-hint <text|--clear> and status line. - GUI: Ultra mode switch + editable text + preset restore on the Subagents page, disabled until multi_agent_v2 is enabled. - tests: reader/writer encodings, clear semantics, inline-table tricky values, API GET/PUT/400 validation, CLI mode-hint round-trip.
…aft editor, docs CodeRabbit findings: - CLI: preserve raw leading/trailing whitespace in mode-hint text; a missing argument is a usage error (never a destructive clear); only --clear unsets. Reject a present whitespace-only value, matching the API 400 contract. - features.ts: refuse to edit an existing multi-line TOML string for the hint key. scanTomlValueEnd stops at the second quote, so rewriting/removing a """...""" value would corrupt the document; convert to single line first. - GUI: the Ultra mode textarea now keeps a local draft and commits via an explicit Save button (remounted on server-value change), so keystrokes are never dropped while a PUT is in flight. /api/v2 fetch consolidated into one shared loader; initial-load failures surface sub.ultraModeLoadFail instead of masquerading as v2-off. V2 requirement is visible text, not only a title attr. - docs: document ocx v2 mode-hint and the multi_agent_mode_hint_text config key (override semantics, --clear, whitespace rejection, v2 requirement).
loadUltraMode now accepts an AbortSignal; the mount effect aborts it on cleanup so a pending fetch cannot apply state after unmount or after a refresh superseded it.
…e, GUI retry/clear
Codex + CodeRabbit findings:
- features.ts: scanTomlValueEnd/decodeTomlStringToken now read complete
multi-line TOML strings ("""...""" and '''...''') so the getter returns
the real hint instead of an empty string. probeCodexSupportsModeHint checks
the installed native codex binary for the multi_agent_mode_hint_text key
(following shim -> npm wrapper -> vendor binary) and refuses writes on older
builds that reject the unknown config member.
- cli/help.ts: advertise mode-hint in the v2 usage and global synopsis.
- GUI: empty/whitespace hint renders as OFF; clearing stays available when v2
is disabled (stale hint would otherwise re-activate); load failures surface
a retry; a successful save clears stale error status and confirms.
- tests: multi-line decode for basic and literal strings.
Rebase onto dev introduced zh-TW as a managed locale with a parity guard. The Ultra mode keys added by this PR were missing from zh-TW and would fail locale-parity on the rebased head.
TOML permits up to two quotes immediately inside the closing delimiter of a multiline string (e.g. """hello"""" → value is hello"). The scanner stopped at the first triple-quote run, so getMultiAgentModeHintText returned text different from what Codex parses. Now consume the full valid closing quote run for both basic and literal multiline strings. Regression coverage for 4- and 5-quote closing runs in both forms.
d8987f5 to
2c11539
Compare
|
Tip For best results, initiate chat on the files or code changes.
You are interacting with an AI system. |
|
🧠 Learnings used
|
🧩 Analysis chain🏁 Script executed: #!/bin/bash
set -euo pipefail
gh pr view 1209 --repo lidge-jun/opencodex \
--json headRefOid,isDraft,state,updatedAt \
--jq '{headRefOid, isDraft, state, updatedAt}'Length of output: 433
The review-readiness gate matches the current PR head. 🧠 Learnings used
|
|
Thank you @dbc-hbin for the work on this PR and for addressing the review feedback. This is useful because Ultra mode is now a proper OCX control instead of a manual config-only feature. Users can enable proactive sub-agent delegation consistently across models and reasoning-effort levels from the UI, CLI, or API. The added TOML safety checks and regression coverage also make it much safer to expose as a user-facing setting. |
3 participants
Summary
Adds an Ultra mode control that enables codex-rs's Proactive multi-agent delegation policy for every model and every reasoning effort, not just native
ultra-effort turns. It exposes the upstreamfeatures.multi_agent_v2.multi_agent_mode_hint_textconfig key through OCX's existing v2 config editor, management API, CLI, and the Subagents GUI.How it works
Upstream codex-rs derives the multi-agent policy from effort:
ultra→MultiAgentMode::Proactive, everything else →ExplicitRequestOnly(core/src/session/multi_agents.rs). A configuredmulti_agent_mode_hint_textoverrides that derivation entirely and injects the configured text as the<multi_agent_mode>developer message. Verified live: with the hint set,max/highsessions receive the Proactive prompt andcollaboration__spawn_agentactually spawns sub-agents.Note: the toggle does not change reasoning effort — it changes the delegation prompt policy. The GUI sublabel says so explicitly.
Changes
getMultiAgentModeHintText/setMultiAgentModeHintText. Handles all three TOML encodings (dedicated table, inline table, bare-boolean upgrade) with EOL preservation, matchingsubagent_developer_instructions.GET /api/v2returnsmultiAgentModeHintText;PUTacceptsstring | null. Empty/whitespace strings are rejected (a present empty override would suppress even the ultra-derived Proactive message upstream).ocx v2 mode-hint <text|--clear>plus a status line.multi_agent_v2is enabled.}, quotes), bare-boolean upgrade, API GET/PUT/400 validation, CLI round-trip.Validation
dev(e8db4e036);zh-TWlocale keys added to satisfy the new parity guard.bun x tsc --noEmit(server + gui) passesbun run lint(gui) passesbun test tests/codex-v2-gate.test.ts tests/management-client-config-route.test.ts— 141 passUI Screenshot
Ultra mode toggle on the Subagents page (switch + description + editor):
Summary by CodeRabbit
UI Screenshot
Ultra mode toggle on the Subagents page (switch + description + editor):
Review readiness checklist
This PR stays in draft until every box below is ticked. Tick all four boxes once the requirements are met:
All CI tests are green on my local testing.
I pushed my PR to the latest dev commit.
I resolved all correct Codex and CodeRabbit findings.
My PR is ready for review.