Improve readability issues by rakyll · Pull Request #2 · google-gemini/gemini-cli

rakyll · 2025-04-17T19:03:23Z

This is only the first change of many changes.

Remove redundant autogenerated comments
Use the recommended file name style
Use camelCase for variable names
Don't introduce submodules for relevant types
Don't introduce constants like modules, these are implementation details
Remove empty files

This is only the first change of many changes. * Remove redundant autogenerated comments * Use the recommended file name style * Use camelCase for variable names * Don't introduce submodules for relevant types * Don't introduce constants like modules, these are implementation details * Remove empty files

feat: Azure api support

…vironments google-gemini#2

…vely function - Combine initial abort check with depth check for efficiency - Remove unnecessary abort check before fs.readdir (no async operations between checks) - Add abort check after fs.readdir async operation where signal can actually change - Remove abort check from inside for loop (synchronous operations only)

…look for closingIssuesReferences instead of looking for the Issue ID in the body which can lead to wrong issues and labels being pulled in.

# This is the 1st commit message: feat: Create BYOID auth client when detecting BYOID credentials This change introduces a BYOID auth client that is created when BYOID credentials are detected. It also refactors the code assist server and setup to use the new AuthClient type. # This is the commit message google-gemini#2: resolve comments # This is the commit message google-gemini#3: load credentials only once and lazy load the client # This is the commit message google-gemini#4: use original method names # This is the commit message google-gemini#5: use original method names for getOauthClient # This is the commit message google-gemini#6: remove redundant test mock

…m_and_yarn-fd296dbd23 chore(deps): bump vite from 7.1.9 to 7.1.11 in the npm_and_yarn group across 1 directory

CRITICAL SECURITY FIX - Removed publicly exposed AWS credentials Files Changed: - BEDROCK_SETUP.md: Replaced real credentials with placeholder examples - QUICK_START.md: Replaced real credentials with placeholder examples Security Impact: - Removed AWS_ACCESS_KEY_ID: BedrockAPIKey-mzur-at-124737196430 - Removed AWS_SECRET_ACCESS_KEY (base64 encoded) Action Required: ⚠️ USER MUST ROTATE AWS BEDROCK API KEYS IMMEDIATELY ⚠️ These credentials were exposed in commit 3ef2c7c ⚠️ Go to AWS Console → IAM → Bedrock API Keys → Rotate Keys This commit removes the exposed secrets from documentation files. Users should now use placeholder examples and replace with their own keys. Fixes: GitHub Secret Scanning Alert google-gemini#2

…ration, and streaming heap parser Gap google-gemini#2: Built-in skill scaffold with SKILL.md, references (advanced-workflows, perfetto-sql), and launch-with-inspector helper script. The skill auto-triggers on memory/performance keywords. Gap google-gemini#2 (cont): InvestigationTool wrapper extends BaseDeclarativeTool, registered in config.ts via maybeRegister(), making `investigate` a first-class tool callable by the LLM. Gap google-gemini#4: StreamingHeapParser processes V8 heapsnapshots in 64KB chunks using a state machine. Files >50MB use streaming (10-15% peak memory), smaller files auto-fallback to JSON.parse. Integrated into analyze_heap_snapshot and diagnose_memory actions. Includes tests for tool wrapper, skill discovery, streaming parser, and SKILL.md structure. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

…ration, and streaming heap parser Gap google-gemini#2: Built-in skill scaffold with SKILL.md, references (advanced-workflows, perfetto-sql), and launch-with-inspector helper script. The skill auto-triggers on memory/performance keywords. Gap google-gemini#2 (cont): InvestigationTool wrapper extends BaseDeclarativeTool, registered in config.ts via maybeRegister(), making `investigate` a first-class tool callable by the LLM. Gap google-gemini#4: StreamingHeapParser processes V8 heapsnapshots in 64KB chunks using a state machine. Files >50MB use streaming (10-15% peak memory), smaller files auto-fallback to JSON.parse. Integrated into analyze_heap_snapshot and diagnose_memory actions. Includes tests for tool wrapper, skill discovery, streaming parser, and SKILL.md structure.

- Add m.youtube.com and music.youtube.com subdomain support (google-gemini#1) - Change mimeType from video/* to video/mp4 per Vertex AI docs (google-gemini#2)

#24857)

…ogle-gemini#2… (google-gemini#24857)

Adds a persistent agent swarm primitive behind the `experimental.swarm` settings flag. The main Gemini agent can now spawn long-lived Claude sub-agent instances, send them multiple messages across orchestrator turns (retaining `messages` state), and release them — going beyond the existing one-shot `kind: anthropic` AgentTool delegation. Scope (v1.0): - Sync only. `message` blocks until the session's turn completes. - In-memory `SwarmManager` singleton; sessions die with the process. - Single discriminated `swarm` tool with `action: spawn | message | release | list`. Zod-backed discriminated union. - Read-only tool whitelist by default (`read_file`, `grep_search`, `glob`, `list_directory`, `read_many_files`); per-spawn `tools` override allowed. - Session abort bound to `Config.getAppAbortSignal()` (SIGINT / process exit), NOT the orchestrator turn signal — ending an orchestrator turn does not kill the swarm. - 30-minute idle TTL with background sweep; sessions wedged in `running` past `2 * TTL` are aborted, marked `error`, and kept in `list()` for user debugging. - Feature-flagged off by default. The Anthropic message loop body from `AnthropicAgentInvocation` was extracted into `anthropic-loop.ts` so both the v1 single-shot path and the new long-lived `SwarmSession` share the same tool-use machinery. Design + reviews: - Multi-turn design discussion: `design-loop/swarm-design.md` (Claude + Gemini, Turns 0-4 + Final Synthesis with the locked v1.0 acceptance E2E). - Phase 1 reviews: `design-loop/phase1-review-opus.md`, `design-loop/phase1-review-gemini.md`. - Phase 2 reviews: `design-loop/phase2-review-opus.md`, `design-loop/phase2-review-gemini.md`. Phase 2 review items addressed in this commit: - Gemini #1: TTL sweep no longer deletes stuck-RUNNING sessions — they're aborted + marked ERROR + kept in `list()`. - Opus #1/#3: per-session app-abort listeners now have a disposer that fires from `SwarmSession.release()` and from the TTL-stuck path; no more unbounded listener accumulation across spawn/release cycles. - Opus #2: `appAbortDisposers` (Config) and `appAbortDisposer` (SwarmManager) are nulled out after firing for clarity. - Opus #4: `lastActiveAt` is stamped on RUNNING entry so a legitimate 35-minute turn is not misjudged "stuck" by the 2 * TTL sweep. Acceptance gate: - The locked stateful-continuity E2E is in `packages/core/src/agents/swarm/swarm-continuity.test.ts`. It intercepts the Anthropic SDK at the module boundary and asserts that the THIRD `messages.create` call (Agent A's second turn) sees the prior user+assistant turns in its `messages` array. If session statelessness regresses (e.g. someone resets `messages = []`), the test fails. Validation gates passed: - `npm run typecheck` (all workspaces) - `node scripts/lint.js --eslint` - `node scripts/lint.js --prettier` - `npm run build --workspace=packages/core` - `npm run build --workspace=packages/cli` - `npx vitest run packages/core/src/agents/` (753 passed) - `npx vitest run packages/core/src/agents/swarm/` (18 passed) Deferred to v1.1+ (per the synthesis): - `async: true` spawn + `poll` / `await` actions. - Shared workspace dir at `~/.gemini/swarm/<session_id>/work/`. - Budget guardrails (`max_spend_usd`, `max_total_tokens`). - Cross-process persistence. - Haiku worker reintegration (user policy default stands). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

…overy Closes the gap between v1.0's "process pool of single-shot workers" and the intended "stateful collaborator team with smart orchestrator" model. R3-locked design after a three-round multi-model debate (see design-loop/), then implemented and put through an Opus + Gemini reviewer loop before commit. Area 1 — `role` / `charter`. Optional short labels (≤80 / ≤200 chars) on `spawn` that flow through the Zod schema, JSON tool schema, session params, `list()`, and the new `swarm_status` snapshot. They also get woven into the session's composed system prompt so the sub-agent knows what hat it's wearing without the orchestrator having to repeat itself in every message. Area 2 — `message_turn_cap_reached` status. Hitting `max_turns` no longer appends a `[Note: hit max_turns=N.]` suffix and silently returns; it's now a first-class outcome. `runAnthropicMessageLoop` returns `{ text, capReached: boolean }`. `SwarmResult.message` splits into: - `status: 'ok' | 'message_turn_cap_reached'` — message outcome - `session_status: SwarmSessionStatus` — session lifecycle (idle/running/ released/error) Cap-reached is a normal IDLE return; the session lives. The single-shot anthropic-invocation path is bit-compatible (silently drops `capReached`). Area 3 — Plan-mode tool filter. `SWARM_BLOCKED_TOOL_NAMES` (containing `ENTER_PLAN_MODE_TOOL_NAME` / `EXIT_PLAN_MODE_TOOL_NAME` imported directly from `tool-names`) is applied in the per-tool clone loop, so both inherit-all and explicit `tools: [...]` paths drop mode-control tools. Closes the host-CLI-state-escalation hole the user surfaced in the Phase 4 live test where a sub-agent inherited `exit_plan_mode` and burned its turn budget trying to escape Plan Mode. Area 4 — `swarm_status` companion tool. New `swarm-status-tool.ts` (`Kind.Other`, no args, no confirm) that calls `SwarmManager.getSwarmStatusSnapshot()`. The snapshot exposes every live session's `role` / `charter` / `status` / `turn_count` / `seconds_since_active`, the shared `workspace_dir`, and a newest-first `recent_events[]` ring (50 entries, fed by `publishActivity`). Sub-agents are deliberately handed this read-only window — the verb surface (`swarm spawn/message/release`) stays orchestrator-only behind `Kind.Agent`. Area 5 — auto system-prompt block + default tool. `SWARM_PROTOCOL_BLOCK` is woven into `composedSystemPrompt` between the tool advertisement and the soft-reject suffix; it tells the sub-agent it's in a swarm, to call `swarm_status()` for peer context, and to append a `[<agent_id> @ <ts>]` line to `<workspace_dir>/state.md` after substantive work. `swarm_status` is appended to `DEFAULT_SWARM_TOOLS` and auto-injected on the inherit-all path (explicit lists are respected). Area 6 — SKILL.md adds four sections covering self-discovery via `swarm_status`, the `state.md` convention, "release on role-exhaustion, not task-completion", and cap-handling. CLAUDE.md's Swarm section is updated for the v1.0.x shape. Tests (6 mandated, all present and exercising the real surface, not theater): - Plan-mode filter regression with explicit list - role/charter round-trip through list() + swarm_status snapshot - cap-reached returns IDLE session_status, turnCount still increments - `getSwarmStatusSnapshot` agents[] + recent_events ordering - composed system prompt contains protocol block + role + charter - anthropic-loop `{ capReached: true }` shape on max_turns Post-review tweaks (Opus #2/#3 follow-ups, addressed before commit): - SWARM_BLOCKED_TOOL_NAMES now references the tool-name constants directly (no drift if those tools are ever renamed) - SWARM_STATUS_TOOL_NAME hoisted to types.ts as single SoT; swarm-manager and swarm-status-tool both import from there (cycle-free) Out of scope (deferred per user): - agent-memory MCP integration (v1.2+; RAG-style retrieval + write-back) - Persistent .events.jsonl on disk (v1.1+; current ring is in-memory only, consistent with "sessions die with parent CLI" policy) - `callerAgentId` resolution from MessageBus name (v1.1; today every sub-agent sees `self_agent_id: undefined`, which is benign) Rejected design directions (recorded in design-loop/swarm-model-r*.md): - `SwarmArchetype` registry + `catalog()` action (Gemini R1 → moved off in R2) - `since_last_turn` / `context_update` orchestrator-push fields (user redirection in R3: "공유 메모리 + self-discovery 방향으로") - `suggest_release` hint from sub-agent (user: "안 넣으면 문제 되는 명확한 시나리오 안 보이면 빼자") Validation: npm run typecheck — pass node scripts/lint.js --eslint — pass node scripts/lint.js --prettier — pass for staged files npm run build --workspace=packages/core — pass npm run build --workspace=packages/cli — pass npx vitest run packages/core/src/agents/ — 766 passed / 1 skipped npx vitest run packages/core/src/scheduler — 146 passed npx vitest run packages/core/src/policy — 326 passed (2 pre-existing topic-policy failures unrelated to this commit; verified clean on f114440 before this work) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Closes a real UX gap surfaced in the user's live testing: the orchestrator (Gemini model) doesn't naturally reach for the `swarm` tool, even when registered, even with explicit prompt steering. It falls back to `run_shell_command` and tries `gemini swarm ...` recursively. The fork ships substantial swarm + policy machinery already (Phases 4–6), but the model-side disposition layer was missing. R1/R2 multi-model design debate (Opus + Gemini in parallel, two rounds) settled the design at `design-loop/swarm-orchestrator- disposition.md`. After implementation, a six-reviewer pass (three angles — TS/clean-code, intent, tests/abstractions — each with one Opus + one Gemini reviewer) ran in parallel; all six returned SHIP or SHIP-WITH-FOLLOW-UP. Cheap follow-ups are addressed in this commit; the rest are noted in the design doc and the agent-memory entry for v2 pickup. Four layers, all gated on `Config.isSwarmEnabled()` so upstream non-swarm users see zero behavior change: 1) Tool description rewrite (~+150 tokens). `SWARM_TOOL_DESCRIPTION` and `SWARM_STATUS_TOOL_DESCRIPTION` now carry explicit "when to use" + the anti-pattern "DO NOT shell out to `gemini` — there is no `gemini swarm` verb." Drift-guard tests pin the anti-pattern phrasing so accidental rewording regresses behavior loudly. 2) Orchestrator system-prompt disposition block + single inline worked example (~+300 tokens, conditional). New `SwarmDispositionOptions` + `renderSwarmDisposition` in `prompts/snippets.ts`. Inserted between `renderSubAgents` and `renderAgentSkills` in `getCoreSystemPrompt`. `promptProvider.ts` gates on `(SWARM_TOOL_NAME ∨ SWARM_STATUS_TOOL_NAME) ∈ registered tools` AND `isSwarmEnabled()`. The block names the tool, flags the no-CLI-verb anti-pattern, references `swarm_status`, and embeds one `<example>` showing a `swarm spawn` call. The example is inline rather than separate so in-context proximity isn't diluted by intervening prompt sections. 3) `swarm-collaboration` skill auto-inline (~+1.6k tokens, only when swarm enabled). `promptProvider.ts` filters the skill out of the regular `<available_skills>` manifest and inlines its SKILL.md body via new `renderSwarmInline`. Removes the activate-skill indirection so the protocol (state.md convention, release rules, paste-verbatim discipline) lands in the orchestrator's context without an extra round-trip. Hardcoded for the single fork-builtin inline candidate; an `inline: boolean` metadata flag was explicitly rejected in R2 (YAGNI; the LOCKED v2 north star reserves the capability/ template data-model surface). 4) Runtime guard — tier-1 default-deny `PolicyRule`. Registered from `config.ts` inside the existing `isSwarmEnabled()` tool- registration block. Pattern matches the JSON-stringified args form (`stableStringify(toolCall.args)`), NOT raw shell text — that ground-truth correction was caught in R2 when both models independently traced `PolicyEngine.matchRule` and found the raw-shell prototype from R1 would silently never match. The correct shape is `/"command":"(gemini|gemini-fork)(\s|"|\\)/`; the policy engine's existing sub-command splitter (`policy-engine.ts:469-475`) handles `bash -c "gemini foo"` and `cd /tmp && gemini ...` via recursive `check()`. The deny message carries the redirect text. `tier-4` user policies can still override. Review-cycle fixes folded in before commit: - Legacy snippets gap (Opus angle 1 #1): `snippets.legacy.ts` now imports the Phase 8 option types and renderers from `snippets.ts` and wires them into legacy `getCoreSystemPrompt`, so Gemini 2.x orchestrators with swarm enabled get the disposition block too. The disposition fix matters more for older models with stronger shell-first priors, not less. - Misleading test narration (Opus angles 2 + 3, cross-flagged): `policy-engine.test.ts` comment for the `bash -c "gemini help"` case had the wrong mechanism. The DENY actually fires via the sub-command splitter recursing into the inner `gemini help`, not the JSON-escape `(\\)` alternative at the top level. Corrected. - `swarm_status`-only branch test gap (Opus angle 3): added a case proving the disposition AND auto-inline both fire when only `SWARM_STATUS_TOOL_NAME` is registered (sub-agents themselves get `swarm_status` without `swarm` per the recursion-guard filter in `swarm-manager.ts`). - Empty-body edge case (Gemini angle 3): `renderSwarmInline` now returns `''` for whitespace-only bodies so a future skill loader returning an empty string doesn't render a dangling `# Skill — <name> (auto-loaded)` header with no content. Test added. Non-blocking review findings deferred to follow-ups (recorded in the design doc / agent-memory entry): - `SWARM_TOOL_NAME` SoT split (Opus angle 1 #3, Gemini angle 1): `SWARM_STATUS_TOOL_NAME` lives in lightweight `agents/swarm/ types.ts`, while `SWARM_TOOL_NAME` is still in heavy `swarm-tool.ts`. Consolidating both into the central `tools/tool-names.ts` is a separate cleanup. - Phase 8 prompt fields bypass `withSection` (Opus angle 1 #2): the operator `GEMINI_PROMPT_<KEY>=0` mute knob doesn't apply to the new sections. Routing through `withSection` is a separate consistency fix. - Layer 4 brittleness on `stableStringify` (Gemini angle 2): the argsPattern coupling to the policy engine's stringify format is a structural smell. A dedicated structured-arg matcher in the policy engine is a v2-level improvement. Tests landed (11 new): - `policy-engine.test.ts`: JSON-shape pattern denies `gemini …`, `gemini-fork …`, and `bash -c "gemini help"` (via recursive splitter); passes through `ls -la` and `echo gemini`. - `swarm-tool.test.ts`: anti-pattern drift guards on both tool descriptions. - `promptProvider.test.ts`: disposition block on/off; auto- inline pulled out/in manifest; only-`swarm_status` branch fires both layers; `renderSwarmInline` empty-body returns ''. - `config.test.ts`: tier-1 deny rule registered iff swarm enabled; carries the expected `source`, `toolName`, `decision`, `argsPattern` shape, and `denyMessage`. Gates: npm run typecheck — pass node scripts/lint.js --eslint — pass node scripts/lint.js --prettier — pass for staged files; design-loop docs auto-formatted by pre-commit hook npm run build --workspace=packages/core — pass npm run build --workspace=packages/cli — pass npx vitest run packages/core/src/policy/ — 330/332 (the 2 pre-existing topic-policy.test.ts failures, unrelated, verified on parent commit f190547) npx vitest run packages/core/src/agents/swarm/ — 36/36 npx vitest run packages/core/src/prompts/ — 65/65 Files committed include the LOCKED design doc (`design-loop/swarm-orchestrator-disposition.md`) and the `.gitignore` exception that tracks it (alongside `swarm-north-star.md`). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

rakyll requested a review from NTaylorMullen April 17, 2025 19:03

NTaylorMullen requested changes Apr 17, 2025

View reviewed changes

Comment thread packages/cli/src/tools/edit.tool.ts Outdated

rakyll force-pushed the core branch from f6867fb to 04a02b4 Compare April 17, 2025 21:00

Revert camelCasing for schemas

0f9fd68

NTaylorMullen approved these changes Apr 17, 2025

View reviewed changes

NTaylorMullen merged commit ece8630 into main Apr 17, 2025

rakyll deleted the core branch April 21, 2025 23:27

srithreepo mentioned this pull request Jun 26, 2025

gemini-2.5-pro is [API Error: got status: 429 Too Many Requests. #1502

Closed

yewenchen pushed a commit to yewenchen/gemini-cli that referenced this pull request Jul 8, 2025

custom ContentGenerator for SiliconFlow (google-gemini#2)

c37a30f

z23cc pushed a commit to z23cc/opengemini-cli that referenced this pull request Jul 10, 2025

Merge pull request google-gemini#2 from frinkleko/azure-api-support

d91f42c

feat: Azure api support

hymjay0 added a commit to hymjay0/gemini-cli that referenced this pull request Jul 12, 2025

Add SSO client integration and Bearer token support for enterprise en…

80f03cb

…vironments google-gemini#2

gracemann365 mentioned this pull request Jul 15, 2025

Gemini Cli is a Goldmine ; She will be World’s #1 Coding Agent #4267

Closed

akabarki76 mentioned this pull request Jul 28, 2025

Security Enhancements: Policy Documentation, Automation & Alert Fixes #5049

Closed

DinoChiesa mentioned this pull request Aug 8, 2025

Gemini CLI is not performing environment variable substitution for MCP Servers #5828

Closed

Enlight432 mentioned this pull request Sep 14, 2025

Decouple Checkpointing from Manual Approval to Allow Safe Auto-Approval Workflows #8436

Closed

timothyfroehlich mentioned this pull request Sep 18, 2025

When including multiple directories, @'ing a directory seems to pull in directories that match in all included directories #8748

Closed

cbcoutinho mentioned this pull request Oct 23, 2025

Improve Authorization server well-known metadata URL construction. #10512

Closed

aka76bm referenced this pull request in aka76bm/gemini-cli Oct 29, 2025

Merge pull request #2 from start-export-MA/dependabot/npm_and_yarn/np…

9b68675

…m_and_yarn-fd296dbd23 chore(deps): bump vite from 7.1.9 to 7.1.11 in the npm_and_yarn group across 1 directory

This was referenced Nov 28, 2025

feat: Implement script output summarization and refine image routing #14097

Closed

feat: Script Output Summarization #14098

Closed

bniladridas mentioned this pull request Sep 28, 2025

Fix clipboard utils test to match settings structure palmshed/geminicli#1

Closed

Vivekgupta008 mentioned this pull request Jan 10, 2026

refactor: prepare extension loading for parallelization #16314

Closed

gemini-code-assist Bot mentioned this pull request Mar 2, 2026

🤖 Add Copilot SDK Expert Agentic Workflow matheus-rech/gemini-cli#1

Open

This was referenced Mar 6, 2026

feat(a2a): enable native gRPC support and protocol routing #21403

Merged

feat(a2a): implement secure acknowledgment and core registry improvements #21404

Closed

SandyTao520 mentioned this pull request Mar 7, 2026

fix(core): add in-memory cache to ChatRecordingService to prevent OOM #21502

Merged

18 tasks

jacob314 mentioned this pull request Mar 10, 2026

feat(ui): implement refreshed UX for Composer layout #21212

Merged

4 tasks

PeterWadie mentioned this pull request Mar 11, 2026

feat(evals): add behavioral eval for error recovery and self-correction #21990

Open

TraceNChase mentioned this pull request Mar 19, 2026

Gemini-3.1-Pro-Preview Keeps Running but Never Completes the Task : This is taking a bit longer, we're still on it. #23097

Open

my-local-agent Bot mentioned this pull request Mar 24, 2026

Fix: Memory leak in Scheduler and improve error handling ponyfly6/gemini-cli#1

Open

github-merge-queue Bot pushed a commit that referenced this pull request Apr 7, 2026

Revert "fix(ui): improve narration suppression and reduce flicker (#2… (

f96d5f9

#24857)

warrenzhu25 pushed a commit to warrenzhu25/gemini-cli that referenced this pull request Apr 9, 2026

Revert "fix(ui): improve narration suppression and reduce flicker (go…

5431b17

…ogle-gemini#2… (google-gemini#24857)

This was referenced Apr 15, 2026

docs: Fix 4 broken links in docs/CONTRIBUTING.md - . ☆ ' ( #25487

Closed

docs: Fix 4 broken links in docs/CONTRIBUTING.md #25488

Closed

sanchaysaxena mentioned this pull request Apr 16, 2026

Gemini CLI returns opaque 403 "The caller does not have permission" for Enterprise users #25512

Closed

SkybuckFlying mentioned this pull request Apr 20, 2026

Gemini‑CLI: Excessive project‑wide scanning makes simple code patches fail #25672

Open

This was referenced Apr 22, 2026

fix: Add isRespondingRef for synchronous blocking and await the retry #20261

Closed

test: add validation tests for esbuild and eslint config files #19866

Closed

martin-mirantes mentioned this pull request Apr 23, 2026

[Bug] Multiple sequential edits to the same file are lost - only the last one persists (after fix #8513) #25868

Open

sripasg added the size/l A large sized PR label Jun 2, 2026

aarongarciauk-del mentioned this pull request Jun 2, 2026

despite explicit instructions to be passive and make no changes gemini made lots of changes. #27618

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Improve readability issues#2

Improve readability issues#2
NTaylorMullen merged 2 commits into
mainfrom
core

rakyll commented Apr 17, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

rakyll commented Apr 17, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants