chore(claude-code)!: strip boundary, agentapi, tasks, tools by matifali · Pull Request #861 · coder/registry

matifali · 2026-04-22T16:43:58Z

Summary

Reduces claude-code to a minimal install-and-configure module for the Claude CLI. Boundary, agentapi, task reporting, session tracking, tool allow/deny, and start orchestration are removed. Script execution is delegated to coder-utils v1.2.0. Starting Claude is now the caller's responsibility (template command, IDE launcher, or a custom coder_script).

Warning

This is a breaking change. See the migration guide below.

Changes

Delete scripts/start.sh. The module no longer launches Claude.
Replace the agentapi sub-module with coder-utils v1.2.0 for install/pre/post script orchestration.
Remove Boundary install, agentapi install, task reporting, session tracking, and tool allow/deny logic.
Remove the npm installation path. The module now always uses the official claude.ai/install.sh installer.
Render scripts/install.sh.tftpl once at plan time via templatefile() and pass the result directly to coder-utils, replacing the runtime base64 encode/decode wrapper and the redundant scripts/install.sh.
Make workdir optional. When set, the module pre-creates the directory and pre-accepts the Claude Code trust dialog for it. When unset, the module installs the CLI and configures authentication only; users accept trust dialogs interactively per project.
Scope MCP servers to Claude Code's user scope via claude mcp add-json --scope user so they are available across every project the workspace owner opens, instead of being tied to a single project directory.
Drop primaryApiKey from the standalone-mode config writer — credentials are already exported via coder_env, writing the key into ~/.claude.json had no effect.
Rename variable claude_api_key → anthropic_api_key (env ANTHROPIC_API_KEY).
Rename variable enable_aibridge → enable_ai_gateway.
AI Gateway now sets ANTHROPIC_AUTH_TOKEN (not ANTHROPIC_API_KEY) to the workspace owner's Coder session token, matching the AI Gateway centralized API key flow.
Fix configure_standalone_mode to also recognize CLAUDE_CODE_OAUTH_TOKEN so OAuth-only users get the onboarding bypass.
Add scripts output (pass-through from coder-utils) so upstream modules can serialize their coder_script resources behind this module's install pipeline via coder exp sync want.
Remove the task_app_id output.
Module logs now live at $HOME/.coder-modules/coder/claude-code/logs/ (was $HOME/.claude-module/).
Drop variables: report_tasks, system_prompt, claude_md_path, allowed_tools, disallowed_tools, enable_boundary, boundary_version, compile_boundary_from_source, use_boundary_directly, order, group, web_app, cli_app, web_app_display_name, cli_app_display_name, install_agentapi, agentapi_version, ai_prompt, subdomain, resume_session_id, continue, dangerously_skip_permissions, enable_state_persistence, permission_mode, install_via_npm.
README: reorder sections (migration warning → prerequisites → workdir → examples), add v4 migration warning with links to Coder Tasks and Boundary docs, move MCP scope note inline with the advanced config example, bump version references to 5.0.0.

Breaking Changes

Before	After
`claude_api_key`	`anthropic_api_key`
`enable_aibridge`	`enable_ai_gateway`
AI Gateway set `ANTHROPIC_API_KEY` to session token	AI Gateway sets `ANTHROPIC_AUTH_TOKEN` to session token
`workdir` required	`workdir` optional
MCP servers scoped to project directory	MCP servers scoped to user (available across all projects)
`module.claude-code.task_app_id`	removed (no `coder_app` created)
`permission_mode`	removed (pass via your own start script)
`install_via_npm`	removed (module always uses the official installer)
`ai_prompt`, `system_prompt`, `allowed_tools`, `disallowed_tools`, `report_tasks`, session/continue vars, Boundary vars, agentapi vars, `web_app`/`cli_app` vars, `order`/`group`, `enable_state_persistence`	removed
`$HOME/.claude-module/*.log`	`$HOME/.coder-modules/coder/claude-code/logs/*.log`

Callers depending on any of the above must migrate. The module no longer starts Claude — provide your own coder_script or template command if you want it to launch automatically.

Validation

terraform fmt -recursive clean
terraform validate clean
terraform test → 13/13 pass
bun test registry/coder/modules/claude-code → 12/12 pass
shellcheck --severity=warning clean
prettier --check clean

🤖 This PR was created with the help of Coder Agents, and needs a human review. 🧑‍💻

…tasks, tools - Remove boundary variables and install logic. - Drop agentapi module; orchestrate scripts through coder-utils instead. - Remove start-script-only variables not shared with install (resume_session_id, continue, ai_prompt, dangerously_skip_permissions). - Remove allowed_tools and disallowed_tools. - Remove report_tasks, system_prompt, claude_md_path, and coder exp mcp / coder_report_task wiring. - Rename claude_api_key to anthropic_api_key (ANTHROPIC_API_KEY). - Rename enable_aibridge to enable_ai_gateway. - Drop install_via_npm; always use the official claude.ai/install.sh installer. - Tighten workdir description and drop dead module_dir_name/task_app_id. - Move module logs to $HOME/.coder-modules/coder/claude-code/logs (matches coder-utils 1.3.0 nested layout).

…le_directory (#874) ## Summary Derives `coder-utils` script names from `module_directory` instead of a separate `agent_name` input. The `module_directory` already encodes both the namespace and the module name, so carrying both is redundant and error-prone. Callers like `claude-code` no longer need to pass `agent_name`. Scripts this module materializes lose the `${agent_name}-utils-` prefix because `module_directory` already namespaces them per-caller. We will address multiple instances of coder-utils per caller in a future iteration if needed. ## Versioning Note Previous tags (`v1.0.0` through `v1.3.0`) have been deleted because no published module ever consumed them — the module was effectively unreleased. This PR ships the first real public version as **`v0.0.1`**, treating it as a fresh start rather than a breaking bump from a version that was never in production use. ## Changes - Remove `agent_name` variable. - Derive `caller_name = "${namespace}-${module_name}"` from `module_directory`. - Validate `module_directory` matches `$HOME/.coder-modules/<namespace>/<module-name>`. - Rename script files on disk from `${agent_name}-utils-<phase>.sh` to plain `<phase>.sh`. - Add a TS test for the `module_directory` validation. - Ship as `v0.0.1` (first published version; all prior tags removed). ## Breaking Changes | Before | After | |---|---| | `agent_name = "myagent"` | removed (derived from `module_directory`) | | `module_directory = ".my-module"` | `module_directory = "$HOME/.coder-modules/<ns>/<name>"` (validated) | | Script files `${agent_name}-utils-install.sh` | `install.sh` | | Script sync names `${agent_name}-install_script` | `${namespace}-${module_name}-install_script` | No callers were depending on the old format (prior tags were unpublished). ## Validation - `terraform fmt -recursive` clean - `terraform validate` clean - `terraform test` → 17/17 pass - `bun test registry/coder/modules/coder-utils` → 5/5 pass - `prettier --check` clean ## Consumer #861 (`claude-code`) consumes this and is currently pinned to the commit SHA until this merges and ships as `v0.0.1`. > 🤖 This PR was created with the help of Coder Agents, and needs a human review. 🧑‍💻

…ia templatefile Render scripts/install.sh.tftpl once at plan time and pass the result directly to coder-utils, replacing the runtime base64 encode/decode wrapper and the redundant scripts/install.sh. Sources coder-utils from a pinned commit on its refactor branch until the `module_directory`-derived caller name lands in a tagged release.

…nd scope MCP to user workdir is now optional. When set, the module still pre-creates the directory and pre-accepts the Claude Code trust dialog for it. When unset, the module installs the CLI and configures authentication only; users accept trust dialogs interactively per project. MCP servers are added at Claude Code's user scope via `claude mcp add-json --scope user` so they are available across every project the workspace owner opens, instead of being tied to a single project directory. For project-local MCP servers, callers should commit a `.mcp.json` to the project repository rather than passing it through this module. Drop primaryApiKey from the standalone-mode config writer. Claude Code reads credentials from the ANTHROPIC_API_KEY and CLAUDE_CODE_OAUTH_TOKEN env vars (which the module already exports via coder_env); writing the key into ~/.claude.json had no effect on authentication. Split the standalone-mode .claude.json writer into two steps: the always-on auth/onboarding keys, and the optional `.projects[workdir]` trust block that only runs when workdir is set.

35C4n0r

LGTM!

DevelopmentCats

Everything looks good to me. I think it honestly makes more sense for this module to stick with just the claude-code install and configuration since everyone seems to have their own methods of utilizing the module, and with /agents we would be moving away from tasks anyways to some extent.

…igration warning

… attribution Rebased onto post-coder#861 main. Adds a typed telemetry input that turns on CLAUDE_CODE_ENABLE_TELEMETRY and the standard OTEL_EXPORTER_OTLP_* env vars in one place, and auto-injects coder.workspace_id, coder.workspace_name, coder.workspace_owner, and coder.template_name into OTEL_RESOURCE_ATTRIBUTES so Claude Code spans and metrics can be joined directly with Coder audit logs and exectrace records on workspace_id without per-template wiring. Bumps README examples to 5.1.0.

… /etc/claude-code Re-authored on top of the post-coder#861 install-only module. Adds a managed_settings variable that the install script writes to /etc/claude-code/managed-settings.d/10-coder.json. Claude Code reads this drop-in directory at startup with the highest configuration precedence, so template authors get an admin-controlled policy file that users inside the workspace cannot override. The mechanism is a local file read with no API call, so it works identically for the Anthropic API, AWS Bedrock, Google Vertex AI, and AI Gateway. Compared to the original PR against v4.x, this drops the deprecation shim for permission_mode/allowed_tools/disallowed_tools (those vars are gone in v5) and the start.sh changes (start.sh is gone). The ~/.claude.json policy-key removal is also dropped from this PR scope since the surrounding configure_standalone_mode logic changed substantially in coder#861; can revisit separately if wanted.

…rk anthropic_api_key sensitive Rebased onto post-coder#861 main. Changes from the original PR: - Targets the renamed anthropic_api_key variable (was claude_api_key). - Targets the renamed enable_ai_gateway variable (was enable_aibridge). - The primaryApiKey removal from the original PR is no longer needed since coder#861's install template does not write that key. - install.sh.tftpl uses templatefile substitution; helper script is passed base64-encoded as ARG_API_KEY_HELPER_SCRIPT. - README bumped to 5.1.0.

…ertex inputs Rebased onto post-coder#861 main. - New use_bedrock and use_vertex bool inputs that set CLAUDE_CODE_USE_BEDROCK=1 / CLAUDE_CODE_USE_VERTEX=1 via coder_env. Mutually exclusive with each other and with enable_ai_gateway. - New anthropic_base_url string input. The existing coder_env.anthropic_base_url resource (previously AI Gateway only) is widened to also fire when this is set; AI Gateway keeps precedence for the value. Mutually exclusive with enable_ai_gateway. - configure_standalone_mode now recognizes use_bedrock / use_vertex / anthropic_base_url as valid auth paths: prints a clear backend message and proceeds to write the onboarding-bypass keys instead of printing the misleading 'No authentication configured' note and returning early. - README: Bedrock and Vertex sections rewritten around the new inputs, leading with attached IAM role / Workload Identity over static credentials. New custom-API-gateway section. Prerequisites and mutual-exclusion caution updated. - Tests: 7 new terraform-test runs (env assertions + 4 expect_failures for mutual exclusion); 3 new bun tests. Closes coder/coder#17402 Closes coder/coder#21835

…entinel Re-authored on top of coder#861. The original PR also fixed the hardcoded TASK_SESSION_ID in start.sh (coder#726); coder#861 removed start.sh entirely so that fix is no longer needed and coder#726 is resolved by coder#861 itself. What remains is install-time: - transcript_retention_days input maps to Claude Code's cleanupPeriodDays setting via a managed-settings.d drop-in so long-lived workspaces do not accumulate unbounded session JSONL. - A Stop hook touches ~/.coder-modules/coder/claude-code/last-stop on every turn end so templates can drive workspace autostop or activity tracking off that file's mtime. Both are written to /etc/claude-code/managed-settings.d/30-coder-lifecycle.json, which the Claude CLI reads regardless of inference backend.

… attribution (#862) ## Problem Claude Code ships an OpenTelemetry exporter for token usage, tool calls, session lifecycle and errors (https://docs.anthropic.com/en/docs/claude-code/monitoring-usage), but the module exposes no first-class wiring for it. Template authors who want telemetry have to know the env var names (`CLAUDE_CODE_ENABLE_TELEMETRY`, the `OTEL_EXPORTER_OTLP_*` family) and write their own `coder_env` blocks. More importantly there is no convention for how to correlate Claude Code telemetry with Coder's own audit logs and `exectrace` records, so even when both are exported they end up as two unjoined datasets. ## Change Adds a `telemetry` input that turns on `CLAUDE_CODE_ENABLE_TELEMETRY` and the standard OTLP exporter env vars in one place: ```tf telemetry = { enabled = true otlp_endpoint = "http://otel-collector.observability:4317" otlp_protocol = "grpc" otlp_headers = { authorization = "Bearer ..." } resource_attributes = { "service.name" = "claude-code" } } ``` When enabled, the module automatically appends `coder.workspace_id`, `coder.workspace_name`, `coder.workspace_owner` and `coder.template_name` to `OTEL_RESOURCE_ATTRIBUTES`. This gives a stable join key between Claude Code spans/metrics and Coder's audit log and exectrace events on `workspace_id`, so a platform team can answer "show me every shell command Claude executed in workspace X alongside the token spend for that session" without custom plumbing. This is purely additive (`coder_env` resources behind `count`), defaults to disabled, and is independent of how Claude is launched, so it composes cleanly with the install-only direction in #861. ## Validation - `terraform fmt`, `terraform validate`, `terraform test` (19/19) pass - `bun test -t telemetry` (2/2) pass: env vars are set with the expected values when enabled, and absent when the input is omitted Disclosure: I work at Anthropic on the Claude Code team. --------- Co-authored-by: DevCats <chris@dualriver.com> Co-authored-by: Atif Ali <me@matifali.dev>

…and start logic (#879) Closes #878 ## What Major refactor of the `coder-labs/codex` module to mirror the `coder/claude-code` v5 changes from #861. ## Changes ### Structural - Replace `module "agentapi"` with `module "coder_utils"` (`registry.coder.com/coder/coder-utils/coder v0.0.1`) - Replace `scripts/install.sh` with `scripts/install.sh.tftpl` (Terraform templatefile) - Delete `scripts/start.sh` - Module dir changed from `.codex-module` to `.coder-modules/coder-labs/codex` - Output changed from `task_app_id` to `scripts` (ordered list of coder exp sync names) - Extracted shared test helpers (`collectScripts`, `runScripts`) into `agentapi/coder-utils-test-helpers.ts` ### Removed variables All AgentAPI pass-throughs, boundary, and start-script-only variables: `order`, `group`, `report_tasks`, `subdomain`, `cli_app`, `web_app_display_name`, `cli_app_display_name`, `install_agentapi`, `agentapi_version`, `ai_prompt`, `continue`, `enable_state_persistence`, `codex_system_prompt`, `enable_boundary`, `boundary_config_path`, `boundary_version`, `compile_boundary_from_source`, `use_boundary_directly`, `codex_model` ### Retained `install_codex` (toggle for skipping npm install when CLI is pre-installed) ### Renamed - `enable_aibridge` -> `enable_ai_gateway` ### Changed - `workdir`: now optional (`default = null`) - `openai_api_key`: conditional env var with `count`, marked `sensitive = true` - `base_config_toml`: heredoc description documenting generated defaults; notes that `model_reasoning_effort` and workdir trust are only applied in default config - Default `config.toml`: stripped `sandbox_mode`, `approval_policy`, `sandbox_workspace_write`, `notice.model_migrations` - Install script: removed Node.js/NVM bootstrap (assumes npm pre-installed), sources NVM if present, fails with actionable error if npm missing - `ARG_CODEX_VERSION` and `ARG_WORKDIR` base64-encoded to prevent shell/TOML injection - Duplicate `[model_providers.aibridge]` guarded with grep before appending - Debug header uses user-facing variable names ### Tests - Terraform: 11 pass - Bun: 15 pass (rewritten to shared `collectScripts`/`runScripts` pattern) - Added: `model-reasoning-effort-standalone`, `ai-gateway-with-custom-base-config`, `ai-gateway-custom-config-no-duplicate-provider`, `install-codex-latest`, `workdir-trusted-project`, `no-workdir-no-project-section` - Negative assertions on `minimal-default-config` ### Docs - Migration guide (v4 to v5) in README - Quoted path in coder_app example - AI Gateway note about custom `base_config_toml` requiring manual `model_provider` > [!WARNING] > Breaking change. Drops support for Coder Tasks and Boundary. Keep using v4.x.x if you depend on them. --- *This PR was authored by Coder Agents.* --------- Co-authored-by: Jay Kumar <jay.kumar@coder.com> Co-authored-by: DevCats <christofer@coder.com>

…ude-code v5 (#885) Aligns codex module variable names with the claude-code v5 conventions established in #861 and #879. - Rename `additional_mcp_servers` to `mcp` to match claude-code's variable name. - Change `codex_version` default from `""` to `"latest"` to match `claude_code_version`. ## Type of Change - [ ] New module - [ ] New template - [x] Bug fix - [ ] Feature/enhancement - [ ] Documentation - [ ] Other ## Module Information **Path:** `registry/coder-labs/modules/codex` **Breaking change:** [x] Yes [ ] No > [!WARNING] > Breaking change for anyone referencing `additional_mcp_servers` by name. Since v5.0.0 was released and deleted on the same day (#879), this should have zero downstream impact. ## Testing & Validation - [x] Tests pass (`bun test`) - [x] Code formatted (`bun fmt`) - [x] Changes tested locally ## Related Issues - Follow-up to #879 - Filed #886 to track adding `mcp_config_remote_path` support to codex --- *This PR was authored by Coder Agents.*

… /etc/claude-code (#863) ## Problem The module configures Claude Code's permission posture by reaching around the permission system rather than through it: - `scripts/install.sh` writes `bypassPermissionsModeAccepted`, `autoModeAccepted`, and `primaryApiKey` directly into the user-writable `~/.claude.json`. Any process in the workspace can read the API key or flip the acceptance flags back. - `scripts/start.sh` adds `--dangerously-skip-permissions` to every task launch, even when the template author set an explicit `permission_mode`. The README has to carry a security warning telling people the module bypasses permission checks. - `permission_mode`, `allowed_tools`, and `disallowed_tools` each plumb through a different ad-hoc path (CLI flag, `coder` subcommand) instead of a single policy surface. ## Change Add a `managed_settings` input that renders to `/etc/claude-code/managed-settings.d/10-coder.json`. Claude Code reads that drop-in directory at startup with the highest configuration precedence (above `~/.claude/settings.json` and project settings), so template authors get an admin-controlled policy file that users inside the workspace cannot override. The mechanism is a local file read with no API call, so it works identically for the Anthropic API, AWS Bedrock, Google Vertex AI, and AI Bridge / AI Gateway. ```hcl managed_settings = { permissions = { defaultMode = "acceptEdits" disableBypassPermissionsMode = "disable" deny = ["Bash(curl:*)", "WebFetch"] } } ``` Supporting changes: - `install.sh` writes the policy file (root-owned, 0644) and stops writing `bypassPermissionsModeAccepted`, `autoModeAccepted`, and `primaryApiKey` into `~/.claude.json`. The API key is already exported via `coder_env` as `CLAUDE_API_KEY`; duplicating it on disk is unnecessary. `hasCompletedOnboarding` stays because there is no env-var alternative for it. - `start.sh` only adds `--dangerously-skip-permissions` for tasks when no explicit `permission_mode` is set (same fix as #846; included here so this PR is self-contained, happy to drop if #846 lands first). - `permission_mode`, `allowed_tools`, and `disallowed_tools` are marked deprecated and shimmed into `managed_settings.permissions` for one release when `managed_settings` is not provided. - README security warning rewritten to point at the policy mechanism instead of telling people the module is unsafe by design. ## Relationship to #861 #861 strips this module to install-and-configure and removes `permission_mode` / `allowed_tools` / `disallowed_tools` outright. `managed_settings` is the natural replacement for those: it is install-time (survives the `start.sh` removal), it covers everything the dropped variables did plus `hooks`, `env`, `model`, `apiKeyHelper`, and the rest of the settings schema, and it does not require the module to know anything about how Claude is launched. If #861 lands first I will rebase this on top and drop the deprecation shim and the `start.sh` hunk. ## Validation - `terraform fmt` / `terraform validate` clean - New tests: `claude-managed-settings-written`, `claude-managed-settings-legacy-shim`, `claude-no-policy-keys-in-claudejson`, plus an assertion in `claude-auto-permission-mode` that `--dangerously-skip-permissions` is absent when a mode is set - Manually verified `/etc/claude-code/managed-settings.d/*.json` precedence in the Claude Code CLI source Closes #818. Relates to #284, #846, #861. Disclosure: I work at Anthropic on the Claude Code team. Happy to adjust scope or split this further if that is easier to review. --------- Co-authored-by: DevCats <chris@dualriver.com> Co-authored-by: DevCats <christofer@coder.com>

…ertex inputs Rebased onto post-coder#861 main. - New use_bedrock and use_vertex bool inputs that set CLAUDE_CODE_USE_BEDROCK=1 / CLAUDE_CODE_USE_VERTEX=1 via coder_env. Mutually exclusive with each other and with enable_ai_gateway. - New anthropic_base_url string input. The existing coder_env.anthropic_base_url resource (previously AI Gateway only) is widened to also fire when this is set; AI Gateway keeps precedence for the value. Mutually exclusive with enable_ai_gateway. - configure_standalone_mode now recognizes use_bedrock / use_vertex / anthropic_base_url as valid auth paths: prints a clear backend message and proceeds to write the onboarding-bypass keys instead of printing the misleading 'No authentication configured' note and returning early. - README: Bedrock and Vertex sections rewritten around the new inputs, leading with attached IAM role / Workload Identity over static credentials. New custom-API-gateway section. Prerequisites and mutual-exclusion caution updated. - Tests: 7 new terraform-test runs (env assertions + 4 expect_failures for mutual exclusion); 3 new bun tests. Closes coder/coder#17402 Closes coder/coder#21835

…rk anthropic_api_key sensitive Rebased onto post-coder#861 main. Changes from the original PR: - Targets the renamed anthropic_api_key variable (was claude_api_key). - Targets the renamed enable_ai_gateway variable (was enable_aibridge). - The primaryApiKey removal from the original PR is no longer needed since coder#861's install template does not write that key. - install.sh.tftpl uses templatefile substitution; helper script is passed base64-encoded as ARG_API_KEY_HELPER_SCRIPT. - README bumped to 5.1.0.

matifali marked this pull request as ready for review April 22, 2026 16:45

matifali mentioned this pull request Apr 22, 2026

refactor(registry/coder/modules/claude-code): slim to install-and-configure only #859

Closed

matifali force-pushed the chore/claude-code-strip-boundary-agentapi-tasks branch 8 times, most recently from 92718d5 to 42ff02a Compare April 22, 2026 17:59

matifali requested review from 35C4n0r and evgeniy-scherbina and removed request for evgeniy-scherbina April 22, 2026 18:01

matifali changed the title ~~chore(claude-code): strip boundary, agentapi, tasks, tools~~ chore(claude-code)!: strip boundary, agentapi, tasks, tools Apr 22, 2026

matifali mentioned this pull request Apr 23, 2026

feat(coder-utils): nest logs under module_directory/logs #870

Merged

matifali requested a review from DevelopmentCats April 23, 2026 06:49

matifali mentioned this pull request Apr 24, 2026

refactor(registry/coder/modules/coder-utils)!: derive names from module_directory #874

Merged

matifali force-pushed the chore/claude-code-strip-boundary-agentapi-tasks branch 3 times, most recently from 3c9937a to 3885188 Compare April 24, 2026 11:19

matifali added 2 commits April 24, 2026 12:23

matifali force-pushed the chore/claude-code-strip-boundary-agentapi-tasks branch from 3885188 to 46ce616 Compare April 24, 2026 12:23

Merge branch 'main' into chore/claude-code-strip-boundary-agentapi-tasks

b13242e

35C4n0r approved these changes Apr 24, 2026

View reviewed changes

DevelopmentCats approved these changes Apr 24, 2026

View reviewed changes

docs(registry/coder/modules/claude-code): reorder README and add v4 m…

297d736

…igration warning

matifali merged commit 124d05f into main Apr 24, 2026
4 checks passed

matifali deleted the chore/claude-code-strip-boundary-agentapi-tasks branch April 24, 2026 15:56

matifali mentioned this pull request Apr 25, 2026

feat(claude-code): first-class anthropic_base_url, use_bedrock, use_vertex inputs #864

Open

This was referenced Apr 28, 2026

fix: added --type aider flag in agentapi #811

Draft

Codex module: MCP server subprocesses fail TLS verification when enable_boundary=true #801

Open

This was referenced Apr 29, 2026

refactor(codex): replace AgentAPI with coder-utils, align with claude-code v5 pattern #878

Closed

refactor(registry/coder-labs/modules/codex)!: remove agentapi, tasks and start logic #879

Merged

This was referenced May 5, 2026

fix(registry/coder-labs/modules/codex): align variable names with claude-code v5 #885

Merged

feat(codex): add mcp_config_remote_path support to match claude-code #886

Open

Harsh9485 mentioned this pull request May 14, 2026

refactor(registry/coder-labs/modules/gemini): remove agentapi, tasks, start script #890

Open

3 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

chore(claude-code)!: strip boundary, agentapi, tasks, tools#861

chore(claude-code)!: strip boundary, agentapi, tasks, tools#861
matifali merged 5 commits into
mainfrom
chore/claude-code-strip-boundary-agentapi-tasks

matifali commented Apr 22, 2026 •

edited

Loading

Uh oh!

35C4n0r left a comment

Uh oh!

DevelopmentCats left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

matifali commented Apr 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Changes

Breaking Changes

Validation

Uh oh!

35C4n0r left a comment

Choose a reason for hiding this comment

Uh oh!

DevelopmentCats left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

matifali commented Apr 22, 2026 •

edited

Loading