mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-06 10:48:12 +02:00
Devin FoleyandPaperclip
cdf04a33fa
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Its adapters supply model catalogs and reasoning controls to agent setup. > - Several provider releases are missing from the fallback catalogs. > - Some newer models also have effort levels that the UI does not offer. > - Operators need the exact supported IDs and controls when discovery is unavailable. > - This pull request updates the existing adapters from current provider documentation. > - Operators can select current coding models without entering custom IDs. ## Linked Issues or Issue Description **What existing behavior does this improve?** Model selection and reasoning controls across the existing coding-agent adapters. **Subsystem affected** Claude, Codex, Grok, Gemini, Cursor, Kimi, and OpenCode adapters; model discovery tests; agent creation and editing. **Current behavior** The catalogs omit Opus 5.5, GPT-6 Sol/Luna, Grok 4.7/4.6/4.5, current Gemini Flash models, and several Cursor/Kimi choices. Bedrock has obsolete IDs. The UI omits supported effort levels and saves Grok effort under a key the runtime does not read. **Proposed behavior** Offer verified current model IDs and model-specific efforts. Remove retired Gemini 2.0 choices. Keep configured defaults and saved model IDs. Keep runtime discovery for account-specific choices. **Reason and benefit** Catch up with provider releases through September 22, 2026. Correct the picker and runtime controls together. **Breaking changes** No database or API change. Gemini 2.0 options leave the picker after their June 1 shutdown. Existing saved IDs remain unchanged. Corrected Bedrock catalog IDs do not rewrite saved configuration. **Additional context** Supersedes the separate GPT-6 Sol PR #13830. Fable 5.1 was already merged in #12730, and GPT-6 Astra in #12851. The Grok 4.6/4.5 proposal #11324 was closed and parked by its author. This change retains the default-sentinel fix from #12062. Related discovery proposals #13127 and #13565 do not supply these catalog and effort updates. Searches found no open PR for the additional model IDs. See [the dated audit](https://github.com/paperclipai/paperclip/blob/feat/claude-opus-5-5/doc/adapter-model-audit-2026-09-22.md) for exact scope, primary sources, runtime observations, and account-specific limits. This updates existing adapters and does not duplicate planned core work. ## What Changed - Add Opus 5.5 for direct Claude and Bedrock, with a Claude Code 2.1.280 gate. Correct and extend Bedrock model IDs. - Add GPT-6 Sol/Luna and Fast mode. Offer Ultra for Astra/Sol and GPT-5.6 Sol/Terra, and Max for both Luna generations. - Add Grok 4.7/4.6/4.5, expose supported Extra High effort, and save Grok edits under `reasoningEffort`. - Add Gemini Flash 3.8/3.7/3.6/3.5, Flash Lite 3.5/3.1, and 3 Flash Preview. Remove retired 2.0 choices. - Add the current documented Cursor fallback models, including Fable 5.1, Composer 2.5, and Muse Spark 1.3. - Refresh OpenCode fallback IDs used in remote environments from its installed provider registry. - Add Kimi K3 256K. Update the existing coding alias to K2.8 Preview and enable its CLI effort settings. - Use model-specific Claude/Grok efforts in creation and editing. Clear unsupported effort when switching models. - Add catalog, CLI/ACP forwarding, compatibility, and UI persistence coverage. Record the audit and sources. ## Verification - Latest head `6e63c9ef53b54ba869cd4fb431a8570bebe289f4`: 53 CI checks passed, 2 skipped. This includes full workspace typecheck, build, and all test shards. Greptile is 5/5 with zero unresolved threads. GitHub reports no merge conflicts. - 340 focused tests passed across adapter metadata, CLI/ACP arguments, Claude version checks, Kimi effort, Grok execution, server model discovery, and UI effort selection/persistence. - `pnpm --filter @paperclipai/adapter-claude-local --filter @paperclipai/adapter-codex-local --filter @paperclipai/adapter-grok-local --filter @paperclipai/adapter-gemini-local --filter @paperclipai/adapter-kimi-local --filter @paperclipai/adapter-cursor-local --filter @paperclipai/adapter-opencode-local typecheck` — passed. The same filters with `build` passed. - `pnpm check:token-gates` and `git diff --check` — passed. - Full workspace and UI typechecks were attempted locally. They stop on existing missing `three` dependencies in `packages/shared/src/cliplab`. - Full `pnpm test:run` and `pnpm build` were not run locally. Worktree creation exhausted disk space, so a clean dependency install is not feasible on this host. Focused checks reuse existing dependencies. CI supplies full workspace verification. - No provider inference was run. Account-specific runtime model lists were inspected where available. - Manual check: select the new models in agent setup and editing. Confirm Luna has Max but no Ultra, Grok 4.7 has Extra High, and Fable 5.1 has Extra High/Max. Save Grok effort and confirm `adapterConfig.reasoningEffort` contains the selection. ## Risks - Catalog presence does not grant account access. Older CLIs and restricted accounts can reject a model. Opus 5.5 has an explicit upgrade check. - Higher effort can increase cost and latency. Existing agent defaults are unchanged. - Cursor fallback IDs come from public model documentation; the local account exposed no live catalog. Runtime discovery still adds account-specific variants. - Kimi effort remains supported only on its explicit CLI engine. This does not add effort support to its default ACP engine. - Saved obsolete Bedrock or retired Gemini IDs are not migrated automatically. ## Model Used OpenAI GPT-6 through Codex, with reasoning, tool use, and code execution. The exact deployment ID and context window are not exposed to this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
6.1 KiB
6.1 KiB
Adapter model audit: September 22, 2026
This audit covers model selection in the existing coding-agent adapters. Catalog entries identify models; provider accounts and installed CLIs determine access. No agent defaults or saved model selections are migrated.
| Adapter | Changes from the audit |
|---|---|
| Claude Code | Add Opus 5.5 and require CLI 2.1.280. Fable 5.1, Fable 5, Sonnet 5, and Mythos 5 were already listed. Expose the documented model-specific effort levels in creation and editing. |
| Claude on Bedrock | Add Opus 5.5, Opus 5, Sonnet 5, Opus 4.7, and Sonnet 4.6. Correct the obsolete -v1 suffix on Opus 4.8 and Fable 5. Apply the Opus 5.5 version check to Bedrock IDs too. |
| Codex and the Codex runner catalog | Add GPT-6 Sol and Luna, including Fast mode. Astra was already listed. Expose efforts through Ultra for Astra, Sol, and GPT-5.6 Sol/Terra; cap both Luna generations at Max. |
| Grok Build | Add Grok 4.7, 4.6, and 4.5. Offer Extra High for 4.7/4.6. Save edited effort as reasoningEffort, which the runtime consumes. Keep grok-build as the sentinel that lets the CLI choose its default. |
| Gemini CLI | Add Flash 3.8, 3.7, 3.6, 3.5, Flash Lite 3.5/3.1, and 3 Flash Preview. Remove the retired Gemini 2.0 choices. Keep Auto and the existing 3.1 Pro and 2.5 choices. |
| Cursor | Add the current documented fallback IDs for Composer 2.5, Opus 5.5, Fable 5.1, Sonnet 5, GPT-5.6 Sol/Terra/Luna, Gemini 3.8 Flash, Muse Spark 1.3, and Grok 4.7/4.6/4.5. Runtime model discovery remains available. |
| OpenCode | Refresh the static fallback used by remote environments with GPT-6 and GPT-5.6 families, current Claude models, Gemini 3.8 Flash, and Grok 4.7. |
| Kimi Code | Add K3 256K. Relabel kimi-for-coding as K2.8 Preview, which replaced K2.7 under the same ID. Forward CLI effort for K2.8 Preview and both K3 variants. |
Sources and verification
- Claude Code model configuration documents the Opus 5.5 CLI requirement and supported efforts. Opus 5.5 specifications and model ID conventions supply direct and Bedrock IDs. Bedrock entries use the catalog's existing US inference-profile convention; regional availability remains account-dependent.
- OpenAI's Codex model guide lists GPT-6 Sol and Luna. The installed Codex model metadata independently lists Astra, Sol, Luna, and all three GPT-5.6 variants with the effort sets used here. GPT-6 Luna specifications also document Fast pricing. Codex's Ultra setting is a CLI capability; it is not inferred from the API's effort enum.
- Grok 4.7 and
Grok 4.6 document their IDs and
four effort levels. The installed
grok modelscommand had no authenticated account and returned only its default sentinel. No inference was run. - Google's model catalog supplies the new Gemini IDs. The retirement schedule records Gemini 2.0 shutdown on June 1, 2026. Gemini 2.5 remains available to existing users. Gemini CLI model selection accepts an explicit model; login method and entitlement determine availability.
- Cursor's catalog links each
model's exact ID.
cursor-agent --list-modelsreturned no models for the local account, so the additions use documented IDs rather than guessed variant suffixes. Account-specific Fast/thinking variants remain discoverable. - Kimi's model configuration documents all four current IDs, K2.8's in-place alias upgrade, and effort support. Kimi effort remains limited to the existing explicit CLI engine; the default ACP engine's effort mapping is outside this catalog update.
Other adapters and restricted models
OpenCode discovers local models, but remote environment routes use its static
fallback catalog. All twelve added provider-qualified IDs were also present in
the installed OpenCode registry. OpenCode model configuration
documents its provider/model format and provider registry.
Pi already discovers models from its runtime or provider registry. Hermes and OpenClaw accept provider configuration without a curated model list. Cursor Cloud obtains its account's model list from Cursor. These paths do not need a static entry per upstream release. Local OpenCode discovery returned current models, including Muse Spark 1.3 and Nemotron 3.5 Lightning.
Anthropic describes Mythos 5.1 as invitation-only in the Fable 5.1 documentation. The public current-model catalog does not publish a selectable ID for it. Keep account discovery and custom IDs available instead of inventing an ID. Grok 4.7 Fast is available in Grok Build and Cursor, but its exact account-specific CLI variant ID was not exposed locally. It is not a public xAI API model. Image, video, audio, and embedding models are outside these coding-agent pickers.
Prior work checked
Fable 5.1 was already merged in #12730. Astra was already merged in #12851. The Grok 4.6/4.5 proposal #11324 was closed and parked by its author. This update preserves the newer CLI-default sentinel behavior from #12062. Open model-discovery work such as #13127 and #13565 is separate from these catalog and effort corrections. No open PR covering the newly added IDs was found before implementation.