feat(provider): add 1M context window support for Anthropic models#14375
Open
DusKing1 wants to merge 1 commit intoanomalyco:devfrom
Open
feat(provider): add 1M context window support for Anthropic models#14375DusKing1 wants to merge 1 commit intoanomalyco:devfrom
DusKing1 wants to merge 1 commit intoanomalyco:devfrom
Conversation
github-actions
bot
added
the
needs:compliance
Contributor
|
The following comment was made by an LLM, it may be inaccurate: Based on my search, I found one related PR: PR #12342: "feat(provider): add adaptive thinking and 1M context support for Claude Opus 4.6" This PR is related because it addresses the same feature (1M context window support for Anthropic models, specifically Claude Opus 4.6). According to the current PR description, PR #14375 is "a minimal alternative to #12342 — no AI SDK version upgrade required," indicating these PRs take different approaches to solving the same problem. |
github-actions
bot
removed
the
needs:compliance
Contributor
|
Thanks for updating your PR! It now meets our contributing guidelines. 👍 |
Contributor
|
+1 on this one, a bit annoying to have opencode keep hitting 200k limit thinking its at 20% of the context rn 😓 |
|
any plans to merge this? |
This was referenced Feb 28, 2026
Add context-1m-2025-08-07 beta header for Anthropic provider, enabling 1M token context window for Claude Opus 4.6, Sonnet 4.6, Sonnet 4.5, and Sonnet 4.0. Override context limit from 200K to 1M for supported models so compaction triggers at the correct threshold instead of prematurely at 200K. Fix compaction token counting: when model.limit.input is set, only count input tokens (not output/thinking) against the input limit. Output tokens do not consume the input context window.
DusKing1
force-pushed
the
feat/1m-context-support
branch
from
5103e1e to
d471249
Compare
6 tasks
vbuccigrossi
pushed a commit
to vbuccigrossi/opencode
that referenced
this pull request
Mar 7, 2026
Tier 1 bug fixes: - Fix O(n²) bash output concatenation with StreamingOutput class (anomalyco#9693) - Fix memory leaks in Bus.once, Format, Plugin, ShareNext, Bootstrap (anomalyco#13514) - Fix FileTime race condition using actual file mtime instead of JS clock - Free memory on compaction prune: clear output/attachments/metadata (anomalyco#7049) - Throttle reasoning-delta storage writes to 50ms intervals (anomalyco#11328) - Handle SIGHUP/SIGTERM to prevent orphaned processes (anomalyco#12718) - Add process.once("close") handler for bash tool reliability Tier 2 features: - Support 1M context window for Anthropic models via beta header (anomalyco#14375) - Input-only token counting for compaction with limit.input models - MCP lazy loading: on-demand tool discovery via mcp_search tool (anomalyco#8771) - MCP servers listed in system prompt when lazy mode enabled - StreamingOutput: output_filter regex for build diagnostics - LSP server cleanup callback for temp directory removal - Extract formatSize utility from uninstall to shared util/format - GitHub CI: fix Bus subscription leak in session event handler Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Issue for this PR
Closes #12323
Type of change
What does this PR do?
Enables the 1M token context window for Anthropic models that support it (Opus 4.6, Sonnet 4.6, Sonnet 4.5, Sonnet 4.0).
Three changes:
Beta header (
provider.ts): Appendscontext-1m-2025-08-07to theanthropic-betaheader. This is the only thing the Anthropic API requires to unlock 1M context.Context limit override (
provider.ts): models.dev currently reportscontext: 200000for these models, which causes compaction to trigger at ~168K tokens. The code now detects 1M-capable models by API ID pattern and overrideslimit.contextto1_000_000. Guarded by< 1_000_000so it becomes a no-op once models.dev updates.Compaction fix (
compaction.ts): Whenmodel.limit.inputis set, the overflow check now counts only input tokens instead of total tokens. Output/thinking tokens don't consume the input context window.This is a minimal alternative to #12342 — same 1M result without the AI SDK v5-v6 upgrade.
How did you verify your code works?
Checklist