chore(deps): Bump strands-agents from 1.50.2 to 1.51.0

[dependabot]

Bumps strands-agents from 1.50.2 to 1.51.0.

Release notes

Sourced from strands-agents's releases.

python/v1.51.0

Auto-drafted from commits in python/v1.50.2..python/v1.51.0, grouped by conventional-commit type. Edit on the release page after publish if you want a polished writeup; the canonical release notes live on the website.

🚀 Features

• feat(middleware): add AgentStreamStage and AgentStreamContext types (#3635) (38980ed4f)
• feat(storage-ts): accept storage as optional top-level Agent parameter (#3660) (dcf09bb93)
• feat(model): add estimateUtilization method to Model base class (#3641) (c84b618a3)
• feat(docs): add hitl classifier documentation (#3630) (86980c497)
• feat: add snapshot session manager to python (#3283) (a059fb91b)
• feat(ts): detect repetitive swarm handoffs (#3461) (a92cb5e01)
• feat(site): community integration catalog with search, filtering, and curated backfill (#3416) (2f907793a)
• feat(hitl-py): add classifier option for LLM-driven risk classification (#3575) (69ed9f320)
• feat: support Tool Choice for Gemini in Python (#3551) (0ab31d7c1)
• feat: add context window limits for Claude 5 and GPT-5.6 families (#3629) (c93666c64)
• feat(context-offloader): add should_offload callback for selective offloading (#3267) (6a925de6c)
• feat(ts): add MCP tool filtering and name prefixes (#3415) (bf94c6701)
• feat(multiagent): add str support for MultiAgentResult and NodeResult (#1998) (8b1f53724)
• feat(interventions-ts): add llm as judge tool risk classifier to hitl (#3566) (55c68b7a5)
• feat(bidi): add telemetry and metrics (#3282) (c0776c008)
• feat(python): add BeforeToolsEvent and AfterToolsEvent batch hooks (#3508) (fd1b985b1)
• feat(a2a): support the interrupt round trip over A2A (#3486) (aae087d6d)

🐛 Fixes

• fix(ci): label fork PRs by verifying the artifact's claim against the PR head (#3705) (d8d366cd8)
• fix(mantel):mantle base path routing (#3691) (7766a2397)
• fix(catalog): point strands-stigmer docsUrl at stigmer.network (#3668) (c9f19f641)
• fix(site): reject redundant languages in astro frontmatter (#3678) (1fe9bb3f1)
• fix(swarm): correct crash-restart resume for handoff and completed swarms (#3391) (7741ecd28)
• fix(bedrock-kb): resolve a default region for the store's clients so it works in cloud envs (#3583) (56cc3d3bd)
• fix(mcp): index document content on hydration with thread safety (#3502) (6c1e56c6c)
• fix(telemetry): record gen_ai.tool.call.arguments/result on execute_tool spans (#3550) (cd98383d9)
• fix: preserve interrupt state across cancelled resumes and middleware re-reads (#3615) (587efb391)
• fix(python): count usage from hook-retried model calls (#3627) (762253c76)
• fix(bedrock): skip guardContent wrap for unsupported image formats (#3607) (527ad68a4)
• fix(session): validate snapshot scope (#3593) (b070786e7)
• fix(ci): exclude bootstrap tools from MCP audit (#3565) (a8ead9484)
• fix(mcp): pin mcp dependency below v2.0.0 (#3524) (8e6b33f4b)
• fix(context-offloader): refresh eviction cycle on retrieve for unified Storage backends (#3487) (b3643bedf)

⚡ Performance

• perf(mcp): hydrate search snippets concurrently (#3435) (fe4cbb948)

♻️ Refactoring

• refactor(vended-tools): mark make_bash with typing_extensions.deprecated (#3595) (3cddf74ff)
• refactor(vended-tools)!: rename sandbox-routed bash tool to shell (#3574) (d50de52db)

... (truncated)

Commits

• f766cd6 docs(labs): remove archived robots-sim, add four active Labs projects (#3694)
• d8d366c fix(ci): label fork PRs by verifying the artifact's claim against the PR head...
• 7766a23 fix(mantel):mantle base path routing (#3691)
• c9f19f6 fix(catalog): point strands-stigmer docsUrl at stigmer.network (#3668)
• 734a259 docs: extend the comment rule to require to-the-point, non-inferable content ...
• 38980ed feat(middleware): add AgentStreamStage and AgentStreamContext types (#3635)
• 1fe9bb3 fix(site): reject redundant languages in astro frontmatter (#3678)
• d7b36d0 test(mcp): wait for the retained task, not the log line (#3537)
• 77c0eb5 ci: label PRs by cognitive complexity, stop counting tests toward size (#3634)
• 7741ecd fix(swarm): correct crash-restart resume for handoff and completed swarms (#3...
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 83.15%. Comparing base (e4ad181) to head (e73b0d5).

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #1195   +/-   ##
=======================================
  Coverage   83.15%   83.15%           
=======================================
  Files         123      123           
  Lines       10260    10260           
=======================================
  Hits         8532     8532           
  Misses       1728     1728           

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.