v0.0.9

What's Changed

• feat: tencent docs by @bgdnvk in #183
• fix: sre agents by @bgdnvk in #178
• feat(mcp): expose Tencent tools over MCP by @rephapeng in #182
• feat(sentry): full Sentry.io integration by @rafeegnash in #184
• feat(linear): first-class Linear integration (PR 1/4) by @rafeegnash in #185
• feat(notion): CLI integration — REST client, ask agent, MCP tools by @rafeegnash in #186
• fix(hermes): runner concurrency + bridge restart in talk by @rafeegnash in #187
• fix(security): tighten conversation-history file perms to 0600 by @rafeegnash in #188
• fix(security): allowlist-sanitize history-file identifiers via SafeSlug by @rafeegnash in #189
• fix/clanker sre deployment by @bgdnvk in #190
• feat: new logo by @bgdnvk in #191
• feat: optimize inference feedback by @bgdnvk in #192
• feat: add Terraform adoption analysis by @bgdnvk in #193
• feat: expand cloud provider coverage by @bgdnvk in #196
• Add Clanker Cloud LLM provider by @bgdnvk in #200
• Fix Clanker Cloud LLM auth header by @bgdnvk in #201
• feat: add onboarding CLI dependency setup by @bgdnvk in #199
• Improve Clanker Cloud agent MCP flows by @bgdnvk in #202
• feat: add observability agent by @bgdnvk in #203
• feat: add Clanker Box runtime by @bgdnvk in #205
• Stream Clanker Cloud LLM responses by @bgdnvk in #206
• Add model override for k8s ask by @bgdnvk in #210
• Expose Kubernetes cluster chat over MCP by @bgdnvk in #211
• Unified multi-provider logs command (query/tail/chat) by @rafeegnash in #212
• Improve security scan coverage by @bgdnvk in #215
• Fix: k8s logs across all namespaces + tolerate not-ready pods by @rafeegnash in #216
• Improve deep research system analysis by @bgdnvk in #213
• Logs: count-based 'last N' tail mode (--tail) by @rafeegnash in #217
• Logs: add GCP, Azure, Cloudflare, DigitalOcean collectors by @rafeegnash in #218
• Fix GCP logs (live-verified): env resolution, sources parsing, message fallback by @rafeegnash in #219
• Harden GCP/Azure/Cloudflare/DigitalOcean log collectors (review fixes) by @rafeegnash in #220
• Annotate SRE heartbeats for Cerebro by @bgdnvk in #214
• Logs poll/dedup edge-case fixes (review round) by @rafeegnash in #221
• feat: add live SRE check by @bgdnvk in #222
• logs: make process-group handling cross-platform (fix Windows build) by @rafeegnash in #223
• fix(aws): don't panic on missing optional cluster_name in ECS log tools by @rafeegnash in #237
• fix(k8s): data race + premature output read in runCommandStreaming by @rafeegnash in #238

Full Changelog: v0.0.8...v0.0.9

v0.0.8

What's Changed

• feat(tencent): add Tencent Cloud provider by @rephapeng in #165
• fix(ci): apply gofmt -s across the tree by @rafeegnash in #176
• fix: sre agent by @bgdnvk in #177
• feat(tencent): add --format json to clanker tencent list <type> by @rafeegnash in #179
• feat(tencent): add --format json to cost by-product and cost top by @rafeegnash in #180
• feat(tencent/security): expose 10 scans as cobra subcommands by @rafeegnash in #181

New Contributors

• @rephapeng made their first contribution in #165

Full Changelog: v0.0.7...v0.0.8

v0.0.7

What's Changed

• fix: release tag by @bgdnvk in #145
• fix/readme versions by @bgdnvk in #146
• feat/more aws by @bgdnvk in #147
• feat: overview agents by @bgdnvk in #149
• feat: cost & k8s phase 1 — anomaly detection, tag audit, networkpolicy audit, resourcedb logging by @rafeegnash in #150
• feat(k8s): Phase 3 — autoscaler validate + storage audit + Phase 2 review fixes by @rafeegnash in #151
• feat(k8s): Phase 4 — workload cost attribution + health audit by @rafeegnash in #152
• feat(k8s): Phase 5 — Karpenter advisor + recommendations by @rafeegnash in #153
• feat(cost): Phase 6 — Savings Plans + RI recommendations by @rafeegnash in #154
• feat(cost): Phase 7 — clanker maker estimate (pre-flight plan cost) by @rafeegnash in #155
• fix(cost): pass full AWS service names to GetReservationPurchaseRecommendation by @rafeegnash in #156
• [codex] add self update command by @masonjames in #157
• feat(scan): clanker scan command with coloured receipt + maker plan export by @rafeegnash in #160
• feat(flyio): first-class Fly.io provider integration by @rafeegnash in #161
• feat: sre by @bgdnvk in #162
• feat: mcp by @bgdnvk in #164
• fix(router): three CLI routing false-positives — schema/index, k8s overlap, CICD vs deployment by @rafeegnash in #166
• feat: agent-cc by @bgdnvk in #167
• feat(k8s): expose scale/restart/rollout/rm CLI subcommands by @rafeegnash in #168
• feat(k8s): expose helm release-management CLI subcommands by @rafeegnash in #169
• feat(k8s): expose apply/exec/port-forward + node lifecycle CLI by @rafeegnash in #170
• feat(k8s): add 'clanker k8s create aks' subcommand by @rafeegnash in #171
• feat(mcp): native Kubernetes tools (16 verbs) by @rafeegnash in #172
• feat(k8s): configurable per-cluster conversation history cap by @rafeegnash in #173
• feat(k8s/sre/4a): playbook framework + crashloop-recovery + CLI fix subcommand by @rafeegnash in #174
• fix: updating readme by @bgdnvk in #175

Full Changelog: v0.0.6...v0.0.7

v0.0.6

feat: Railway provider support (#144)

* add Railway CLI client, types, and conversation history

Adds the internal/railway package with a GraphQL client against Railway's
Backboard v2 endpoint, strongly-typed models covering the full
Workspace->Project->Environment->Service->Deployment hierarchy, and a
per-workspace conversation history store with atomic persistence.

* railway: add backend credential types and client methods

Adds RailwayCredentials struct, ProviderRailway constant, and
StoreRailwayCredentials / GetRailwayCredentials on the backend client so
the credentials subcommand can round-trip Railway account tokens
through the clanker backend like the other providers.

* railway: wire credentials store, test, and delete into credentials command

storeRailwayCredentials resolves the account token from flags, config,
or RAILWAY_API_TOKEN and persists via the backend client.
testRailwayCredentials verifies the token by POSTing a minimal
GraphQL me query to backboard.railway.com/graphql/v2 and decoding
the response envelope (honouring Railway's 200-with-errors shape).

* railway: add routing keywords and LLM classifier branch

Adds Railway to ServiceContext, registers railway-specific keywords
(railway, railway.app, railway project/service/deployment/volume/
environment/plugin, nixpacks, railway.json/.toml), triggers LLM
classification when Railway is inferred, and clears other cloud
flags when classification lands on railway.

* railway: wire ask pipeline, MCP tools, and phase-1 subcommand

Adds --railway flag and the handleRailwayQuery path (mirrors Vercel):
resolve token -> create client -> fetch context -> load per-workspace
conversation history -> build system prompt -> dispatch to configured
AI provider -> persist exchange. Registers clanker_railway_ask /
clanker_railway_list MCP tools covering projects, services,
deployments, domains, variables, volumes, and workspaces. Registers
the railway cobra tree and the phase-1 railway ask stub so the
subcommand is discoverable alongside vercel.

* railway: register --railway flag on ask command and update help text

The --railway flag was read via cmd.Flags().GetBool but never registered
with Flags().Bool, so `clanker ask --railway ...` surfaced as an unknown
flag instead of routing to handleRailwayQuery. Also threads Railway
through the credentials-subcommand long descriptions so help output
lists it alongside the other providers.

* railway: wire into maker mode (prompt, provider inference, plan execution)

Adds the --railway branch to --maker mode explicit provider routing,
keyword-based provider inference, LLM classification prompt, plan
prompt dispatcher (RailwayPlanPromptWithMode), and plan execution
dispatcher (ExecuteRailwayPlan). Without these glue points the
maker pipeline could not emit or apply Railway plans even though
exec_railway.go and railway_prompts.go were already in place.

* railway: fall back to backend credentials store in resolveRailwayToken

* railway: route maker plans through the non-AWS direct-output branch

* railway: read railway.json and railway.toml during repo exploration

* railway: honour context cancellation during GraphQL retry sleeps

* railway: surface GetUsage decode errors to callers

* railway: release conversation mutex during disk i/o

* railway: block backtick and $(...) in maker command validation

* railway: batch GetRelevantContext fetches and drop redundant GetProject

* railway: thread includeRailway through applyDiscoveryContextDefaults

* railway: remove placeholder ask subcommand stubs

* railway: add set/add alias for variable subcommand

* railway: document GraphQL retry budget matches Vercel client

* railway: extend applyDiscoveryContextDefaults tests with railway case

---------

Co-authored-by: nash <nash@clankercloud.ai>

v0.0.3

What's Changed

• feat: add Linux cross-platform support and CI workflow by @rafeegnash in #16
• fix: aws cli os support by @bgdnvk in #17
• Feature/k8s cli support by @rafeegnash in #19
• fix(k8s): handle eks commands in K8s plan executor by @rafeegnash in #21
• feat: gcp support by @bgdnvk in #22
• feat: terraform support by @bgdnvk in #23
• feat(k8s): add k8s ask command for natural language cluster queries by @rafeegnash in #25
• feat(cloudflare): add Cloudflare agent with LLM-based routing by @rafeegnash in #27
• feat(cloudflare): add Cloudflare agent with DNS subagent by @rafeegnash in #26
• feat: integrate backend credential management by @rafeegnash in #29
• feat: Azure support with backend integration by @rafeegnash in #30
• feat(k8s): add GKE and AKS support with feature parity to EKS by @rafeegnash in #48
• feat(k8s/cluster): implement AKS cluster provider by @rafeegnash in #77
• test(k8s/plan): add comprehensive test coverage for plan package by @rafeegnash in #78
• test(k8s): add test coverage for client package by @rafeegnash in #79
• feat(k8s/cluster): add errorHint method to EKS provider by @rafeegnash in #80
• feat(k8s/cluster): standardize timeout configuration across providers by @rafeegnash in #82
• refactor(k8s): extract client adapters to separate file by @rafeegnash in #83
• refactor(k8s/cluster): extract common provider utilities by @rafeegnash in #84
• chore(k8s/cluster): add debug logging convention and helper by @rafeegnash in #85
• feat(k8s/cluster): add security best practices documentation by @rafeegnash in #86
• feat(k8s/cluster): add retry logic with exponential backoff to EKS provider by @rafeegnash in #81
• feat: deployer by @bgdnvk in #32
• feat(iam): add IAM agent with LLM-based routing by @rafeegnash in #88
• feat(iam): add IAM agent for security analysis and remediation by @rafeegnash in #87
• feat: anthropic support by @bgdnvk in #89
• feat: wordpress deploy by @bgdnvk in #90
• feat: add config scan command for credential detection by @rafeegnash in #92
• feat: plan retry by @bgdnvk in #93
• feat: Add DeepSeek and MiniMax LLM provider support by @rafeegnash in #99
• feat: Add cost command for cloud cost analysis by @rafeegnash in #100
• feat: Add Cloudflare deployment CLI commands by @rafeegnash in #101
• feat: repairing plan by @bgdnvk in #94
• fix: wp and openclaw deployments by @bgdnvk in #102
• fix: autofix plan and openclaw better checks for dupe commands by @bgdnvk in #103

New Contributors

• @rafeegnash made their first contribution in #16

Full Changelog: v0.0.2...v0.0.3

v0.0.2

releases

v0.0.1-meet-your-maker

What's Changed

• maker by @bgdnvk in #10

Full Changelog: v3_alpha...v0.0.1-meet-your-maker

v3_alpha

What's Changed

• openai-key-default by @bgdnvk in #7
• chore: simplifying code and readme by @bgdnvk in #8

Full Changelog: v2_alpha...v3_alpha

v2_alpha

What's Changed

• feat: discover, compliance flags and more aws services by @bgdnvk in #1
• fix: limit the amount of default aws calls in parallel by @bgdnvk in #2
• feat: aws agent by @bgdnvk in #3
• log fixed and openapi n anthropic override flags by @bgdnvk in #4
• refactor for alpha v2 by @bgdnvk in #5
• feat/gemini support by @bgdnvk in #6

New Contributors

• @bgdnvk made their first contribution in #1

Full Changelog: alpha...v2_alpha

0.0.1

CLANKER