From cbf8466e8efbdb3c86ae7c05d8657480ca698917 Mon Sep 17 00:00:00 2001 From: rajkumarsakthivel Date: Fri, 15 May 2026 20:56:53 +0100 Subject: [PATCH] docs: update landing page and add v0.4.20 release blog post Update index.html with agent-neutral wording and add blog post covering --agent flag, input/output savings split, and upgrade fix. --- docs/blog/v0-4-20-multi-agent-savings.html | 161 +++++++++++++++++++++ docs/index.html | 9 +- 2 files changed, 168 insertions(+), 2 deletions(-) create mode 100644 docs/blog/v0-4-20-multi-agent-savings.html diff --git a/docs/blog/v0-4-20-multi-agent-savings.html b/docs/blog/v0-4-20-multi-agent-savings.html new file mode 100644 index 0000000..1d0558c --- /dev/null +++ b/docs/blog/v0-4-20-multi-agent-savings.html @@ -0,0 +1,161 @@ + + + + + + v0.4.20: Multi-Agent Targeting and Input/Output Savings Split + + + + + + + + + + + + + +
+
May 15, 2026 · 4 min read
+

v0.4.20: Multi-Agent Targeting and Input/Output Savings Split

+

Target specific AI coding agents with --agent, see accurate cost savings split by input and output tokens, and get reliable upgrade version detection.

+ +

Target the agent you actually use

+

cce init has always auto-detected your editor. That works well when you have Claude Code installed. But if you only use Codex, or only use Copilot, auto-detection could miss your setup or write config files you don't need.

+

Now you can be explicit:

+ +
cce init --agent codex      # Codex only: ~/.codex/config.toml + AGENTS.md
+cce init --agent copilot    # VS Code only: .vscode/mcp.json + .github/copilot-instructions.md
+cce init --agent claude     # Claude only: .mcp.json + CLAUDE.md
+cce init --agent all        # Every supported editor
+cce init                    # Auto-detect (same as before)
+ +

Each flag writes exactly what that agent needs. No surprise edits to files belonging to other editors.

+ +

What gets written

+ + + + + + + + + + +
FlagMCP configInstruction file
--agent claude.mcp.jsonCLAUDE.md
--agent codex~/.codex/config.tomlAGENTS.md
--agent copilot.vscode/mcp.json.github/copilot-instructions.md
--agent allAll of the above + Cursor, Gemini, OpenCode, TabnineAll instruction files
+ +

--agent all is computed from the editor registry at runtime. When new editors are added to CCE, all picks them up automatically.

+ +

Input and output savings, split correctly

+

Before this release, cce savings priced everything at the input token rate. That was wrong. Output tokens cost 5x more than input tokens on Opus ($75/1M vs $15/1M). A small output savings is worth more in dollars than a large input savings.

+ +

The savings report now splits these correctly:

+ +
  Input savings   8.6k  tokens   $0.13
+  Output savings  325  tokens   $0.02
+  ──────────────────────────────────────────
+  Total saved   8.9k  tokens   $0.15
+  ~4.5k tokens / query  ~$0.08 / query
+
+  Breakdown:
+    retrieval              48%  ▰▰▰▰▰▰▰▰▰▰    6.0k    $0.09 · 1 call
+    chunk compression      20%  ▰▰▰▰▱▱▱▱▱▱    2.6k    $0.04 · 1 call
+    output compression*     2%  ▰▱▱▱▱▱▱▱▱▱     325    $0.02 · 1 call
+
+  Cost estimate based on Opus pricing (input $15/1M, output $75/1M)
+ +

The pricing module now fetches both input and output rates from the Anthropic docs page. Old cache files from previous versions are migrated automatically.

+ +

Upgrade version detection fix

+

cce upgrade had a bug where it always reported "Already on latest version" even after a successful upgrade. The running process couldn't see the new version metadata because uv tool upgrade installs into a separate virtual environment.

+

The fix: after upgrading, CCE shells out to the upgraded binary with --version to read the real post-upgrade version. Simple, reliable.

+ +

Upgrade

+ +
cce upgrade
+ +

Or manually:

+ +
uv tool upgrade code-context-engine
+ +
+

Existing projects: Run cce init --agent all if you want to add instruction files for Codex and Copilot. Your existing CLAUDE.md and .mcp.json will be preserved.

+
+ +

Full changelog

+ + +
+

Get started

+

Install CCE and start saving tokens in under a minute.

+ GitHub → +
+ +
+ release + v0.4.20 + multi-agent + token-savings + codex + copilot +
+
+ + + diff --git a/docs/index.html b/docs/index.html index 979b3b4..5d1f2ce 100644 --- a/docs/index.html +++ b/docs/index.html @@ -962,7 +962,7 @@

Index once.
Save 94%.

  ✓ Indexed 1,247 chunks from 89 files   - Done! Restart Claude Code to activate CCE. + Done! Restart your AI coding agent to activate CCE. @@ -1247,6 +1247,11 @@

How CCE stacks up

Deep dives

+ +
May 15, 2026 · 4 min read
+
v0.4.20: Multi-Agent Targeting and Input/Output Savings Split
+
New --agent flag for cce init, accurate cost tracking with separate input and output token pricing, and upgrade detection fix.
+
May 5, 2026 · 8 min read
What is Code Context Engine? Complete Guide
@@ -1298,7 +1303,7 @@

Stop paying to
re-read code.

→
2 cce init
→ -
3 Restart Claude Code
+
3 Restart editor
→
✓ Saving tokens